Update README.md

CJK Symbols and Punctuation range u3000 > u303F

.github/FUNDING.yml

@@ -0,0 +1 @@
+ko_fi: erew123

.github/workflows/publish-docker.yml

@@ -0,0 +1,67 @@
+name: Publish Docker image
+
+on:
+  push:
+    branches: [main]
+  release:
+    types: [published]
+  workflow_dispatch:
+
+jobs:
+  build_and_push:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        include:
+          - dockerfile: "Dockerfile"
+            platforms: "linux/amd64"
+            tag_name: "cpu"
+          - dockerfile: "nvidia.Dockerfile"
+            platforms: "linux/amd64"
+            tag_name: "cuda"
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Lowercase Actor and Extract Repo Name
+        run: |
+          echo "ACTOR_LOWER=$(echo ${{ github.actor }} | tr '[:upper:]' '[:lower:]')" >> $GITHUB_ENV
+          echo "REPO_NAME=$(echo ${{ github.repository }} | cut -d'/' -f 2)" >> $GITHUB_ENV
+
+      - name: Login to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ env.ACTOR_LOWER }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Login to DockerHub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ vars.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          file: ./${{ matrix.dockerfile }}
+          platforms: ${{ matrix.platforms }}
+          push: true
+          tags: |
+            ghcr.io/${{ env.ACTOR_LOWER }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}-${{ github.sha }}
+            ghcr.io/${{ env.ACTOR_LOWER }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}
+            ghcr.io/${{ env.ACTOR_LOWER }}/${{ env.REPO_NAME }}:latest
+            ${{ vars.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}-${{ github.sha }}
+            ${{ vars.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}:${{ matrix.tag_name }}
+            ${{ vars.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}:latest
+
+      - name: Docker Hub Description
+        uses: peter-evans/dockerhub-description@v3.4.2
+        with:
+          username: ${{ vars.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+          repository: ${{ vars.DOCKERHUB_USERNAME }}/${{ env.REPO_NAME }}

Dockerfile

@@ -0,0 +1,12 @@
+FROM ubuntu:22.04
+ENV HOST 0.0.0.0
+RUN apt-get update && apt-get upgrade -y \
+    && apt-get install -y git build-essential portaudio19-dev \
+    python3 python3-pip gcc wget \
+    && ln -s /usr/bin/python3 /usr/bin/python
+WORKDIR /app
+COPY . .
+RUN pip install --no-cache-dir -r requirements_other.txt
+EXPOSE 7851
+RUN chmod +x launch.sh
+ENTRYPOINT ["sh", "-c", "./launch.sh"]

README.md

@@ -1,40 +1,91 @@
 # AllTalk TTS
 AllTalk is an updated version of the Coqui_tts extension for Text Generation web UI. Features include:
 
-- **Can be run as a** [standalone](https://github.com/erew123/alltalk_tts?#-running-alltalk-as-a-standalone-app) **or part of** [Text-generation-webui](https://github.com/erew123/alltalk_tts?#-installation-on-text-generation-web-ui)
+- **Can be run as a** [standalone](https://github.com/erew123/alltalk_tts/#-quick-setup-text-generation-webui--standalone-installation) **or part of** [Text-generation-webui](https://github.com/erew123/alltalk_tts/#-quick-setup-text-generation-webui--standalone-installation) **using the a quick setup utility**
 - **Model Finetuning:** Train the model specifically on a voice of your choosing for better reproduction.
 - **Local/Custom models:** Use any of the XTTSv2 models (API Local and XTTSv2 Local).
-- **Bulk TTS Generator/Editor:** Generate hours of TTS into one big file or have something read back to you.
+- **Bulk TTS Generator/Editor:** Generate hours of TTS into one big file or have something read back to you [demo](https://www.youtube.com/watch?v=hunvXn0mLzc).
-- **DeepSpeed:** A 3-4x performance boost generating TTS. [DeepSpeed Windows/Linux Instructions](https://github.com/erew123/alltalk_tts?tab=readme-ov-file#deepspeed-installation-options) [Screenshot](https://github.com/erew123/alltalk_tts/assets/35898566/548619c8-5f1b-47d0-a73d-54d2fee3f3db)
+- **DeepSpeed:** A 2-3x performance boost generating TTS. [Screenshot](https://github.com/erew123/screenshots/raw/main/deepspeed.jpg)
-- **Low VRAM mode:** Great for people with small GPU memory or if your VRAM is filled by your LLM. [Screenshot](https://github.com/erew123/alltalk_tts#screenshots)
+- **Low VRAM mode:** Great for people with small GPU memory or if your VRAM is filled by your LLM.
-- **Custom Start-up Settings:** Adjust your default start-up settings. [Screenshot](https://github.com/erew123/alltalk_tts#screenshots)
+- **Custom Start-up Settings:** Adjust your default start-up settings. [Screenshot](https://github.com/erew123/screenshots/raw/main/settingsanddocs.jpg)
 - **Narrarator:** Use different voices for main character and narration. [Example Narration](https://vocaroo.com/18nrv7FR6wuA)
-- **Optional wav file maintenance:** Configurable deletion of old output wav files. [Screenshot](https://github.com/erew123/alltalk_tts#screenshots)
+- **Optional wav file maintenance:** Configurable deletion of old output wav files. [Screenshot](https://github.com/erew123/screenshots/raw/main/settingsanddocs.jpg)
-- **Documentation:** Fully documented with a built in webpage. [Screenshot](https://github.com/erew123/alltalk_tts#screenshots)
+- **Documentation:** Fully documented with a built in webpage. [Screenshot](https://github.com/erew123/screenshots/raw/main/settingsanddocs.jpg)
-- **Console output:** Clear command line output for any warnings or issues.
+- **Clear Console output:** Clear command line output for any warnings or issues.
 - **API Suite and 3rd Party support via JSON calls:** Can be used with 3rd party applications via JSON calls.
+- **SillyTavern integration:** Full integration with SillyTavern. [Screenshot](https://github.com/erew123/screenshots/raw/main/sillytavern.jpg)
 
-## Index
+### Index
 
-- 🟩 [Installation](https://github.com/erew123/alltalk_tts?#-installation-on-text-generation-web-ui)
+- 🟩 [Installation](https://github.com/erew123/alltalk_tts/#-quick-setup-text-generation-webui--standalone-installation)
 - 🟪 [Updating & problems with updating](https://github.com/erew123/alltalk_tts?#-updating)
 - 🟫 [Screenshots](https://github.com/erew123/alltalk_tts#-screenshots)
 - 🟨 [Help with problems](https://github.com/erew123/alltalk_tts?#-help-with-problems)
 - ⚫ [Finetuning a model](https://github.com/erew123/alltalk_tts?#-finetuning-a-model)
 - 🔵🟢🟡 [DeepSpeed Installation (Windows & Linux)](https://github.com/erew123/alltalk_tts?#-deepspeed-installation-options)
-- 🟦 [Running AllTalk as a standalone app](https://github.com/erew123/alltalk_tts?#-running-alltalk-as-a-standalone-app)
 - ⬜ [AllTalk TTS Generator](https://github.com/erew123/alltalk_tts?#-alltalk-tts-generator)
 - 🟠 [API Suite and JSON-CURL](https://github.com/erew123/alltalk_tts?#-api-suite-and-json-curl)
 - 🔴 [Future to-do list & Upcoming updates](https://github.com/erew123/alltalk_tts?#-future-to-do-list)
 
-## 🔄 Updates
+### 🔄 Feature requests, Updates & Bug fixes
 Please check the below link to find a list of all recent updates and changes.
 ####     🔄 **Updates list & bug fixes list** can be found [here](https://github.com/erew123/alltalk_tts/issues/25)
+####     🔄 **Current Feature request list** can be found [here](https://github.com/erew123/alltalk_tts/discussions/74)
+
+I welcome your input and ideas for new features, suggestions, and improvements. Feel free to share your thoughts and collaborate in the discussions area. If you find this project valuable and would like to show your appreciation, you can make a donation on my [Ko-fi](https://ko-fi.com/erew123) page. Your support goes a long way in ensuring that I can continue to deliver even better features and experiences.
+
+**ERROR** `ImportError: cannot import name 'SampleOutput' from 'transformers.generation.utils'` please see this issue [here](https://github.com/erew123/alltalk_tts/issues/82)
+
+### 🟩 Quick Setup (Text-generation-webui & Standalone Installation)
+For Windows 10/11 and Linux machines there is a quick setup script. Please note, Python on Windows requires you install the C++ development [tools](https://wiki.python.org/moin/WindowsCompilers) to compile packages, further details can be found in the help section.
+
+Click to expand the correct section below:
+<details>
+	<summary>QUICK SETUP - Text-Generation-webui</summary><br>
+
+ If you wish to see this as a video, please go [here](https://www.youtube.com/watch?v=icn2XS5rUH8)
+1) To download the AllTalk setup you can either:
+   - A) Go to the [Releases page](https://github.com/erew123/alltalk_tts/releases) and download the latest `alltalk_tts.zip` then extract it to the text-generation-webui extensions folder<br>e.g. `\text-generation-webui\extensions\alltalk_tts\`.<br><br>
+   - B) Go to a terminal/console, move into the `\text-generation-webui\extensions\` folder<br>and `git clone https://github.com/erew123/alltalk_tts`<br><br>
+3) In a terminal/command prompt, in the text-generation-webui folder you will start its Python environment with either `cmd_windows.bat` or `./cmd_linux.sh`
+4) Move into the AllTalk folder e.g. `cd extensions` then `cd alltalk_tts`
+5) Start the AllTalk setup script `atsetup.bat` or `./atsetup.sh`
+6) Follow the on-screen prompts and install the correct requirements files that you need. It's recommended to test AllTalk works before installing DeepSpeed.
+
+   Any time you need to make changes to AllTalk, or use Finetuning etc, always start the Text-generation-webui Python environment first.
+
+   Please read the `🟩 Other installation notes` (also additional voices are available there).
+
+   Finetuning & DeepSpeed have other installation requirements (depending on your OS) so please read any instructions in the setup utility and refer back here to this page for detailed instructions (as needed).<br><br>
+</details>
+<details>
+	<summary>QUICK SETUP - Standalone Installation</summary><br>
+
+ If you wish to see this as a video, please go [here](https://www.youtube.com/watch?v=AQYCccDRbaY)
+1) To download the AllTalk setup you can either:
+   - A) Go to the [Releases page](https://github.com/erew123/alltalk_tts/releases) and download the latest `alltalk_tts.zip` and extract it to the folder of your choice<br>e.g. `C:\myfiles\alltalk_tts\`.<br><br>
+   - B) Go to a terminal/console, move into the folder of your choice e.g `C:\myfiles\` folder<br>and `git clone https://github.com/erew123/alltalk_tts`<br><br>
+4) In a terminal/command prompt, move into the AllTalk folder e.g. `cd alltalk_tts`
+5) Start the AllTalk setup script `atsetup.bat` or `./atsetup.sh`
+6) Follow the on-screen prompts and install the correct requirements files that you need. It's recommended to test AllTalk works before installing DeepSpeed.
+
+   DeepSpeed on Windows machines will be installed as standard. Linux machines have other requirements which are detailed within the setup utility and on this page.
+
+   Please read the `🟩 Other installation notes` (also additional voices are available there).
+
+   You cannot have a dash in your folder path e.g. `c:\myfiles\alltalk_tts-main` so please ensure you remove any `-` from your folder path. This is a conda specific requirement and will cause AllTalk not to start at all.
+
+   Finetuning has other installation requirements so please read any instructions in the setup utility and refer back here to this page for detailed instructions.<br><br>
+</details>
+
+### 🟩 Manual Installation - As part of Text generation web UI
+On Mac's or if you wish to perform a manual installation. Click to expand the correct section below:
+<details>
+	<summary>MANUAL INSTALLATION - Text-Generation-webui</summary><br>
 
-## 🟩 Installation on Text generation web UI
 This has been tested on the current Dec 2023 release of Text generation webUI. If you have not updated it for a while, you may wish to update Text generation webUI, [instructions here](https://github.com/oobabooga/text-generation-webui?tab=readme-ov-file#how-to-install)
 
-If you want to watch a video of how to do the below [link here](https://youtu.be/9BPKuwaav5w) 
+- If you want to watch a video of how to do the below [link here](https://youtu.be/9BPKuwaav5w)<br>
 
 1) In a command prompt/terminal window you need to move into your Text generation webUI folder:<br><br>
 `cd text-generation-webui`
@@ -58,19 +109,77 @@ If you want to watch a video of how to do the below [link here](https://youtu.be
 7) **(Optional DeepSpeed)** If you have an Nvidia Graphics card on a system running Linux or Windows and wish to use **DeepSpeed** please follow these instructions [here](https://github.com/erew123/alltalk_tts?#-deepspeed-installation-options). **However**, I would highly reccommend before you install DeepSpeed, you start text-generation-webui up, confirm AllTalk starts correctly and everything is working, as DeepSpeed can add another layer of complications troubleshooting any potential start-up issues. If necessary you can `pip uninstall deepspeed`.
 
 8) You can now start move back to the main Text generation webUI folder `cd ..` (a few times), start Text generation webUI with whichever **one** of the startup scripts is correct for your OS (`start_windows.bat`,`./start_linux.sh`, `start_macos.sh` or `start_wsl.bat`)  and load the AllTalk extension in the Text generation webUI **session** tab.<br><br> Starting Text-generation-webui with its correct start-up script is $\textcolor{red}{\textsf{VERY IMPORTANT}}$.
-   
-10) Please read the note below about start-up times and also the note about ensuring your character cards are set up [correctly](https://github.com/erew123/alltalk_tts#the-one-thing-i-cant-easily-work-around)
 
-11) Some extra voices downloadable [here](https://drive.google.com/file/d/1bYdZdr3L69kmzUN3vSiqZmLRD7-A3M47/view?usp=drive_link)
+   Any time you need to make changes to AllTalk, or use Finetuning etc, always start the Text-generation-webui Python environment first.
+
+   Please read the `🟩 Other installation notes` (also additional voices are available there).
+
+   Finetuning & DeepSpeed have other installation requirements (depending on your OS) so please read any instructions in the setup utility and refer back here to this page for detailed instructions (as needed).<br><br>
+
+</details>
+
+### 🟩 Manual Installation - As a Standalone Application
+On Mac's or if you wish to perform a manual installation. Click to expand the correct section below:
+<details>
+	<summary>MANUAL INSTALLATION - I want to run AllTalk as a standalone when installed with Text-generation-webui</summary><br>
+	
+If you already have AllTalk as a extension of Text-generation-webui, and wish to run it as standalone, load Text-generation-webui's Python environment `cmd_windows.bat`, `./cmd_linux.sh`, `cmd_macos.sh` or `cmd_wsl.bat`, move into the AllTalk folder `cd extensions` > `cd alltalk_tts` and start AllTalk with `python script.py`. There is nothing beyond this you would need to do.
+</details>
+<details>
+	<summary>MANUAL INSTALLATION - I wish to do a custom install of AllTalk</summary><br>
+	
+AllTalk will run as a standalone app, as long as you install its requirements files into whatever Python environment you are using. You can follow the steps to install the AllTalk's requirements into whatever Python environment you wish. Because I dont know what Python environment you are wanting to use, I can only give you a loose set of installation instructions. 
+
+Please note, at time of writing, the TTS engine requires Python **3.9.x** to **3.11.x** [TTS Engine details here](https://pypi.org/project/TTS/). AllTalk and its requirements are tested on Python **3.11.x**.
+
+#### 🟩 A very quick understanding of Python Environments.
+Different Python applications have different requirements, some of those requirement’s conflict with other Python applications requirements. To work around this problem, you can create different Python environments that remain separated from one another. A simple way of looking at Python environments, is just like how your house has different rooms for specific purposes (Kitchen, Bathroom, Bedroom etc). You can create a Python environment that is built/customised specifically for your current applications needs/purposes and will **not** interfere with any other Python applications environments/installations. <br><br>If you are adept at managing Python environments, have an existing Python environment and know that you won’t cause any conflicts by installing AllTalk's requirements within that Python environment, then load up your Python environment and install the requirements. For everyone else, here is a basic guide on installing AllTalk in its own custom Python environment (there will be small variations between OS's, but the principle is the same).
+
+**Note:** A standard VENV can cause module path issues, hence Conda is the correct method to create a Python environment for AllTalk. 
+
+#### 🟩 Building a custom Python Environment with Miniconda
+1) Open a terminal/command prompt, and confirm that both `python --version` and `pip` both work. Neither of them should give an error message. If they do you may need to install Python (and maybe Pip).<br><br>[Python Website](https://www.python.org/downloads/)<br>[Pip Website](https://pip.pypa.io/en/stable/installation/)<br><br>Once you have those working you can now continue on.<br><br>
+
+2) Assuming you don't already have Miniconda installed, we will need to download and install Minoconda as this is what we will use to build our custom Python environment.<br><br>[Miniconda Website](https://docs.conda.io/projects/miniconda/en/latest/)<br><br>Download the Miniconda version that is correct for your OS and then install it. Miniconda will create some items in your Start Menu or Application Launcher called something like `Anaconda Prompt`<br><br> You will start the `Anaconda Prompt` and your prompt in your terminal/command prompt will say something like: <br><br>`(base) C:\users\myaccount\>`<br><br> The important bit is that it has the `(base)`, the location after that doesn't matter. `(base)` signifies we are in the base conda Python environment and can now create custom Python environments with Conda.<br><br>
+  
+3) In your Anaconda Prompt command prompt/terminal, move into the folder where you want to download AllTalk to and then git clone this repository. For simplicity I am going to assume that location is `c:\myfiles\`. So you will:<br><br>`cd myfiles`<br><br>`git clone https://github.com/erew123/alltalk_tts`<br><br>
+
+4) Now we will create our custom Conda Python 3.11.5 environment and give it the name alltalkenv by typing the following at the prompt:<br><br>`conda create --name alltalkenv python=3.11.5`<br><br>You will be prompted if you want to continue and you say yes.<br><br>Once that process has completed, we now need to change from the `(base)` Conda Python environment, to our newly created `(alltalkenv)` environment. So type the following:<br><br>`conda activate alltalkenv`<br><br>Your prompt should now change from `(base) C:\myfiles\>` to `(alltalkenv) C:\myfiles\>`<br><br>
+
+5) **If you are NOT using an Nvidia card and CUDA, skip to step 6**. To force PyTorch to install with CUDA, perform the following:<br><br>`pip cache purge` (Clear the current Pip cache)<br><br>`pip uninstall torch torchaudio` (Uninstall Torch and Torchaudio from the `alltalkenv` environment)<br><br>
+You can now either install the CUDA 11.8 or 12.1 version of Torch and Torchaudio with **one** of the following<br><br>**CUDA 11.8** > `pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118`<br><br>**CUDA 12.1** > `pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121`<br><br>
+
+6) Move into the alltalk_tts folder and install one of the two requirements files. Whichever one of the two is correct for your machine type:<br><br>`cd alltalk_tts`<br><br>
+**Nvidia graphics card machines** - `pip install -r requirements_nvidia.txt`<br><br>
+**Other machines (mac, amd etc)** - `pip install -r requirements_other.txt`<br><br>
+
+7) Start AllTalk with `python script.py`<br><br>
+
+🟩 Anytime you wish to use AllTalk, update its requirements, install some other requirements such as DeepSpeed, you will need to start its Conda Python Environment in the terminal/prompt, which you will do with `conda activate alltalkenv` as long as the Conda executable is accessible at the command prompt/terminal you are in.<br><br>It is fully possible to create a batch file or script file that you can use as a launcher from your Start Menu/Application Launcher that will start the environment and AllTalk for you. 
+
+Deepspeed and other such things can be installed. Please read the relevant instructions for those items, however, make the relevant changes to load your correct Python environment when installing any requirements files and starting AllTalk.<br><br>
+
+   Any time you need to make changes to AllTalk, or use Finetuning etc, always start your Python environment first.
+
+   Please read the `🟩 Other installation notes` (also additional voices are available there).
+
+   Finetuning & DeepSpeed have other installation requirements (depending on your OS) so please read any instructions in the setup utility and refer back here to this page for detailed instructions (as needed).<br><br>
+
+</details>
+
 
 #### 🟩 Other installation notes
-On first startup, AllTalk will download the Coqui XTTSv2 2.0.2 model to its **models** folder (1.8GB space required). Check the command prompt/terminal window if you want to know what its doing. After it says "Model Loaded" the Text generation webUI is usually available on its IP address a few seconds later, for you to connect to in your browser.
+On first startup, AllTalk will download the Coqui XTTSv2 2.0.2 model to its **models** folder (1.8GB space required). Check the command prompt/terminal window if you want to know what its doing. After it says "Model Loaded" the Text generation webUI is usually available on its IP address a few seconds later, for you to connect to in your browser. If you are running a headless system and need to change the IP, please see the Help with problems section down below.
 
 Once the extension is loaded, please find all documentation and settings on the link provided in the interface (as shown in the screenshot below).
 
 **Where to find voices** https://aiartes.com/voiceai or https://commons.wikimedia.org/ or interviews on youtube etc. Instructions on how to cut down and prepare a voice sample are within the built in documentation.
 
-#### 🟩 The one thing I cant easily work around
+Please read the note below about start-up times and also the note about ensuring your character cards are set up [correctly](https://github.com/erew123/alltalk_tts#-a-note-on-character-cards--greeting-messages)
+
+Some extra voices for AllTalk are downloadable [here](https://drive.google.com/file/d/1bYdZdr3L69kmzUN3vSiqZmLRD7-A3M47/view?usp=drive_link) and [here](https://drive.google.com/file/d/1CPnx1rpkuKvVj5fGr9OiUJHZ_e8DfTzP/view)
+
+#### 🟩 A note on Character Cards & Greeting Messages
 Messages intended for the Narrator should be enclosed in asterisks `*` and those for the character inside quotation marks `"`. However, AI systems often deviate from these rules, resulting in text that is neither in quotes nor asterisks. Sometimes, text may appear with only a single asterisk, and AI models may vary their formatting mid-conversation. For example, they might use asterisks initially and then switch to unmarked text. A properly formatted line should look like this:
 
 `"`Hey! I'm so excited to finally meet you. I've heard so many great things about you and I'm eager to pick your brain about computers.`"` `*`She walked across the room and picked up her cup of coffee`*`
@@ -79,22 +188,34 @@ Most narrator/character systems switch voices upon encountering an asterisk or q
 
 With improvements to the splitter/processor, I'm confident it's functioning well. You can monitor what AllTalk identifies as Narrator lines on the command line and adjust its behavior if needed (Text Not Inside - Function).
 
-## 🟪 Updating
+### 🟪 Updating
+<details>
+	<summary>UPDATING - I am using Text-Generation-webui</summary><br>
 This is pretty much a repeat of the installation process. 
 
 1) In a command prompt/terminal window you need to move into your Text generation webUI folder:<br><br>
 `cd text-generation-webui` and start the Python environment for your OS with whichever **one** of the below is correct for your OS:<br><br>
 `cmd_windows.bat`, `./cmd_linux.sh`, `cmd_macos.sh` or `cmd_wsl.bat`<br>
 
-2) Move into your extensions and alltalk_tts folder:<br><br>
+2) Move into your extensions and alltalk_tts folder e.g. `cd extensions` then `cd alltalk_tts`
-`cd extensions` then `cd alltalk_tts`
 
-3) At the command prompt/terminal, type:<br><br>
+3) At the command prompt/terminal, type `git pull`
-`git pull`
 
 4) Install the correct requirements for your machine:<br><br>
 **Nvidia graphics card machines** - `pip install -r requirements_nvidia.txt`<br><br>
-**Other machines (mac, amd etc)** - `pip install -r requirements_other.txt`
+**Other machines (mac, amd etc)** - `pip install -r requirements_other.txt`<br><br>
+</details>
+<details>
+	<summary>UPDATING - I am running as a Standalone Application</summary><br>
+	
+1) In a command prompt/terminal window you need to move into your `alltalk_tts` folder and run `start_environment.bat` or `/start_environment.sh` to load the Python environment.
+
+2) At the command prompt/terminal, type `git pull` and wait for it to complete the download.
+
+3) Install the correct requirements for your machine:<br><br>
+**Nvidia graphics card machines** - `pip install -r requirements_nvidia.txt`<br><br>
+**Other machines (mac, amd etc)** - `pip install -r requirements_other.txt`<br><br>
+</details>
 
 #### 🟪 Updating "git pull" error
 
@@ -146,17 +267,17 @@ You can now start text-generation-webui or AllTalk (standalone) and it should st
 Assuming its all working fine and you are happy, you can delete the old alltalk_tts.old folder.
 </details>
 
-## 🟫 Screenshots
+### 🟫 Screenshots
-|![image](https://github.com/erew123/alltalk_tts/assets/35898566/15c6ba0b-e6b0-4570-8253-b920dd76174d) | ![image](https://github.com/erew123/alltalk_tts/assets/35898566/548619c8-5f1b-47d0-a73d-54d2fee3f3db) |
+|![image](https://github.com/erew123/screenshots/raw/main/textgensettings.jpg) | ![image](https://github.com/erew123/screenshots/raw/main/setuputilitys.jpg) | ![image](https://github.com/erew123/screenshots/raw/main/deepspeed.jpg) |![image](https://github.com/erew123/screenshots/raw/main/textgen.jpg) |
-|:---:|:---:|
+|:---:|:---:|:---:|:---:|
-|![image](https://github.com/erew123/alltalk_tts/assets/35898566/b0e13dba-c6b1-4ab7-845d-244ac1158330) |  ![image](https://github.com/erew123/alltalk_tts/assets/35898566/e35e987c-543a-486b-b4fb-ee6ebe6f59c6) |
+|![image](https://github.com/erew123/screenshots/raw/main/settingsanddocs.jpg) | ![image](https://github.com/erew123/screenshots/raw/main/finetune1.jpg) | ![image](https://github.com/erew123/screenshots/raw/main/finetune2.jpg) |![image](https://github.com/erew123/screenshots/raw/main/sillytavern.jpg)|
-|![image](https://github.com/erew123/alltalk_tts/assets/35898566/68edc968-bdd2-4f98-9d56-b9ca40decf26) | ![image](https://github.com/erew123/alltalk_tts/assets/35898566/eb5e617b-2345-418d-8267-a9d30f705a10) |
+
-|![image](https://github.com/erew123/alltalk_tts/assets/35898566/4bd0f02e-298d-4e46-95ea-afc003c1cb70) |
+### 🟨 Help with problems
 
-## 🟨 Help with problems
 #### &nbsp;&nbsp;&nbsp;&nbsp; 🔄 **Minor updates/bug fixes list** can be found [here](https://github.com/erew123/alltalk_tts/issues/25)
 
 #### 🟨 How to make a diagnostics report file
+If you are on a Windows machine or a Linux machine, you should be able to use the `atsetup.bat` or `./atsetup.sh` utility to create a diagnositcs file. If you are unable to use the `atsetup` utility, please follow the instructions below.
 <details>
 	<summary>Click to expand</summary>
 	
@@ -184,7 +305,7 @@ Assuming its all working fine and you are happy, you can delete the old alltalk_
 **A)** Its trying to load the voice model into your graphics card VRAM (assuming you have a Nvidia Graphics card, otherwise its your system RAM)<br>
 **B)** Its trying to start up the mini-webserver and send the "ready" signal back to the main process.
 
-Before giving other possibilities a go, some people with **old machines** are finding their startup times are **very** slow 2-3 minutes. Ive extended the allowed time within the script from 1 minute to 2 minutes. **If you have an older machine** and wish to try extending this further, you can do so by editing `script.py` and changing line 251 `timeout = 120` changing the timeout to a larger value e.g `timeout = 240` (4 minutes).
+Before giving other possibilities a go, some people with **old machines** are finding their startup times are **very** slow 2-3 minutes. Ive extended the allowed time within the script from 1 minute to 2 minutes. **If you have an older machine** and wish to try extending this further, you can do so by editing `script.py` and changing `startup_wait_time = 120` (120 seconds, aka 2 minutes) at the top of the script.py file, to a larger value e.g `startup_wait_time = 240` (240 seconds aka 4 minutes).
 
 **Note:** If you need to create a support ticket, please create a `diagnostics.log` report file to submit with a support request. Details on doing this are above.
 
@@ -213,6 +334,21 @@ Other possibilities for this issue are:
 11) You have built yourself a custom Python environment and something is funky with it. This is very hard to diagnose as its not a standard environment. You may want to updating text-generation-webui and re installing its requirements file (whichever one you use that comes down with text-generation-webui).
 </details>
 
+#### 🟨 Windows & Python requirements for compiling packages
+
+`ERROR: Microsoft Visual C++ 14.0 or greater is required` or `ERROR: Could not build wheels for TTS.` or `ModuleNotFoundError: No module named 'TTS`
+
+<details>
+	<summary>Click to expand</summary><br>
+
+ Python requires that you install C++ development tools on Windows. This is detailed on the [Python site here](https://wiki.python.org/moin/WindowsCompilers). You would need to install `MSVCv142 - VS 2019 C++ x64/x86 build tools` and `Windows 10/11 SDK` from the C++ Build tools section. 
+ 
+ You can get hold of the **Community** edition [here](https://visualstudio.microsoft.com/downloads/) the during installation, selecting `C++ Build tools` and then `MSVCv142 - VS 2019 C++ x64/x86 build tools` and `Windows 10/11 SDK`. 
+
+![image](https://github.com/erew123/screenshots/raw/main/pythonrequirementswindows.jpg)
+ 
+</details>
+
 #### 🟨 I think AllTalks requirements file has installed something another extension doesn't like
 <details>
 	<summary>Click to expand</summary><br>
@@ -235,6 +371,15 @@ You can either follow the [Problems Updating](https://github.com/erew123/alltalk
 If you want to use DeepSpeed, you need an Nvidia Graphics card and to install DeepSpeed on your system. Instructions are [here](https://github.com/erew123/alltalk_tts#-deepspeed-installation-options)
 </details>
 
+#### 🟨 I am running a Headless system and need to change the IP Address manually as I cannot reach the config page.
+<details>
+	<summary>Click to expand</summary><br>
+	
+To do this you can edit the `confignew.json` file within the `alltalk_tts` folder. You would look for `"ip_address": "127.0.0.1",` and change the `127.0.0.1` to your chosen IP address,then save the file and start AllTalk.<br><br>
+
+When doing this, be careful not to impact the formatting of the JSON file. Worst case, you can re-download a fresh copy of `confignew.json` from this website and that will put you back to a factory setting.
+</details>
+
 #### 🟨 I am having problems updating/some other issue where it wont start up/Im sure this is a bug
 <details>
 	<summary>Click to expand</summary><br>
@@ -244,6 +389,14 @@ Please see [Problems Updating](https://github.com/erew123/alltalk_tts#-problems-
 Also, is your text-generation-webui up to date? [instructions here](https://github.com/oobabooga/text-generation-webui?tab=readme-ov-file#how-to-install)
 </details>
 
+#### 🟨 Standalone Install - start_{youros}.xx opens and closes instantly and AllTalk doesnt start
+<details>
+	<summary>Click to expand</summary><br>
+
+This is more than likely caused by having a `-` in your folder path e.g. `c:\myfiles\alltalk_tts-main`. In this circumstance you would be best renaming the folder to remove the `-` from its name e.g. `c:\myfiles\alltalk_tts`, delete the `alltalk_environment` folder and `start_alltalk.bat` or `start_alltalk.sh` and then re-run `atsetup` to re-create the environment and startup files. 
+
+</details>
+
 #### 🟨 I am having problems getting AllTalk to start after changing settings or making a custom setup/model setup.
 
 <details>
@@ -279,13 +432,14 @@ Depending on which of your Nvidia GPU's is the more powerful one, you can change
 
 </details>
 
-## ⚫ Finetuning a model
+### ⚫ Finetuning a model
 If you have a voice that the model doesnt quite reproduce correctly, or indeed you just want to improve the reproduced voice, then finetuning is a way to train your "XTTSv2 local" model **(stored in `/alltalk_tts/models/xxxxx/`)** on a specific voice. For this you will need:
 
 - An Nvidia graphics card. (Please see this [note](https://github.com/erew123/alltalk_tts#-i-have-multiple-gpus-and-i-have-problems-running-finetuning) if you have multiple Nvidia GPU's).
 - To install a few portions of the Nvidia CUDA 11.8 Toolkit (this will not impact text-generation-webui's cuda setup.
 - 18GB of disk space free (most of this is used temporarily)
 - At least 2 minutes of good quality speech from your chosen speaker in mp3, wav or flacc format, in one or more files (have tested as far as 20 minutes worth of audio).
+- As a side note, many people seem to think that the Whisper v2 model (used on Step 1) is giving better results at generating training datasets, so you may prefer to try that, as opposed to the Whisper 3 model.
 
 #### ⚫ How will this work/How complicated is it?
 Everything has been done to make this as simple as possible. At its simplest, you can literally just download a large chunk of audio from an interview, and tell the finetuning to strip through it, find spoken parts and build your dataset. You can literally click 4 buttons, then copy a few files and you are done. At it's more complicated end you will clean up the audio a little beforehand, but its still only 4x buttons and copying a few files.
@@ -293,9 +447,17 @@ Everything has been done to make this as simple as possible. At its simplest, yo
 #### ⚫ The audio you will use
 I would suggest that if its in an interview format, you cut out the interviewer speaking in audacity or your chosen audio editing package. You dont have to worry about being perfect with your cuts, the finetuning Step 1 will go and find spoken audio and cut it out for you. Is there is music over the spoken parts, for best quality you would cut out those parts, though its not 100% necessary. As always, try to avoid bad quality audio with noises in it (humming sounds, hiss etc). You can try something like [Audioenhancer](https://audioenhancer.ai/) to try clean up noisier audio. There is no need to down-sample any of the audio, all of that is handled for you. Just give the finetuning some good quality audio to work with. 
 
+#### ⚫ A note about anonymous training Telemetry information & disabling it
+Portions of Coqui's TTS trainer scripts gather anonymous training information which you can disable. Their statement on this is listed [here](https://github.com/coqui-ai/Trainer?tab=readme-ov-file#anonymized-telemetry). Although I have tried to pass `TRAINER_TELEMETRY=0` through AllTalk, it appears you will have to set this manually if you wish to finetune on a non-internet enabled computer or disable the anonymous data being sent. You can do this by:
+
+- On Windows by typing `set TRAINER_TELEMETRY=0`
+- On Linux & Mac by typing `export TRAINER_TELEMETRY=0`
+
+Before you start `finetune.py`. You will now be able to finetune offline and no anonymous training data will be sent. 
+
 #### ⚫ Important requirements CUDA 11.8
-As mentioned you must have a small portion of the Nvidia CUDA Toolkit **11.8** installed. Not higher or lower versions. Specifically **11.8**. You do not have to uninstall any other versions, change any graphics drivers, reinstall torch or anything like that. To keep the download+install as small as possible, you will need to:
+As mentioned you must have a small portion of the Nvidia CUDA Toolkit **11.8** installed. Not higher or lower versions. Specifically **11.8**. You do not have to uninstall any other versions, change any graphics drivers, reinstall torch or anything like that. This requirement is for Step1 of Finetuning. To keep the download+install as small as possible, you will need to:
-- Download the **xxx (network)** install of the Nvidia Cuda Toolkit 11.8 from [here](https://developer.nvidia.com/cuda-11-8-0-download-archive)
+- Download the **xxx (network)** install of the Nvidia CUDA Toolkit 11.8 from [here](https://developer.nvidia.com/cuda-11-8-0-download-archive)
 - Run the installer. At minimum, you need to [minimally] install the `nvcc` compiler and the `CUBLAS` development and runtime libraries:
   - Select **Custom Advanced** as your installation type.
   - Uncheck all the checkboxes in the list.
@@ -314,6 +476,8 @@ As mentioned you must have a small portion of the Nvidia CUDA Toolkit **11.8** i
 - When you have made the changes, open a **new** terminal/command prompt (in order to load the new search paths) and `nvcc --version`. It should report back `Cuda compilation tools, release 11.8.` at which point, you are good to go.
 - If it doesn't report that, check you have correctly set the search environment paths, dont have overlapping other versions of cuda paths etc.
 
+**Note:** Its also important that your Torch and Torchaudio have cuda installed (of any version). If you run the AllTalk diagnostics you can see your Torch and Torchaudio versions listed there. Cuda 11.8 will be listed as `cu118` and Cuda 12.1 as `cu121`. This Torch and Torchaudio is seperate to the above requirement to have the Nvidia CUDA Toolkit installed, so dont confuse the two different requirements. If you dont have Cuda installed on Torch and Torchaudio, Step 2 of Finetuning will fail.
+
 #### ⚫ Starting Finetuning
 **NOTE:** Please make sure you have started AllTalk at least once after updating, so that it downloads the additional files needed for finetuning. 
 
@@ -340,6 +504,19 @@ As mentioned you must have a small portion of the Nvidia CUDA Toolkit **11.8** i
 11) Follow the on-screen instructions when the web interface starts up.
 12) When you have finished finetuning, the final tab will tell you what to do with your files and how to move your newly trained model to the correct location on disk.
 
+#### ⚫ Evaluation Data Percentage
+In the process of finetuning, it's crucial to balance the data used for training the model against the data reserved for evaluating its performance. Typically, a portion of the dataset is set aside as an 'evaluation set' to assess the model's capabilities in dealing with unseen data. On Step 1 of finetuning you have the option to adjust this evaluation data percentage, offering more control over your model training process.<br><br>
+**Why Adjust the Evaluation Percentage?**<br><br>
+Adjusting the evaluation percentage **can** be beneficial in scenarios with limited voice samples. When dealing with a smaller dataset, allocating a slightly larger portion to training could enhance the model's ability to learn from these scarce samples. Conversely, with abundant data, a higher evaluation percentage might be more appropriate to rigorously test the model's performance. There are currently no absolutely optimal split percentages as it varies by dataset.
+- **Default Setting:** The default evaluation percentage is set at 15%, which is a balanced choice for most datasets.
+- **Adjustable Range:** Users can now adjust this percentage, but it’s generally recommend keeping it between 5% and 30%.
+  - **Lower Bound:** A minimum of 5% ensures that there's enough data to evaluate model performance.
+  - **Upper Bound:** Its suggested not exceeding 30% for evaluation to avoid limiting the amount of data available for training.
+
+- **Understanding the Impact:** Before adjusting this setting, it's important to understand its impact on model training and evaluation. Incorrect adjustments can lead to suboptimal model performance.
+- **Gradual Adjustments:** For those unfamiliar with the process, we recommend reading up on training data and training sets, then making small, incremental changes and observing their effects.
+- **Data Quality:** Regardless of the split, the quality of the audio data is paramount. Ensure that your datasets are built from good quality audio with enough data within them.
+
 #### ⚫ Using a Finetuned model in Text-generation-webui
 
 At the end of the finetune process, you will have an option to `Compact and move model to /trainedmodel/` this will compact the raw training file and move it to `/model/trainedmodel/`. When AllTalk starts up within Text-generation-webui, if it finds a model in this location a new loader will appear in the interface for `XTTSv2 FT` and you can use this to load your finetuned model. <br><br>**Be careful** not to train a new model from the base model, then overwrite your current `/model/trainedmodel/` **if** you want a seperately trained model. This is why there is an `OPTION B` to move your just trained model to `/models/lastfinetuned/`.
@@ -352,7 +529,7 @@ At the end of the finetune process, you will have an option to `Compact and move
 
 If you've compacted and moved your model, its highly unlikely you would want to keep that data, however the choice is there to keep it if you wish. It will be between 5-10GB in size, so most people will want to delete it.
 
-## 🔵🟢🟡 DeepSpeed Installation Options
+### 🔵🟢🟡 DeepSpeed Installation Options
 **NOTE**: You **DO NOT** need to set Text-generation-webUI's **--deepspeed** setting for AllTalk to be able to use DeepSpeed. These are two completely separate things and incorrectly setting that on Text-generation-webUI may cause other complications.
 
 #### 🔵 Linux Installation
@@ -361,6 +538,8 @@ If you've compacted and moved your model, its highly unlikely you would want to
 
 ➡️DeepSpeed requires an Nvidia Graphics card!⬅️
 
+- #### DeepSpeed Installation for Text generation webUI
+
 1) Preferably use your built in package manager to install CUDA tools. Alternatively download and install the Nvidia Cuda Toolkit for Linux [Nvidia Cuda Toolkit 11.8 or 12.1](https://developer.nvidia.com/cuda-toolkit-archive)<br><br>
 2) Open a terminal console.<br><br>
 3) Install libaio-dev (however your Linux version installs things) e.g. `sudo apt install libaio-dev`<br><br>
@@ -372,14 +551,37 @@ If you've compacted and moved your model, its highly unlikely you would want to
 `export CUDA_HOME=/etc/alternatives/cuda`<br><br>
 **every** time you run `./cmd_linux.sh`.<br> <br>
 If you try to start DeepSpeed with the CUDA_HOME path set incorrectly, expect an error similar to `[Errno 2] No such file or directory: /home/yourname/text-generation-webui/installer_files/env/bin/nvcc`<br> <br>
-9) Now install deepspeed with pip install deepspeed<br><br>
+You can also add the `export` line into the start scripts just below the `conda active .......` line, to avoid running the command each time. <br> <br>
-10) You can now start Text generation webUI `python server.py` ensuring to activate your extensions.<br><br>
+8) Now install deepspeed with pip install deepspeed<br><br>
+9) You can now start Text generation webUI `python server.py` ensuring to activate your extensions.<br><br>
 Just to reiterate, starting Text-generation-webUI with `./start_linux.sh` will overwrite the CUDA_HOME variable unless you have permanently changed it, hence always starting it with `./cmd_linux.sh` **then** setting the environment variable manually (step 7) and **then** `python server.py`, which is how you would need to run it each time, unless you permanently set the environment variable for CUDA_HOME within Text-generation-webUI's standard Python environment.
 <br><br>
 **Removal** - If it became necessary to uninstall DeepSpeed, you can do so with `./cmd_linux.sh` and then `pip uninstall deepspeed`<br><br>
+
+- #### DeepSpeed Installation for standalone alltalk_tts app
+
+1) Preferably use your built in package manager to install CUDA tools. Alternatively download and install the Nvidia Cuda Toolkit for Linux [Nvidia Cuda Toolkit 11.8 or 12.1](https://developer.nvidia.com/cuda-toolkit-archive)<br><br>
+2) Open a terminal console.<br><br>
+3) Install libaio-dev (however your Linux version installs things) e.g. `sudo apt install libaio-dev` If you are using an RPM based distribution the package will probably be named `libaio-devel`.<br><br> 
+4) Navigate to your alltalk_tts folder e.g. `cd alltext_tts`<br><br>
+5) Start the alltalk_tts Python environment `conda activate alltalkenv`<br><br>
+6) You will need to set the **CUDA_HOME** environment variable. Details to change it each time are on the next step. Below is a link to Conda's manual and changing environment variables permanently though its possible changing it permanently could affect other extensions, you would have to test.<br> <br>
+[Conda manual - Environment variables](https://conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html#set-env-vars)<br><br>
+7) Set the environment path for CUDA_HOME e.g. `export CUDA_HOME=/usr/local/cuda-12.1/bin` or `export CUDA_HOME=/etc/alternative/cuda`.  Verify the path on your Linux distro before setting this variable.<br>
+If you try to start DeepSpeed with the CUDA_HOME path set incorrectly, expect an error similar to `[Errno 2] No such file or directory` or `CUDA_HOME does not exist`<br> <br>
+If you set the `env` variable and you receive an error of `[Errno 2] No such file or directory: '/usr/local/cuda-12.1/bin/bin/nvcc'` with a double `bin/bin` path, you can remove the env variable with `unset CUDA_HOME` and add the path to your linux PATH env variable with: `export PATH=$PATH:/usr/local/cuda-12.1/bin`. (Verify the path on your Linux distro before setting this variable.)  However if you are using other applications that use CUDA, you will want to verify that configuring the path did not break those applications. <br><br> 
+8) Now install deepspeed with `pip install deepspeed`<br><br>
+9) You can now start the alltalk_tts webUI with `python script.py`<br><br>
+<br><br>
+**Removal** - If it became necessary to uninstall DeepSpeed, you can do so by entering your `alltalkenv` enviroment `conda activate alltalkenv` and then running `pip uninstall deepspeed`<br><br>
+
+
 </details>
-	
+
 #### 🟢🟡 Windows Installation
+<details>
+	<summary>Click to Expand: Windows DeepSpeed options</summary><br>
+	
 DeepSpeed v11.2 will work on the current default text-generation-webui Python 3.11 environment! You have 2x options for how to setup DeepSpeed on Windows. A quick way (🟢Option 1) and a long way (🟡Option 2).
 
 Thanks to [@S95Sedan](https://github.com/S95Sedan) - They managed to get DeepSpeed 11.2 working on Windows via making some edits to the original Microsoft DeepSpeed v11.2 installation. The original post is [here](https://github.com/oobabooga/text-generation-webui/issues/4734#issuecomment-1843984142).
@@ -504,45 +706,13 @@ def get_shm_size():
 <br><br>
 **Removal** - If it became necessary to uninstall DeepSpeed, you can do so with `cmd_windows.bat` and then `pip uninstall deepspeed`<br><br>
 </details>
+</details>
 
-## 🟦 Running AllTalk as a standalone app
+### ⬜ AllTalk TTS Generator
-AllTalk will run as a standalone app, as long as you install its requirements files into whatever Python environment you are using. You can follow the steps to install the AllTalk's requirements into whatever Python environment you wish. Because I dont know what Python environment you are wanting to use, I can only give you a loose set of installation instructions. 
+AllTalk TTS Generator is the solution for converting large volumes of text into speech using the voice of your choice. Whether you're creating audio content or just want to hear text read aloud, the TTS Generator is equipped to handle it all efficiently. Please see here for a quick [demo](https://www.youtube.com/watch?v=hunvXn0mLzc)<br><br>The link to open the TTS generator can be found on the built-in Settings and Documentation page.<br><br>**DeepSpeed** is **highly** recommended to speed up generation. **Low VRAM** would be best turned off and your LLM model unloaded from your GPU VRAM (unload your model). **No Playback** will reduce memory overhead on very large generations (15,000 words or more). Splitting **Export to Wav** into smaller groups will also reduce memory overhead at the point of exporting your wav files (so good for low memory systems). 
 
-Please note, at time of writing, the TTS engine requires Python **3.9.x** to **3.11.x** [TTS Engine details here](https://pypi.org/project/TTS/). AllTalk and its requirements are tested on Python **3.11.x**.
+#### ⬜ Estimated Throughput
-
+This will vary by system for a multitude of reasons, however, while generating a 58,000 word document to TTS, with DeepSpeed enabled, LowVram disabled, splitting size 2 and on an Nvidia RTX 4070, throughput was around 1,000 words per minute. Meaning, this took 1 hour to generate the TTS. Exporting to combined wavs took about 2-3 minutes total.
-#### 🟦 (Option 1) I already have AllTalk installed as an extension of Text-generation-webui
-If you already have AllTalk as a extension of Text-generation-webui, and wish to run it as standalone, load Text-generation-webui's Python environment `cmd_windows.bat`, `./cmd_linux.sh`, `cmd_macos.sh` or `cmd_wsl.bat`, move into the AllTalk folder `cd extensions` > `cd alltalk_tts` and start AllTalk with `python script.py`. There is nothing beyond this you would need to do.
-
-#### 🟦 (Option 2) I wish to do a custom install of AllTalk
-#### 🔹 A very quick understanding of Python Environments.
-Different Python applications have different requirements, some of those requirement’s conflict with other Python applications requirements. To work around this problem, you can create different Python environments that remain separated from one another. A simple way of looking at Python environments, is just like how your house has different rooms for specific purposes (Kitchen, Bathroom, Bedroom etc). You can create a Python environment that is built/customised specifically for your current applications needs/purposes and will **not** interfere with any other Python applications environments/installations. <br><br>If you are adept at managing Python environments, have an existing Python environment and know that you won’t cause any conflicts by installing AllTalk's requirements within that Python environment, then load up your Python environment and install the requirements. For everyone else, here is a basic guide on installing AllTalk in its own custom Python environment (there will be small variations between OS's, but the principle is the same).
-
-**Note:** A standard VENV can cause module path issues, hence Conda is the correct method to create a Python environment for AllTalk. 
-
-#### 🔹 Building a custom Python Environment with Miniconda
-1) Open a terminal/command prompt, and confirm that both `python --version` and `pip` both work. Neither of them should give an error message. If they do you may need to install Python (and maybe Pip).<br><br>[Python Website](https://www.python.org/downloads/)<br>[Pip Website](https://pip.pypa.io/en/stable/installation/)<br><br>Once you have those working you can now continue on.<br><br>
-
-2) Assuming you don't already have Miniconda installed, we will need to download and install Minoconda as this is what we will use to build our custom Python environment.<br><br>[Miniconda Website](https://docs.conda.io/projects/miniconda/en/latest/)<br><br>Download the Miniconda version that is correct for your OS and then install it. Miniconda will create some items in your Start Menu or Application Launcher called something like `Anaconda Prompt`<br><br> You will start the `Anaconda Prompt` and your prompt in your terminal/command prompt will say something like: <br><br>`(base) C:\users\myaccount\>`<br><br> The important bit is that it has the `(base)`, the location after that doesn't matter. `(base)` signifies we are in the base conda Python environment and can now create custom Python environments with Conda.<br><br>
-  
-3) In your Anaconda Prompt command prompt/terminal, move into the folder where you want to download AllTalk to and then git clone this repository. For simplicity I am going to assume that location is `c:\myfiles\`. So you will:<br><br>`cd myfiles`<br><br>`git clone https://github.com/erew123/alltalk_tts`<br><br>
-
-4) Now we will create our custom Conda Python 3.11.5 environment and give it the name alltalkenv by typing the following at the prompt:<br><br>`conda create --name alltalkenv python=3.11.5`<br><br>You will be prompted if you want to continue and you say yes.<br><br>Once that process has completed, we now need to change from the `(base)` Conda Python environment, to our newly created `(alltalkenv)` environment. So type the following:<br><br>`conda activate alltalkenv`<br><br>Your prompt should now change from `(base) C:\myfiles\>` to `(alltalkenv) C:\myfiles\>`<br><br>
-
-5) **If you are NOT using an Nvidia card and CUDA, skip to step 6**. To force PyTorch to install with CUDA, perform the following:<br><br>`pip cache purge` (Clear the current Pip cache)<br><br>`pip uninstall torch torchaudio` (Uninstall Torch and Torchaudio from the `alltalkenv` environment)<br><br>
-You can now either install the CUDA 11.8 or 12.1 version of Torch and Torchaudio with **one** of the following<br><br>**CUDA 11.8** > `pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118`<br><br>**CUDA 12.1** > `pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121`<br><br>
-
-6) Move into the alltalk_tts folder and install one of the two requirements files. Whichever one of the two is correct for your machine type:<br><br>`cd alltalk_tts`<br><br>
-**Nvidia graphics card machines** - `pip install -r requirements_nvidia.txt`<br><br>
-**Other machines (mac, amd etc)** - `pip install -r requirements_other.txt`<br><br>
-
-7) Start AllTalk with `python script.py`<br><br>
-
-🔹Anytime you wish to use AllTalk, update its requirements, install some other requirements such as DeepSpeed, you will need to start its Conda Python Environment in the terminal/prompt, which you will do with `conda activate alltalkenv` as long as the Conda executable is accessible at the command prompt/terminal you are in.<br><br>It is fully possible to create a batch file or script file that you can use as a launcher from your Start Menu/Application Launcher that will start the environment and AllTalk for you. 
-
-Deepspeed and other such things can be installed. Please read the relevant instructions for those items, however, make the relevant changes to load your correct Python environment when installing any requirements files and starting AllTalk.<br><br>
-
-## ⬜ AllTalk TTS Generator
-AllTalk TTS Generator is the solution for converting large volumes of text into speech using the voice of your choice. Whether you're creating audio content or just want to hear text read aloud, the TTS Generator is equipped to handle it all efficiently.<br><br>The link to open the TTS generator can be found on the built-in Settings and Documentation page. 
 
 #### ⬜ Quick Start
 - **Text Input:** Enter the text you wish to convert into speech in the 'Text Input' box.
@@ -553,15 +723,16 @@ Once you have sent text off to be generated, either as a stream or wav file gene
 If you are generating wav files and populating the queue, you can generate one lot of text to speech, then input your next lot of text and it will continue adding to the list.
 #### ⬜ TTS Generation Modes
 - **Wav Chunks:** Perfect for creating audio books, or anything you want to keep long term. Breaks down your text into manageable wav files and queues them up. Generation begins automatically, and playback will start after a few chunks have been prepared ahead. You can set the volume to 0 if you don’t want to hear playback. With Wav chunks, you can edit and/or regenerate portions of the TTS as needed.
-- **Streaming:** For immediate playback without the ability to save. Ideal for on-the-fly speech generation and listening. This will not generate wav files and it will play back through your browser. You cannot stop the server generating the TTS once it has been sent.
+- **Streaming:** For immediate playback without the ability to save. Ideal for on-the-fly speech generation and listening. This will not generate wav files and it will play back through your browser. You cannot stop the server generating the TTS once it has been sent.<br><br>
-With wav chunks you can either playback “In Browser” which is the web page you are on, or “On Server” which is through the console/terminal where AllTalk is running from. Only generation “In Browser” can play back smoothly and populate the Generated TTS List. Setting the Volume will affect the volume level played back both “In Browser” and “On Server”.
+With wav chunks you can either playback “In Browser” which is the web page you are on, or “On Server” which is through the console/terminal where AllTalk is running from, or "No Playback". Only generation “In Browser” can play back smoothly and populate the Generated TTS List. Setting the Volume will affect the volume level played back both “In Browser” and “On Server”.<br><br>
+For generating **large amounts of TTS**, it's recommended to select the **No Playback** option. This setting minimizes the memory usage in your web browser by avoiding the loading and playing of audio files directly within the browser, which is particularly beneficial for handling extensive audio generations. The definition of large will vary depending on your system RAM availability (will update when I have more information as to guidelines). Once the audio is generated, you can export your list to JSON (for safety) and use the **Play List** option to play back your audio.
 #### ⬜ Playback and List Management
 - **Playback Controls:** Utilize 'Play List' to start from the beginning or 'Stop Playback' to halt at any time.
 - **Custom Start:** Jump into your list at a specific ID to hear a particular section.
 - **Regeneration and Editing:** If a chunk isn't quite right, you can opt to regenerate it or edit the text directly. Click off the text to save changes and hit regenerate for the specific line.
 - **Export/Import List:** Save your TTS list as a JSON file or import one. Note: Existing wav files are needed for playback. Exporting is handy if you want to take your files away into another program and have a list of which wav is which, or if you keep your audio files, but want to come back at a later date, edit one or two lines, regenerate the speech and re-combine the wav’s into one new long wav.
 #### ⬜ Exporting Your Audio
-- **Export to WAV:** Combine all generated TTS from the list, into one single WAV file for easy download and distribution.
+- **Export to WAV:** Combine all generated TTS from the list, into one single WAV file for easy download and distribution. Its always recommended to export your list to a JSON before exporting, so that you have a backup, should something go wrong. You can simply re-import the list and try exporting again.<br><br>When exporting, there is a file size limit of 1GB and as such you have the option to choose how many files to include in each block of audio exported. 600 is just on the limit of 1GB, depending on the average file size, so 500 or less is a good amount to work with. You can combine the generated files after if you wish, in Audacity or similar.<br><br>Additionally, lower export batches will lower the memory requirements, so if your system is low on memory (maybe 8 or 16GB system), you can use smaller export batches to keep the memory requirement down.
 #### ⬜ Customization and Preferences
 - **Character Voice:** Choose the voice that will read your text.
 - **Language:** Select the language of your text.
@@ -574,7 +745,7 @@ With wav chunks you can either playback “In Browser” which is the web page y
 - Generated audio can be played back from the list, which also highlights the currently playing chunk.
 - The TTS Generator remembers your settings, so you can pick up where you left off even after refreshing the page.
 
-## 🟠 API Suite and JSON-CURL
+### 🟠 API Suite and JSON-CURL
 ### 🟠Overview
 The Text-to-Speech (TTS) Generation API allows you to generate speech from text input using various configuration options. This API supports both character and narrator voices, providing flexibility for creating dynamic and engaging audio content.
 
@@ -596,6 +767,22 @@ Retrieve a list of available voices for generating speech.
 
    JSON return: `{"voices": ["voice1.wav", "voice2.wav", "voice3.wav"]}`
 
+#### 🟠 Current Settings Endpoint<br>
+Retrieve a list of available voices for generating speech.
+
+- URL: `http://127.0.0.1:7851/api/currentsettings`<br> - Method: `GET`<br>
+
+   `curl -X GET "http://127.0.0.1:7851/api/currentsettings"`
+
+   JSON return: ```{"models_available":[{"name":"Coqui","model_name":"API TTS"},{"name":"Coqui","model_name":"API Local"},{"name":"Coqui","model_name":"XTTSv2 Local"}],"current_model_loaded":"XTTSv2 Local","deepspeed_available":true,"deepspeed_status":true,"low_vram_status":true,"finetuned_model":false}```
+
+  `name & model_name` = listing the currently available models.<br>
+  `current_model_loaded` = what model is currently loaded into VRAM.<br>
+  `deepspeed_available` = was DeepSpeed detected on startup and available to be activated.<br>
+  `deepspeed_status` = If DeepSpeed was detected, is it currently activated.<br>
+  `low_vram_status` = Is Low VRAM currently enabled.<br>
+  `finetuned_model` = Was a finetuned model detected. (XTTSv2 FT).<br>
+
 #### 🟠 Preview Voice Endpoint
 Generate a preview of a specified voice with hardcoded settings.
 
@@ -640,12 +827,13 @@ Generate a preview of a specified voice with hardcoded settings.
 
    JSON return `{"status": "lowvram-success"}`
 
-### 🟠 TTS Generation Endpoint
+### 🟠 TTS Generation Endpoint (Standard Generation)
+Streaming endpoint details are further down the page.
 
 - URL: `http://127.0.0.1:7851/api/tts-generate`<br> - Method: `POST`<br> - Content-Type: `application/x-www-form-urlencoded`<br>
 
-### 🟠 Example command lines
+### 🟠 Example command lines (Standard Generation)
-Standard TTS speech Example (standard text) generating a time-stamped file<br>
+Standard TTS generation supports Narration and will generate a wav file/blob. Standard TTS speech Example (standard text) generating a time-stamped file<br>
 
 `curl -X POST "http://127.0.0.1:7851/api/tts-generate" -d "text_input=All of this is text spoken by the character. This is text not inside quotes, though that doesnt matter in the slightest" -d "text_filtering=standard" -d "character_voice_gen=female_01.wav" -d "narrator_enabled=false" -d "narrator_voice_gen=male_01.wav" -d "text_not_inside=character" -d "language=en" -d "output_file_name=myoutputfile" -d "output_file_timestamp=true" -d "autoplay=true" -d "autoplay_volume=0.8"`<br>
 
@@ -748,7 +936,32 @@ Example JSON TTS Generation Response:
 
 `{"status":"generate-success","output_file_path":"C:\\text-generation-webui\\extensions\\alltalk_tts\\outputs\\myoutputfile_1704141936.wav","output_file_url":"http://127.0.0.1:7851/audio/myoutputfile_1704141936.wav","output_cache_url":"http://127.0.0.1:7851/audiocache/myoutputfile_1704141936.wav"}`
 
+### 🟠 TTS Generation Endpoint (Streaming Generation)
+Streaming TTS generation does NOT support Narration and will generate an audio stream. Streaming TTS speech JavaScript Example:<br>
+
+- URL: `http://localhost:7851/api/tts-generate-streaming`<br> - Method: `POST`<br> - Content-Type: `application/x-www-form-urlencoded`<br><br>
+
+```
+// Example parameters
+const text = "Here is some text";
+const voice = "female_01.wav";
+const language = "en";
+const outputFile = "stream_output.wav";
+// Encode the text for URL
+const encodedText = encodeURIComponent(text);
+// Create the streaming URL
+const streamingUrl = `http://localhost:7851/api/tts-generate-streaming?text=${encodedText}&voice=${voice}&language=${language}&output_file=${outputFile}`;
+// Create and play the audio element
+const audioElement = new Audio(streamingUrl);
+audioElement.play(); // Play the audio stream directly
+```
+- **Text (text):** This is the actual text you want to convert to speech. It should be a string and must be URL-encoded to ensure that special characters (like spaces and punctuation) are correctly transmitted in the URL. Example: `Hello World` becomes `Hello%20World` when URL-encoded.<br>
+- **Voice (voice):** This parameter specifies the voice type to be used for the TTS. The value should match one of the available voice options in AllTalks voices folder. This is a string representing the file, like `female_01.wav`.<br>
+- **Language (language):** This setting determines the language in which the text should be spoken. A two-letter language code (like `en` for English, `fr` for French, etc.).<br>
+- **Output File (output_file):** This parameter names the output file where the audio will be streamed. It should be a string representing the file name, such as `stream_output.wav`. AllTalk will not save this as a file in its outputs folder.<br>
+<br>
+
 ### 🔴 Future to-do list
-- SillyTavern Support
+- I am maintaining a list of things people request [here](https://github.com/erew123/alltalk_tts/discussions/74)
 - Possibly add some additional TTS engines (TBD).
 - Have a break!

atsetup.bat

@@ -0,0 +1,504 @@
+@echo off
+cd /D "%~dp0"
+
+set PATH=%PATH%;%SystemRoot%\system32
+
+:: Generate the ESC character
+for /F %%a in ('echo prompt $E ^| cmd') do set "ESC=%%a"
+
+:: Standard Colors
+set "BLACK=%ESC%[30m"
+set "RED=%ESC%[31m"
+set "GREEN=%ESC%[32m"
+set "YELLOW=%ESC%[33m"
+set "BLUE=%ESC%[34m"
+set "MAGENTA=%ESC%[35m"
+set "CYAN=%ESC%[36m"
+set "WHITE=%ESC%[37m"
+set "L_BLACK=%ESC%[90m"
+set "L_RED=%ESC%[91m"
+set "L_GREEN=%ESC%[92m"
+set "L_YELLOW=%ESC%[93m"
+set "L_BLUE=%ESC%[94m"
+set "L_MAGENTA=%ESC%[95m"
+set "L_CYAN=%ESC%[96m"
+set "L_WHITE=%ESC%[97m"
+set "RESET=%ESC%[0m"
+
+@rem Check if curl is available
+curl --version >nul 2>&1
+if "%ERRORLEVEL%" NEQ "0" (
+    echo curl is not available on this system. Please install curl then re-run the script https://curl.se/ 
+	echo or perform a manual installation of a Conda Python environment.
+    goto end
+)
+
+:MainMenu
+cls
+echo.
+echo    %L_BLUE%ALLTALK WINDOWS SETUP UTILITY%RESET%
+echo.
+echo    INSTALLATION TYPE
+echo    1) I am using AllTalk as part of %L_GREEN%Text-generation-webui%RESET%
+echo    2) I am using AllTalk as a %L_GREEN%Standalone Application%RESET%
+echo.
+echo    9) %L_RED%Exit/Quit%RESET%
+echo.
+set /p UserOption="    Enter your choice: "
+
+if "%UserOption%"=="1" goto WebUIMenu
+if "%UserOption%"=="2" goto StandaloneMenu
+if "%UserOption%"=="9" goto End
+goto MainMenu
+
+:WebUIMenu
+cls
+echo.
+echo    %L_BLUE%TEXT-GENERATION-WEBUI SETUP%RESET%
+echo.
+echo    Please ensure you have started your Text-generation-webui Python 
+echo    environment. If you have NOT done this, please run %L_GREEN%cmd_windows.bat%RESET% 
+echo    in the %L_GREEN%text-generation-webui%RESET% folder and then re-run this script.
+echo.
+echo    BASE REQUIREMENTS
+echo    1) Install the requirements for a %L_GREEN%Nvidia machine%RESET%.
+echo    2) Install the requirements for a %L_GREEN%AMD or MAC machine%RESET%.
+echo.
+echo    OPTIONAL
+echo    3) Install the Finetuning requirements.
+echo    4) Install DeepSpeed v11.2 for CUDA %L_GREEN%11.8%RESET% and Python-3.11.x.
+echo    5) Install DeepSpeed v11.2 for CUDA %L_GREEN%12.1%RESET% and Python-3.11.x.
+echo    6) Uninstall DeepSpeed.
+echo.
+echo.   OTHER
+echo    7) Generate a diagnostics file.
+echo.
+echo    9) %L_RED%Exit/Quit%RESET%
+echo.
+set /p WebUIOption="Enter your choice: "
+if "%WebUIOption%"=="1" goto InstallNvidiaTextGen
+if "%WebUIOption%"=="2" goto InstallOtherTextGen
+if "%WebUIOption%"=="3" goto InstallFinetuneTextGen
+if "%WebUIOption%"=="4" goto InstallDeepSpeed118TextGen
+if "%WebUIOption%"=="5" goto InstallDeepSpeed121TextGen
+if "%WebUIOption%"=="6" goto UnInstallDeepSpeed
+if "%WebUIOption%"=="7" goto GenerateDiagsTextGen
+if "%WebUIOption%"=="9" goto End
+goto WebUIMenu
+
+:StandaloneMenu
+cls
+echo.
+echo    %L_BLUE%ALLTALK STANDALONE APPLICATION SETUP%RESET%
+echo.
+echo    BASE REQUIREMENTS
+echo    1) Install AllTalk as a Standalone Application
+echo.
+echo    OPTIONAL
+echo    2) Delete AllTalk's custom Python environment
+echo    3) Install the Finetuning requirements
+echo.
+echo.   OTHER
+echo    4) Generate a diagnostics file
+echo.
+echo    9) %L_RED%Exit/Quit%RESET%
+echo.
+set /p StandaloneOption="Enter your choice: "
+if "%StandaloneOption%"=="1" goto InstallCustomStandalone
+if "%StandaloneOption%"=="2" goto DeleteCustomStandalone
+if "%StandaloneOption%"=="3" goto InstallFinetuneStandalone
+if "%StandaloneOption%"=="4" goto GenerateDiagsStandalone
+if "%StandaloneOption%"=="9" goto End
+goto StandaloneMenu
+
+:InstallNvidiaTextGen
+pip install -r requirements_nvidia.txt
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    There was an error installing the Nvidia requirements.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+Echo.
+echo.
+Echo    Nvidia machine requirements installed successfully.
+Echo. 
+pause
+goto WebUIMenu
+
+:InstallOtherTextGen
+pip install -r requirements_other.txt
+if %ERRORLEVEL% neq 0 (
+    echo. 
+    echo    There was an error installing the Other requirements.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+Echo.
+echo.
+Echo    Other machine requirements installed successfully.
+Echo. 
+pause
+goto WebUIMenu
+
+:InstallFinetuneTextGen
+pip install -r requirements_finetune.txt
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    There was an error installing the Finetune requirements.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+Echo.
+Echo    Finetune requirements installed successfully. Please ensure you have installed CUDA 11.8.
+Echo    Finetune needs access to %L_GREEN%cublas64_11.dll%RESET% and will error if this is not setup correctly.
+Echo    Please see here for details %L_GREEN%https://github.com/erew123/alltalk_tts#-finetuning-a-model%RESET%
+Echo.
+pause
+goto WebUIMenu
+
+:InstallDeepSpeed118TextGen
+echo Downloading DeepSpeed...
+curl -LO https://github.com/erew123/alltalk_tts/releases/download/deepspeed/deepspeed-0.11.2+cuda118-cp311-cp311-win_amd64.whl
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    Failed to download DeepSpeed wheel file.
+    echo    Please check your internet connection or try again later.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+echo DeepSpeed wheel file downloaded successfully.
+echo Installing DeepSpeed...
+pip install deepspeed-0.11.2+cuda118-cp311-cp311-win_amd64.whl
+if %ERRORLEVEL% neq 0 (
+    echo. 
+    echo    Failed to install DeepSpeed.
+    echo    Please check if the wheel file is compatible with your system.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+Echo.
+echo.
+Echo    DeepSpeed installed successfully.
+Echo. 
+del deepspeed-0.11.2+cuda118-cp311-cp311-win_amd64.whl
+pause
+goto WebUIMenu
+
+:InstallDeepSpeed121TextGen
+echo Downloading DeepSpeed...
+curl -LO https://github.com/erew123/alltalk_tts/releases/download/deepspeed/deepspeed-0.11.2+cuda121-cp311-cp311-win_amd64.whl
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    Failed to download DeepSpeed wheel file.
+    echo    Please check your internet connection or try again later.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+echo    DeepSpeed wheel file downloaded successfully.
+echo    Installing DeepSpeed...
+pip install deepspeed-0.11.2+cuda121-cp311-cp311-win_amd64.whl
+if %ERRORLEVEL% neq 0 (
+    echo. 
+    echo    Failed to install DeepSpeed.
+    echo    Please check if the wheel file is compatible with your system.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+Echo.
+echo.
+Echo    DeepSpeed installed successfully.
+Echo. 
+del deepspeed-0.11.2+cuda121-cp311-cp311-win_amd64.whl
+pause
+goto WebUIMenu
+
+:UnInstallDeepSpeed
+pip uninstall deepspeed
+if %ERRORLEVEL% neq 0 (
+    echo. 
+    echo    There was an error uninstalling DeepSpeed.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto WebUIMenu
+)
+echo.
+Echo    DeepSpeed uninstalled successfully.
+Echo. 
+pause
+goto WebUIMenu
+
+:GenerateDiagsTextGen
+Python diagnostics.py
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    There was an error running diagnostics. Have you correctly started your 
+    echo    Text-generation-webui Python environment with %L_GREEN%cmd_windows.bat%RESET%?
+    echo.
+    pause
+    goto WebUIMenu
+)
+Echo.
+echo.
+Echo    Diagnostics.log generated. Please scroll up to look over the log.
+Echo. 
+pause
+goto WebUIMenu
+
+:InstallCustomStandalone
+set PATH=%PATH%;%SystemRoot%\system32
+
+@rem Check if curl is available
+curl --version >nul 2>&1
+if "%ERRORLEVEL%" NEQ "0" (
+    echo curl is not available on this system. Please install curl then re-run the script https://curl.se/ 
+	echo or perform a manual installation of a Conda Python environment.
+    goto end
+)
+echo "%CD%"| findstr /C:" " >nul && echo This script relies on Miniconda which can not be silently installed under a path with spaces. Please correct your folder names and re-try installation. && goto exit
+
+@rem Check for special characters in installation path
+set "SPCHARMESSAGE=WARNING: Special characters were detected in the installation path! This can cause the installation to fail!"
+echo "%CD%"| findstr /R /C:"[!#\$%&()\*+,;<=>?@\[\]\^`{|}~]" >nul && (
+    call :PrintBigMessage %SPCHARMESSAGE%
+)
+set SPCHARMESSAGE=
+
+@rem fix failed install when installing to a separate drive
+set TMP=%cd%\alltalk_environment
+set TEMP=%cd%\alltalk_environment
+
+@rem deactivate existing conda envs as needed to avoid conflicts
+(call conda deactivate && call conda deactivate && call conda deactivate) 2>nul
+
+@rem config
+set INSTALL_DIR=%cd%\alltalk_environment
+set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda
+set INSTALL_ENV_DIR=%cd%\alltalk_environment\env
+set MINICONDA_DOWNLOAD_URL=https://repo.anaconda.com/miniconda/Miniconda3-py310_23.3.1-0-Windows-x86_64.exe
+set conda_exists=F
+
+@rem figure out whether git and conda need to be installed
+call "%CONDA_ROOT_PREFIX%\_conda.exe" --version >nul 2>&1
+if "%ERRORLEVEL%" EQU "0" (
+    set conda_exists=T
+    call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%"
+    goto RunScript
+)
+
+@rem download and install conda if not installed
+echo Downloading Miniconda from %MINICONDA_DOWNLOAD_URL% to %INSTALL_DIR%\miniconda_installer.exe
+mkdir "%INSTALL_DIR%"
+call curl -Lk "%MINICONDA_DOWNLOAD_URL%" > "%INSTALL_DIR%\miniconda_installer.exe" || ( echo. && echo Miniconda failed to download. && goto end )
+echo Installing Miniconda to %CONDA_ROOT_PREFIX%
+start /wait "" "%INSTALL_DIR%\miniconda_installer.exe" /InstallationType=JustMe /NoShortcuts=1 /AddToPath=0 /RegisterPython=0 /NoRegistry=1 /S /D=%CONDA_ROOT_PREFIX%
+echo Miniconda version:
+call "%CONDA_ROOT_PREFIX%\_conda.exe" --version || ( echo. && echo Miniconda not found. && goto end )
+
+@rem create the installer env
+echo Packages to install: %PACKAGES_TO_INSTALL%
+call "%CONDA_ROOT_PREFIX%\_conda.exe" create --no-shortcuts -y -k --prefix "%INSTALL_ENV_DIR%" python=3.11 || ( echo. && echo Conda environment creation failed. && goto end )
+
+@rem check if conda environment was actually created
+if not exist "%INSTALL_ENV_DIR%\python.exe" ( echo. && echo Conda environment is empty. && goto end )
+
+@rem activate installer env
+call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%" || ( echo. && echo Miniconda hook not found. && goto end )
+
+@rem Ask user for the type of requirements to install
+echo.
+echo    %L_BLUE%Choose the type of requirements to install%RESET%
+echo.
+echo    1. Nvidia graphics card machines
+echo    2. Other machines (mac, amd, etc)
+echo.
+set /p UserChoice="Enter your choice (1 or 2): "
+
+@rem Install requirements based on user choice
+if "%UserChoice%" == "1" (
+    echo.
+    echo Installing Nvidia requirements...
+    echo Downloading Pytorch with CUDA..
+    pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --upgrade --force-reinstall --index-url https://download.pytorch.org/whl/cu121
+    pip install numpy==1.24.4
+    pip install typing-extensions>=4.8.0
+    pip install networkx<3.0.0,>=2.5.0
+    pip install fsspec>=2023.6.0
+    pip install soundfile==0.12.1
+    pip install uvicorn==0.24.0.post1
+    pip install transformers>=4.37.1
+    pip install TTS==0.21.3
+    pip install fastapi==0.104.1
+    pip install Jinja2==3.1.2
+    pip install requests==2.31.0
+    pip install tqdm==4.66.1
+    pip install importlib-metadata==4.8.1
+    pip install packaging==23.2
+    pip install pydantic==1.10.13
+    pip install sounddevice==0.4.6
+    pip install python-multipart==0.0.6
+    pip install cutlet>=0.3.0
+    pip install unidic-lite>=1.0.8
+    echo Downloading DeepSpeed...
+    curl -LO https://github.com/erew123/alltalk_tts/releases/download/DeepSpeed-12.7/deepspeed-0.12.7+d058d4b-cp311-cp311-win_amd64.whl
+    echo Installing DeepSpeed...
+    pip install deepspeed-0.12.7+d058d4b-cp311-cp311-win_amd64.whl
+    del deepspeed-0.12.7+d058d4b-cp311-cp311-win_amd64.whl
+) else (
+    echo Installing requirements for other machines...
+    pip install -r requirements_other.txt
+)
+
+@rem Create start_environment.bat to run AllTalk environment
+echo @echo off > start_environment.bat
+echo cd /D "%~dp0" >> start_environment.bat
+echo set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda >> start_environment.bat
+echo set INSTALL_ENV_DIR=%cd%\alltalk_environment\env >> start_environment.bat
+echo call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%" >> start_environment.bat
+@rem Create start_alltalk.bat to run AllTalk
+echo @echo off > start_alltalk.bat
+echo cd /D "%~dp0" >> start_alltalk.bat
+echo set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda >> start_alltalk.bat
+echo set INSTALL_ENV_DIR=%cd%\alltalk_environment\env >> start_alltalk.bat
+echo call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%" >> start_alltalk.bat
+echo call python script.py >> start_alltalk.bat
+Echo.
+Echo    start_alltalk.bat has been created.
+Echo    You can now start AllTalk with %L_YELLOW%start_alltalk.bat%RESET%
+Echo.
+pause
+goto StandaloneMenu
+
+:DeleteCustomStandalone
+@rem Check if the alltalk_environment directory exists
+if not exist "%cd%\alltalk_environment\" (
+    echo.
+    echo    %L_GREEN%alltalk_environment%RESET% directory does not exist. No need to delete.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+@rem Check if a Conda environment is active
+if not defined CONDA_PREFIX goto NoCondaEnvDeleteCustomStandalone
+@rem Deactivate Conda environment if it's active
+Echo    Exiting the Conda Environment. Please run %L_GREEN%atsetup.bat%RESET% again and delete the environment.
+conda deactivate
+:NoCondaEnvDeleteCustomStandalone
+echo Deleting "alltalk_environment". Please wait.
+rd /s /q "alltalk_environment"
+del start_alltalk.bat
+del start_environment.bat
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    Failed to delete alltalk_environment folder.
+    echo    Please make sure it is not in use and try again.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+echo.
+Echo.
+echo    Environment %L_GREEN%alltalk_environment%RESET% deleted. Please set up the environment again.
+Echo.
+pause
+goto StandaloneMenu
+
+:InstallFinetuneStandalone
+cd /D "%~dp0"
+set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda
+set INSTALL_ENV_DIR=%cd%\alltalk_environment\env
+@rem Check if the Conda environment exists
+if not exist "%INSTALL_ENV_DIR%\python.exe" (
+    echo.
+    echo    The Conda environment at "%INSTALL_ENV_DIR%" does not exist.
+    echo    Please install the environment before proceeding.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+@rem Attempt to activate the Conda environment
+call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%"
+if errorlevel 1 (
+    echo. 
+    echo    Failed to activate the Conda environment.
+    echo    Please check your installation and try again.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+@rem Proceed with installing requirements
+pip install -r requirements_finetune.txt
+if %ERRORLEVEL% neq 0 (
+    echo. 
+    echo    There was an error installing the Finetune requirements.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+Echo.
+Echo    Finetune requirements installed successfully. Please ensure you have installed CUDA 11.8.
+Echo    Finetune needs access to %L_GREEN%cublas64_11.dll%RESET% and will error if this is not setup correctly.
+Echo    Please see here for details %L_GREEN%https://github.com/erew123/alltalk_tts#-finetuning-a-model%RESET%
+Echo.
+pause
+goto StandaloneMenu
+
+:GenerateDiagsStandalone
+cd /D "%~dp0"
+set CONDA_ROOT_PREFIX=%cd%\alltalk_environment\conda
+set INSTALL_ENV_DIR=%cd%\alltalk_environment\env
+@rem Check if the Conda environment exists
+if not exist "%INSTALL_ENV_DIR%\python.exe" (
+    echo.
+    echo    The Conda environment at "%INSTALL_ENV_DIR%" does not exist.
+    echo    Please install the environment before proceeding.
+    echo. 
+    pause
+    goto StandaloneMenu
+)
+@rem Attempt to activate the Conda environment
+call "%CONDA_ROOT_PREFIX%\condabin\conda.bat" activate "%INSTALL_ENV_DIR%"
+if errorlevel 1 (
+    echo. 
+    echo    Failed to activate the Conda environment.
+    echo    Please check your installation and try again.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+@rem Run diagnostics
+Python diagnostics.py
+if %ERRORLEVEL% neq 0 (
+    echo.
+    echo    There was an error running diagnostics.
+    echo    Press any key to return to the menu.
+    echo.
+    pause
+    goto StandaloneMenu
+)
+Echo.
+Echo.
+Echo    Diagnostics.log generated. Please scroll up to look over the log.
+Echo.
+pause
+goto StandaloneMenu
+
+:End
+echo Exiting AllTalk Setup Utility...
+exit /b

atsetup.sh

@@ -0,0 +1,443 @@
+#!/bin/bash
+
+# ANSI color codes
+RED='\033[1;31m'
+GREEN='\033[1;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[1;34m'
+CYAN='\033[1;36m'
+MAGENTA='\033[1;35m'
+WHITE='\033[1;37m'
+L_RED='\033[1;91m'
+L_GREEN='\033[1;92m'
+L_YELLOW='\033[1;93m'
+L_BLUE='\033[1;94m'
+L_CYAN='\033[1;96m'
+L_MAGENTA='\033[1;95m'
+NC='\033[0m' # No Color
+
+# Navigate to the script's directory
+cd "$(dirname "$0")"
+
+# Function to check if curl is installed
+check_curl() {
+    if ! command -v curl &> /dev/null; then
+        echo "curl is not available on this system. Please install curl then re-run the script https://curl.se/"
+        echo "or perform a manual installation of a Conda Python environment."
+        exit 1
+    fi
+}
+
+# Main Menu
+main_menu() {
+    while true; do
+        clear
+        echo
+        echo -e "    ${L_BLUE}ALLTALK LINUX SETUP UTILITY${NC}"
+        echo
+        echo "    INSTALLATION TYPE"
+        echo -e "    1) I am using AllTalk as part of ${L_GREEN}Text-generation-webui${NC}"
+        echo -e "    2) I am using AllTalk as a ${L_GREEN}Standalone Application${NC}"
+        echo
+        echo -e "    9)${L_RED} Exit/Quit${NC}"
+        echo
+        read -p "    Enter your choice: " user_option
+
+        case $user_option in
+            1) webui_menu ;;
+            2) standalone_menu ;;
+            9) exit 0 ;;
+            *) echo "Invalid option"; sleep 2 ;;
+        esac
+    done
+}
+
+# Text-generation-webui Menu
+webui_menu() {
+    while true; do
+        clear
+        echo
+        echo -e "    ${L_BLUE}TEXT-GENERATION-WEBUI SETUP${NC}"
+        echo
+        echo -e "    Please ensure you have started your Text-generation-webui Python"
+        echo -e "    environment. If you have NOT done this, please run ${L_GREEN}/cmd_linux.sh${NC}"
+        echo -e "    in the ${L_GREEN}text-generation-webui${NC} folder and then re-run this script."
+        echo
+        echo "    BASE REQUIREMENTS"
+        echo -e "    1) Install the AllTalk requirements for an ${L_GREEN}Nvidia GPU machine.${NC}"
+        echo -e "    2) Install the AllTalk requirements for an ${L_GREEN}AMD or MAC machine.${NC}"
+        echo
+        echo "    OPTIONAL"
+        echo "    3) Install the Finetuning requirements."
+        echo "    4) Install DeepSpeed."
+        echo "    5) Uninstall DeepSpeed."
+        echo
+        echo "    OTHER"
+        echo "    6) Generate a diagnostics file."
+        echo
+        echo -e "    9)${L_RED} Exit/Quit${NC}"
+        echo
+        read -p "    Enter your choice: " webui_option
+
+        case $webui_option in
+            1) install_nvidia_textgen ;;
+            2) install_other_textgen ;;
+            3) install_finetune_textgen ;;
+            4) install_deepspeed ;;
+            5) uninstall_deepspeed ;;
+            6) generate_diagnostics_textgen ;;
+            9) exit 0 ;;
+            *) echo "Invalid option"; sleep 2 ;;
+        esac
+    done
+}
+
+install_nvidia_textgen() {
+    local requirements_file="requirements_nvidia.txt"
+    echo "    Installing Finetune requirements from $requirements_file..."
+    if ! pip install -r "$requirements_file"; then
+        echo "    There was an error installing the Nvidia requirements."
+        echo "    Please check the output for details."
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+    echo "    Nvidia requirements installed successfully."
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+install_other_textgen() {
+    local requirements_file="requirements_other.txt"
+    echo "    Installing Other machine requirements from $requirements_file..."
+    if ! pip install -r "$requirements_file"; then
+        echo "    There was an error installing the Other requirements."
+        echo "    Please check the output for details."
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+    echo "    Other machine requirements installed successfully."
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+install_finetune_textgen() {
+    local requirements_file="requirements_finetune.txt"
+    echo "    Installing Finetune requirements from $requirements_file..."
+    if ! pip install -r "$requirements_file"; then
+        echo "    There was an error installing the Finetune requirements."
+        echo "    Please check the output for details."
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+    echo
+    echo "    Finetune base requirements installed successfully."
+    echo
+    echo -e "    Finetuning requires access to ${GREEN}Cublas${NC} from the ${GREEN}Nvidia CUDA Toolkit${NC}, so will need installing."
+    echo
+    echo -e "    Instructions can be found here:"
+    echo -e "    ${GREEN}https://github.com/erew123/alltalk_tts?#-finetuning-a-model${NC}"
+    echo
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+# Function to install DeepSpeed
+install_deepspeed() {
+    clear
+    echo
+    echo -e "    ${L_BLUE}DEEPSPEED INSTALLATION REQUIREMENTS${NC}"
+    echo
+    echo -e "    - NVIDIA CUDA Toolkit must be installed from your ${L_GREEN}Linux package manager${NC}"
+    echo -e "      or ${L_GREEN}https://developer.nvidia.com/cuda-toolkit-archive${NC}"
+    echo -e "    - The environment variable ${L_GREEN}CUDA_HOME${NC} must be set in your Python env"
+    echo -e "      e.g. export CUDA_HOME=/usr/local/cuda."
+    echo -e "    - ${L_GREEN}libaio-dev${NC} must be installed."
+    echo
+    echo -e "    See the following link for full instructions:"
+    echo -e "    ${L_GREEN}https://github.com/erew123/alltalk_tts?#-deepspeed-installation-options${NC}"
+    echo
+    echo -e "    ${L_BLUE}Please ${L_RED}confirm${L_BLUE} that you have completed these steps before continuing" 
+    echo -e "    with the DeepSpeed installation, or the install ${L_RED}will fail.${NC}"
+    echo
+    read -p "    Have you completed all the above steps? (y/n): " confirm
+
+    if [ "$confirm" != "y" ]; then
+        echo -e "    ${RED}DeepSpeed installation cannot proceed without completing the prerequisites.${NC}"
+        return
+    fi
+
+    echo -e "\n    ${GREEN}Proceeding with DeepSpeed installation...${NC}"
+    pip install deepspeed
+    if [ $? -ne 0 ]; then
+        echo -e "    ${RED}There was an error installing DeepSpeed.${NC}"
+        return
+    fi
+
+    echo -e "    ${GREEN}DeepSpeed installed successfully.${NC}"
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+uninstall_deepspeed() {
+    echo "Uninstalling DeepSpeed..."
+    pip uninstall -y deepspeed
+    if [ $? -ne 0 ]; then
+        echo "    There was an error uninstalling DeepSpeed."
+        echo "    Press any key to return to the menu."
+        read -n 1
+        return
+    fi
+    echo "    DeepSpeed uninstalled successfully."
+    echo "    Press any key to continue."
+    read -n 1
+}
+
+generate_diagnostics_textgen() {
+    # Run diagnostics
+    if ! python diagnostics.py; then
+        echo "    There was an error running diagnostics."
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+
+    echo "    Diagnostics completed successfully."
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+# Standalone Menu
+standalone_menu() {
+    while true; do
+        clear
+        echo
+        echo -e "    ${L_BLUE}ALLTALK STANDALONE APPLICATION SETUP${NC}"
+        echo
+        echo "    BASE REQUIREMENTS"
+        echo "    1) Install AllTalk as a Standalone Application"
+        echo
+        echo "    OPTIONAL"
+        echo "    2) Delete AllTalk's custom Python environment"
+        echo "    3) Install the Finetuning requirements"
+        echo "    4) Install DeepSpeed."
+        echo
+        echo "    OTHER"        
+        echo "    5) Generate a diagnostics file"
+        echo
+        echo -e "    9)${L_RED} Exit/Quit${NC}"
+        echo
+        read -p "    Enter your choice: " standalone_option
+
+        case $standalone_option in
+            1) install_custom_standalone ;;
+            2) delete_custom_standalone ;;
+            3) install_finetune_standalone ;;
+            4) install_deepspeed ;;
+            5) generate_diagnostics_standalone ;;
+            9) exit 0 ;;
+            *) echo "Invalid option"; sleep 2 ;;
+        esac
+    done
+}
+
+install_custom_standalone() {
+    cd "$(dirname "${BASH_SOURCE[0]}")"
+
+    if [[ "$(pwd)" =~ " " ]]; then
+        echo "This script relies on Miniconda which can not be silently installed under a path with spaces."
+        exit
+    fi
+
+    # Deactivate existing conda envs as needed to avoid conflicts
+    { conda deactivate && conda deactivate && conda deactivate; } 2> /dev/null
+
+    OS_ARCH=$(uname -m)
+    case "${OS_ARCH}" in
+        x86_64*)    OS_ARCH="x86_64" ;;
+        arm64* | aarch64*) OS_ARCH="aarch64" ;;
+        *)          echo "Unknown system architecture: $OS_ARCH! This script runs only on x86_64 or arm64" && exit ;;
+    esac
+
+    # Config
+    INSTALL_DIR="$(pwd)/alltalk_environment"
+    CONDA_ROOT_PREFIX="${INSTALL_DIR}/conda"
+    INSTALL_ENV_DIR="${INSTALL_DIR}/env"
+    MINICONDA_DOWNLOAD_URL="https://repo.anaconda.com/miniconda/Miniconda3-py310_23.3.1-0-Linux-${OS_ARCH}.sh"
+
+    if [ ! -x "${CONDA_ROOT_PREFIX}/bin/conda" ]; then
+        echo "Downloading Miniconda from $MINICONDA_DOWNLOAD_URL to ${INSTALL_DIR}/miniconda_installer.sh"
+        mkdir -p "${INSTALL_DIR}"
+        curl -L "${MINICONDA_DOWNLOAD_URL}" -o "${INSTALL_DIR}/miniconda_installer.sh"
+        chmod +x "${INSTALL_DIR}/miniconda_installer.sh"
+        bash "${INSTALL_DIR}/miniconda_installer.sh" -b -p "${CONDA_ROOT_PREFIX}"
+        echo "Miniconda installed."
+    fi
+
+    if [ ! -d "${INSTALL_ENV_DIR}" ]; then
+        "${CONDA_ROOT_PREFIX}/bin/conda" create -y --prefix "${INSTALL_ENV_DIR}" python=3.11
+        echo "Conda environment created at ${INSTALL_ENV_DIR}."
+    fi
+
+    # Activate the environment and install requirements
+    source "${CONDA_ROOT_PREFIX}/etc/profile.d/conda.sh"
+    conda activate "${INSTALL_ENV_DIR}"
+
+    echo
+    echo -e "    ${L_BLUE}Choose the type of requirements to install${NC}"
+    echo
+    echo "    1. Nvidia graphics card machines"
+    echo "    2. Other machines (mac, amd, etc)"
+    echo
+    read -p "    Enter your choice (1 or 2): " user_choice
+
+    if [ "$user_choice" == "1" ]; then
+    	pip install torch==2.1.0 torchvision==0.16.0 torchaudio==2.1.0 --upgrade --force-reinstall --index-url https://download.pytorch.org/whl/cu121
+    	pip install numpy==1.24.4
+	pip install typing-extensions>=4.8.0
+	pip install networkx<3.0.0,>=2.5.0
+    	pip install fsspec>=2023.6.0
+	pip install soundfile==0.12.1
+    	pip install uvicorn==0.24.0.post1
+        pip install transformers>=4.37.1
+    	pip install TTS==0.21.3
+    	pip install fastapi==0.104.1
+    	pip install Jinja2==3.1.2
+    	pip install requests==2.31.0
+    	pip install tqdm==4.66.1
+    	pip install importlib-metadata==4.8.1
+    	pip install packaging==23.2
+    	pip install pydantic==1.10.13
+    	pip install sounddevice==0.4.6
+    	pip install python-multipart==0.0.6
+        pip install cutlet>=0.3.0
+    	pip install unidic-lite>=1.0.8
+    else
+        pip install -r requirements_other.txt
+    fi
+    # Create start_environment.sh to run AllTalk
+    cat << EOF > start_environment.sh
+#!/bin/bash
+cd "$(dirname "${BASH_SOURCE[0]}")"
+if [[ "$(pwd)" =~ " " ]]; then echo This script relies on Miniconda which can not be silently installed under a path with spaces. && exit; fi
+# deactivate existing conda envs as needed to avoid conflicts
+{ conda deactivate && conda deactivate && conda deactivate; } 2> /dev/null
+# config
+CONDA_ROOT_PREFIX="$(pwd)/alltalk_environment/conda"
+INSTALL_ENV_DIR="$(pwd)/alltalk_environment/env"
+# environment isolation
+export PYTHONNOUSERSITE=1
+unset PYTHONPATH
+unset PYTHONHOME
+export CUDA_PATH="$INSTALL_ENV_DIR"
+export CUDA_HOME="$CUDA_PATH"
+# activate env
+bash --init-file <(echo "source \"$CONDA_ROOT_PREFIX/etc/profile.d/conda.sh\" && conda activate \"$INSTALL_ENV_DIR\"")
+EOF
+    # Create start_alltalk.sh to run AllTalk
+    cat << EOF > start_alltalk.sh
+#!/bin/bash
+source "${CONDA_ROOT_PREFIX}/etc/profile.d/conda.sh"
+conda activate "${INSTALL_ENV_DIR}"
+python script.py
+EOF
+    chmod +x start_alltalk.sh
+    chmod +x start_environment.sh
+    echo
+    echo
+    echo -e "    start_alltalk.sh has been created."
+    echo -e "    You can now start AllTalk with ${L_YELLOW}./start_alltalk.sh${NC}"
+    echo
+    read -p "    Press any key to continue. " -n 1
+}
+
+
+delete_custom_standalone() {
+    local env_dir="$PWD/alltalk_environment"
+    # Check if the alltalk_environment directory exists
+    if [ ! -d "$env_dir" ]; then
+        echo "    \"$env_dir\" directory does not exist. No need to delete."
+        read -p "    Press any key to continue. " -n 1
+        echo
+        return
+    fi
+    # Check if a Conda environment is active and deactivate it
+    if [ -n "$CONDA_PREFIX" ]; then
+        echo "    Exiting the Conda environment. You may need to start ./atstart.sh again"
+        conda deactivate
+    fi
+    echo "Deleting \"$env_dir\". Please wait."
+    rm -rf "$env_dir"
+    if [ -d "$env_dir" ]; then
+        echo "    Failed to delete \"$env_dir\" folder."
+        echo "    Please make sure it is not in use and try again."
+    else
+        echo "    Environment \"$env_dir\" deleted successfully."
+    fi
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+install_finetune_standalone() {
+    local env_dir="$PWD/alltalk_environment"
+    local conda_root_prefix="${env_dir}/conda"
+    local install_env_dir="${env_dir}/env"
+    if [ ! -d "${install_env_dir}" ]; then
+        echo "    The Conda environment at '${install_env_dir}' does not exist."
+        echo "    Please install the environment before proceeding."
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+    source "${conda_root_prefix}/etc/profile.d/conda.sh"
+    conda activate "${install_env_dir}"
+    local requirements_file="requirements_finetune.txt"
+    echo "Installing Finetune requirements from $requirements_file..."
+    if ! pip install -r "$requirements_file"; then
+        echo "    There was an error installing the Finetune requirements."
+        echo "    Please check the output for details."
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+    echo
+    echo "    Finetune base requirements installed successfully."
+    echo
+    echo -e "    Finetuning requires access to ${GREEN}Cublas${NC} from the ${GREEN}Nvidia CUDA Toolkit${NC}, so will need installing."
+    echo
+    echo -e "    Instructions can be found here:"
+    echo -e "    ${GREEN}https://github.com/erew123/alltalk_tts?#-finetuning-a-model${NC}"
+    echo
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+generate_diagnostics_standalone() {
+    local env_dir="$PWD/alltalk_environment"
+    local conda_root_prefix="${env_dir}/conda"
+    local install_env_dir="${env_dir}/env"
+    if [ ! -d "${install_env_dir}" ]; then
+        echo "    The Conda environment at '${install_env_dir}' does not exist."
+        echo "    Please install the environment before proceeding."
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+    source "${conda_root_prefix}/etc/profile.d/conda.sh"
+    conda activate "${install_env_dir}"
+    if ! python diagnostics.py; then
+        echo "    There was an error running diagnostics."
+        read -p "    Press any key to return to the menu. " -n 1
+        echo
+        return
+    fi
+    echo "    Diagnostics completed successfully."
+    read -p "    Press any key to continue. " -n 1
+    echo
+}
+
+
+# Start the main menu
+main_menu

confignew.json

@@ -1 +1,25 @@
-{"activate": true, "autoplay": true, "branding": "AllTalk ", "narrator_enabled": false, "deepspeed_activate": false, "delete_output_wavs": "Disabled", "ip_address": "127.0.0.1", "language": "English", "low_vram": false, "local_temperature": "0.7", "local_repetition_penalty": "10.0", "tts_model_loaded": true, "tts_model_name": "tts_models/multilingual/multi-dataset/xtts_v2", "narrator_voice": "female_01.wav", "output_folder_wav": "extensions/alltalk_tts/outputs/", "output_folder_wav_standalone": "outputs/", "port_number": "7851", "remove_trailing_dots": false, "show_text": true, "tts_method_api_local": false, "tts_method_api_tts": false, "tts_method_xtts_local": true, "voice": "female_01.wav"}
+{
+    "activate": true,
+    "autoplay": true,
+    "branding": "AllTalk ",
+    "narrator_enabled": false,
+    "deepspeed_activate": false,
+    "delete_output_wavs": "Disabled",
+    "ip_address": "127.0.0.1",
+    "language": "English",
+    "low_vram": false,
+    "local_temperature": "0.7",
+    "local_repetition_penalty": "10.0",
+    "tts_model_loaded": true,
+    "tts_model_name": "tts_models/multilingual/multi-dataset/xtts_v2",
+    "narrator_voice": "female_01.wav",
+    "output_folder_wav": "extensions/alltalk_tts/outputs/",
+    "output_folder_wav_standalone": "outputs/",
+    "port_number": "7851",
+    "remove_trailing_dots": false,
+    "show_text": true,
+    "tts_method_api_local": false,
+    "tts_method_api_tts": false,
+    "tts_method_xtts_local": true,
+    "voice": "female_01.wav"
+}

diagnostics.py

@@ -215,6 +215,13 @@ def log_system_info():
 
             # Print colored output
             print(f"{package_name.ljust(max_package_length)}  Required: {color_required}{operator} {required_version.ljust(12)}\033[0m  Installed: {color_installed}{installed_version}\033[0m")
+
+        print("\nOn Nvidia Graphics cards machines, if your \033[92mInstalled\033[0m version of \033[92mTorch\033[0m and \033[92mTorchaudio\033[0m does")    
+        print("not have \033[92m+cu118\033[0m (Cuda 11.8) or \033[92m+cu121\033[0m (Cuda 12.1) listed after them, you do not have CUDA")
+        print("installed for Torch or Torchaudio in this Python environment. This will cause you problems")
+        print("with \033[94mAllTalk\033[0m and \033[94mFinetuning.\033[0m You may have to 'pip install' a new version of torch and")
+        print("torchaudio, using '\033[94m--upgrade --force-reinstall\033[0m' with the correct version of PyTorch for\033[0m")
+        print("your Python environment.\033[0m")
         print("\033[94m\nRequirements file specifier meanings:\033[0m")
         explanation = textwrap.dedent("""
         == Exact version              != Any version except          < Less than               

docker-compose-cuda.yml

@@ -0,0 +1,20 @@
+version: '3.8'
+services:
+  alltalk-tts:
+    image: erew123/alltalk_tts:cuda
+    restart: unless-stopped
+    ports:
+      - "7851:7851"
+    volumes:
+      - ./outputs:/app/outputs/
+      - ./models:/app/models/
+      - ./voices:/app/voices/
+      - ./finetune/put-voice-samples-in-here:/app/finetune/put-voice-samples-in-here
+      - ./dockerconfig.json:/app/confignew.json
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [ gpu ]

docker-compose.yml

@@ -0,0 +1,13 @@
+version: '3.8'
+services:
+  alltalk-tts:
+    image: erew123/alltalk_tts:cpu
+    restart: unless-stopped
+    ports:
+      - "7851:7851"
+    volumes:
+      - ./outputs:/app/outputs/
+      - ./models:/app/models/
+      - ./voices:/app/voices/
+      - ./finetune/put-voice-samples-in-here:/app/finetune/put-voice-samples-in-here
+      - ./dockerconfig.json:/app/confignew.json

dockerconfig.json

@@ -0,0 +1,25 @@
+{
+    "activate": true,
+    "autoplay": true,
+    "branding": "AllTalk ",
+    "narrator_enabled": false,
+    "deepspeed_activate": true,
+    "delete_output_wavs": "Disabled",
+    "ip_address": "127.0.0.1",
+    "language": "English",
+    "low_vram": false,
+    "local_temperature": "0.7",
+    "local_repetition_penalty": "10.0",
+    "tts_model_loaded": true,
+    "tts_model_name": "tts_models/multilingual/multi-dataset/xtts_v2",
+    "narrator_voice": "female_01.wav",
+    "output_folder_wav": "extensions/alltalk_tts/outputs/",
+    "output_folder_wav_standalone": "outputs/",
+    "port_number": "7851",
+    "remove_trailing_dots": false,
+    "show_text": true,
+    "tts_method_api_local": false,
+    "tts_method_api_tts": false,
+    "tts_method_xtts_local": true,
+    "voice": "female_01.wav"
+}

finetune.py

@@ -75,10 +75,10 @@ def create_temporary_file(folder, suffix=".wav"):
     unique_filename = f"custom_tempfile_{int(time.time())}_{random.randint(1, 1000)}{suffix}"
     return os.path.join(folder, unique_filename)
 
-def format_audio_list(target_language, whisper_model, out_path, gradio_progress=progress):
+def format_audio_list(target_language, whisper_model, out_path, eval_split_number, gradio_progress=progress):
     audio_files = [os.path.join(audio_folder, file) for file in os.listdir(audio_folder) if file.endswith(('.mp3', '.flac', '.wav'))]
     buffer=0.2
-    eval_percentage=0.15
+    eval_percentage = eval_split_number / 100.0
     speaker_name="coqui"
     audio_total_size = 0
     os.makedirs(out_path, exist_ok=True)
@@ -87,6 +87,7 @@ def format_audio_list(target_language, whisper_model, out_path, gradio_progress=
     print("[FINETUNE] \033[94mPart of AllTalk\033[0m https://github.com/erew123/alltalk_tts/")
     print("[FINETUNE] \033[94mCoqui Public Model License\033[0m")
     print("[FINETUNE] \033[94mhttps://coqui.ai/cpml.txt\033[0m")
+    print(f"[FINETUNE] \033[94mWhisper model: \033[92m{whisper_model} \033[94mLanguage: \033[92m{target_language} \033[94mEvaluation data percentage: \033[92m{eval_split_number}%\033[0m")
     print("[FINETUNE] \033[94mStarting Step 1\033[0m - Preparing Audio/Generating the dataset")
     # Write the target language to lang.txt in the output directory
     lang_file_path = os.path.join(out_path, "lang.txt")
@@ -917,7 +918,9 @@ if __name__ == "__main__":
                 #### &nbsp;&nbsp;&nbsp;&nbsp; - Place your audio files in <span style="color: #3366ff;">{str(audio_folder)}</span>                
                 #### &nbsp;&nbsp;&nbsp;&nbsp; - Your audio samples can be in the format <span style="color: #3366ff;">mp3, wav,</span> or <span style="color: #3366ff;">flac.</span>
                 #### &nbsp;&nbsp;&nbsp;&nbsp; - You will need a minimum of <span style="color: #3366ff;">2 minutes</span> of audio in either one or multiple audio files. Very small sample files cause errors, so I would suggest 30 seconds and longer samples. 
-                #### &nbsp;&nbsp;&nbsp;&nbsp; - When you have completed Steps 1, 2, and 3, you are welcome to delete your samples from "put-voice-samples-in-here".<br>
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - When you have completed Steps 1, 2, and 3, you are welcome to delete your samples from "put-voice-samples-in-here".
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - FYI Anecdotal evidence suggests that the Whisper 2 model may yield superior results in audio splitting and dataset creation.
+                #### &nbsp;&nbsp;&nbsp;&nbsp; - If this step is failing, it will be worth running the diagnostics with atsetup and confirming you have cu118 or cu112 listed against your torch and torchaudio.<br>
                 ### 🟨 <u>What this step is doing</u>
                 #### &nbsp;&nbsp;&nbsp;&nbsp; - With step one, we are going to be stripping your audio file(s) into smaller files, using Whisper to find spoken words/sentences, compile that into excel sheets of training data, ready for finetuning the model on Step 2.
                 #### &nbsp;&nbsp;&nbsp;&nbsp; - Whilst you can choose multiple Whisper models, its best only to use the 1 model as each one is about 3GB in size and will download to your local huggingface cache on first-time use. If and when you have completed training, you wish to delete this 3GB model from your system, you are welcome to do so.
@@ -966,6 +969,14 @@ if __name__ == "__main__":
                         "ja"
                     ],
                 )
+
+                eval_split_number = gr.Number(
+                    label="Evaluation data Split (the % to use for Evaluation data)",
+                    value=15,  # Default value
+                    minimum=5,  # Minimum value
+                    maximum=95,  # Maximum value
+                    step=1,  # Increment step
+                )
             progress_data = gr.Label(
                 label="Progress:"
             )
@@ -977,14 +988,14 @@ if __name__ == "__main__":
 
             prompt_compute_btn = gr.Button(value="Step 1 - Create dataset")
         
-            def preprocess_dataset(language,  whisper_model, out_path, progress=gr.Progress(track_tqdm=True)):
+            def preprocess_dataset(language,  whisper_model, out_path, eval_split_number, progress=gr.Progress(track_tqdm=True)):
                 clear_gpu_cache()
                 test_for_audio_files = [file for file in os.listdir(audio_folder) if any(file.lower().endswith(ext) for ext in ['.wav', '.mp3', '.flac'])]
                 if not test_for_audio_files:
                     return "I cannot find any mp3, wav or flac files in the folder called 'put-voice-samples-in-here'", "", ""
                 else:
                     try:
-                        train_meta, eval_meta, audio_total_size = format_audio_list(target_language=language, whisper_model=whisper_model ,out_path=out_path, gradio_progress=progress)
+                        train_meta, eval_meta, audio_total_size = format_audio_list(target_language=language, whisper_model=whisper_model, out_path=out_path, eval_split_number=eval_split_number, gradio_progress=progress)
                     except:
                         traceback.print_exc()
                         error = traceback.format_exc()
@@ -1272,6 +1283,7 @@ if __name__ == "__main__":
                     lang,
                     whisper_model,
                     out_path,
+                    eval_split_number,
                 ],
                 outputs=[
                     progress_data,

launch.sh

@@ -0,0 +1,5 @@
+#!/bin/sh
+python modeldownload.py
+uvicorn tts_server:app --host 0.0.0.0 --port 7851 --workers 1 --proxy-headers &
+sleep 5
+python script.py

nvidia.Dockerfile

@@ -0,0 +1,20 @@
+FROM nvidia/cuda:12.1.1-devel-ubuntu22.04
+ENV HOST 0.0.0.0
+RUN apt-get update && apt-get upgrade -y \
+    && apt-get install -y git build-essential portaudio19-dev \
+    python3 python3-pip gcc wget \
+    ocl-icd-opencl-dev opencl-headers clinfo \
+    libclblast-dev libopenblas-dev \
+    && mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd \
+    && ln -s /usr/bin/python3 /usr/bin/python
+WORKDIR /app
+COPY . .
+ENV CUDA_DOCKER_ARCH=all
+
+RUN pip install --no-cache-dir -r requirements_nvidia.txt && \
+    pip install --no-cache-dir -r requirements_finetune.txt && \
+    pip install --no-cache-dir -r requirements_other.txt && \
+    pip install --no-cache-dir deepspeed
+EXPOSE 7851
+RUN chmod +x launch.sh
+ENTRYPOINT ["sh", "-c", "./launch.sh"]

requirements_nvidia.txt

@@ -1,6 +1,7 @@
 numpy>=1.22.0
 soundfile>=0.12.1
 uvicorn>=0.24.0.post1
+transformers>=4.37.1
 TTS>=0.21.3
 torch>=2.1.0+cu118
 torchaudio>=2.1.0+cu118
@@ -13,3 +14,5 @@ packaging>=23.2
 pydantic>=1.10.13
 sounddevice>=0.4.6
 python-multipart>=0.0.6
+cutlet>=0.3.0
+unidic-lite>=1.0.8

requirements_other.txt

@@ -1,6 +1,7 @@
 numpy>=1.22.0
 soundfile>=0.12.1
 uvicorn>=0.24.0.post1
+transformers>=4.37.1
 TTS>=0.21.3
 torch>=2.1.0
 torchaudio>=2.1.0
@@ -13,3 +14,5 @@ packaging>=23.2
 pydantic>=1.10.13
 sounddevice>=0.4.6
 python-multipart>=0.0.6
+cutlet>=0.3.0
+unidic-lite>=1.0.8

script.py

@@ -16,18 +16,28 @@ import numpy as np
 import soundfile as sf
 import uuid
 
+######################################
+#### ALLTALK ALLOWED STARTUP TIME ####
+######################################
+startup_wait_time = 120
+
+# You can change the above setting to a larger number to allow AllTAlk more time to start up. The default setting is 120 seconds (2 minutes).
+# On some older systems you may need to allow AllTalk more time. So you could set it to 240 (4 minutes) which will give AllTalk more to load.
+
 #################################################################
 #### LOAD PARAMS FROM confignew.json - REQUIRED FOR BRANDING ####
 #################################################################
 # STARTUP VARIABLE - Create "this_dir" variable as the current script directory
 this_dir = Path(__file__).parent.resolve()
 
+
 # load config file in and get settings
 def load_config(file_path):
     with open(file_path, "r") as config_file:
         config = json.load(config_file)
     return config
 
+
 config_file_path = this_dir / "confignew.json"
 # Load the params dictionary from the confignew.json file
 params = load_config(config_file_path)
@@ -48,6 +58,7 @@ except ModuleNotFoundError:
 # IMPORT - Attempt Importing DeepSpeed (required for displaying Deepspeed checkbox in gradio)
 try:
     import deepspeed
+
     deepspeed_installed = True
 except ImportError:
     deepspeed_installed = False
@@ -60,6 +71,7 @@ try:
     from modules.logging_colors import logger
     from modules.ui import create_refresh_button
     from modules.utils import gradio
+
     # This is set to check if the script is being run within text generation webui or as a standalone script. False is running as part of text gen web ui or a gradio interface
     running_in_standalone = False
     output_folder_wav = params["output_folder_wav"]
@@ -80,10 +92,12 @@ process_lock = threading.Lock()
 # Base setting for a possible FineTuned model existing and the loader being available
 tts_method_xtts_ft = False
 
+
 # Gather the voice files
 def get_available_voices():
     return sorted([voice.name for voice in Path(f"{this_dir}/voices").glob("*.wav")])
 
+
 #########################
 #### LICENSE DISPLAY ####
 #########################
@@ -141,6 +155,7 @@ def check_required_files():
     subprocess.run(["python", str(download_script_path)])
     print(f"[{params['branding']}Startup] All required files are present.")
 
+
 # STARTUP Call Check routine
 check_required_files()
 
@@ -155,7 +170,9 @@ finetuned_model = trained_model_directory.exists()
 # If true, this will add a extra option in the Gradio interface for loading Xttsv2 FT
 if finetuned_model:
     required_files = ["model.pth", "config.json", "vocab.json"]
-    finetuned_model = all((trained_model_directory / file).exists() for file in required_files)
+    finetuned_model = all(
+        (trained_model_directory / file).exists() for file in required_files
+    )
 if finetuned_model:
     print(f"[{params['branding']}Startup] Finetuned model \033[93mDetected\033[0m")
 
@@ -173,6 +190,7 @@ elif params["tts_method_xtts_local"] == True:
 # Set the default for Narrated text without asterisk or quotes to be Narrator
 non_quoted_text_is = True
 
+
 ######################
 #### GRADIO STUFF ####
 ######################
@@ -230,62 +248,80 @@ def signal_handler(sig, frame):
 
 # Attach the signal handler to the SIGINT signal (Ctrl+C)
 signal.signal(signal.SIGINT, signal_handler)
-
+# Check if we're running in docker
-# Start the subprocess
+if os.path.isfile("/.dockerenv"):
-process = subprocess.Popen(["python", script_path])
-
-# Check if the subprocess has started successfully
-if process.poll() is None:
-    print(f"[{params['branding']}Startup] TTS Subprocess starting")
     print(
-        f"[{params['branding']}Startup] Readme available here:",
+        f"[{params['branding']}Startup] \033[94mRunning in Docker. Please wait.\033[0m"
-        f"http://{params['ip_address']}:{params['port_number']}",
     )
 else:
-    print(
+    # Start the subprocess
-        f"[{params['branding']}Startup] \033[91mWarning\033[0m TTS Subprocess Webserver failing to start process"
+    process = subprocess.Popen(["python", script_path])
-    )
+    # Check if the subprocess has started successfully
-    print(
+    if process.poll() is None:
-        f"[{params['branding']}Startup] \033[91mWarning\033[0m It could be that you have something on port:",
+        print(f"[{params['branding']}Startup] TTS Subprocess starting")
-        params["port_number"],
+        print(f"[{params['branding']}Startup]")
-    )
-    print(
-        f"[{params['branding']}Startup] \033[91mWarning\033[0m Or you have not started in a Python environement with all the necesssary bits installed"
-    )
-    print(
-        f"[{params['branding']}Startup] \033[91mWarning\033[0m Check you are starting Text-generation-webui with either the start_xxxxx file or the Python environment with cmd_xxxxx file."
-    )
-    print(
-        f"[{params['branding']}Startup] \033[91mWarning\033[0m xxxxx is the type of OS you are on e.g. windows, linux or mac."
-    )
-    print(
-        f"[{params['branding']}Startup] \033[91mWarning\033[0m Alternatively, you could check no other Python processes are running that shouldnt be e.g. Restart your computer is the simple way."
-    )
-    # Cleanly kill off this script, but allow text-generation-webui to keep running, albeit without this alltalk_tts
-    sys.exit(1)
-
-timeout = 120  # Adjust the timeout as needed
-
-# Introduce a delay before starting the check loop
-time.sleep(26)  # Wait 26 secs before checking if the tts_server.py has started up.
-start_time = time.time()
-while time.time() - start_time < timeout:
-    try:
-        response = requests.get(f"{base_url}/ready")
-        if response.status_code == 200:
-            break
-    except requests.RequestException as e:
-        # Print the exception for debugging purposes
         print(
-            f"[{params['branding']}Startup] \033[91mWarning\033[0m TTS Subprocess has NOT started up yet, Will keep trying for 120 seconds maximum. Please wait."
+            f"[{params['branding']}Startup] \033[94m {params['branding']}Settings & Documentation:\033[00m",
+            f"\033[92mhttp://{params['ip_address']}:{params['port_number']}\033[00m",
         )
-    time.sleep(4)
+        print(f"[{params['branding']}Startup]")
-else:
+    else:
-    print(
+        print(
-        f"[{params['branding']}Startup] Startup timed out. Check the server logs for more information."
+            f"[{params['branding']}Startup] \033[91mWarning\033[0m TTS Subprocess Webserver failing to start process"
-    )
+        )
-    # Cleanly kill off this script, but allow text-generation-webui to keep running, albeit without this alltalk_tts
+        print(
-    sys.exit(1)
+            f"[{params['branding']}Startup] \033[91mWarning\033[0m It could be that you have something on port:",
+            params["port_number"],
+        )
+        print(
+            f"[{params['branding']}Startup] \033[91mWarning\033[0m Or you have not started in a Python environement with all the necesssary bits installed"
+        )
+        print(
+            f"[{params['branding']}Startup] \033[91mWarning\033[0m Check you are starting Text-generation-webui with either the start_xxxxx file or the Python environment with cmd_xxxxx file."
+        )
+        print(
+            f"[{params['branding']}Startup] \033[91mWarning\033[0m xxxxx is the type of OS you are on e.g. windows, linux or mac."
+        )
+        print(
+            f"[{params['branding']}Startup] \033[91mWarning\033[0m Alternatively, you could check no other Python processes are running that shouldnt be e.g. Restart your computer is the simple way."
+        )
+        # Cleanly kill off this script, but allow text-generation-webui to keep running, albeit without this alltalk_tts
+        sys.exit(1)
+
+    timeout = startup_wait_time  # Gather timeout setting from startup_wait_time
+
+    # Introduce a delay before starting the check loop
+    time.sleep(26)  # Wait 26 secs before checking if the tts_server.py has started up.
+    start_time = time.time()
+    while time.time() - start_time < timeout:
+        try:
+            response = requests.get(f"{base_url}/ready")
+            if response.status_code == 200:
+                break
+        except requests.RequestException as e:
+            # Print the exception for debugging purposes
+            print(
+                f"[{params['branding']}Startup] \033[91mWarning\033[0m TTS Subprocess has NOT started up yet, Will keep trying for {timeout} seconds maximum. Please wait."
+            )
+        time.sleep(5)
+    else:
+        print(
+            f"\n[{params['branding']}Startup] Startup timed out. Full help available here \033[92mhttps://github.com/erew123/alltalk_tts#-help-with-problems\033[0m"
+        )
+        print(
+            f"[{params['branding']}Startup] On older system you may wish to open and edit \033[94mscript.py\033[0m with a text editor and changing the"
+        )
+        print(
+            f"[{params['branding']}Startup] \033[94mstartup_wait_time = 120\033[0m setting to something like \033[94mstartup_wait_time = 240\033[0m as this will allow"
+        )
+        print(
+            f"[{params['branding']}Startup] AllTalk more time to try load the model into your VRAM. Otherise please visit the Github for"
+        )
+        print(
+            f"[{params['branding']}Startup] a list of other possible troubleshooting options."
+        )
+        # Cleanly kill off this script, but allow text-generation-webui to keep running, albeit without this alltalk_tts
+        sys.exit(1)
 
 
 #####################################
@@ -340,6 +376,7 @@ def send_reload_request(tts_method):
         )
         return {"status": "error", "message": str(e)}
 
+
 ##################
 #### LOW VRAM ####
 ##################
@@ -380,7 +417,7 @@ def send_deepspeed_request(deepspeed_param):
             audio_path = this_dir / "templates" / "deepspeedenabled.wav"
         else:
             audio_path = this_dir / "templates" / "deepspeeddisabled.wav"
-        
+
         url = f"{base_url}/api/deepspeed?new_deepspeed_value={deepspeed_param}"
         headers = {"Content-Type": "application/json"}
         response = requests.post(url, headers=headers)
@@ -454,9 +491,13 @@ def combine(audio_files, output_folder, state):
 
     # Save the combined audio to a file with a specified sample rate
     if "character_menu" in state:
-        output_file_path = os.path.join(output_folder, f'{state["character_menu"]}_{int(time.time())}_combined.wav')
+        output_file_path = os.path.join(
+            output_folder, f'{state["character_menu"]}_{int(time.time())}_combined.wav'
+        )
     else:
-        output_file_path = os.path.join(output_folder, f'TTSOUT_{int(time.time())}_combined.wav')
+        output_file_path = os.path.join(
+            output_folder, f"TTSOUT_{int(time.time())}_combined.wav"
+        )
     sf.write(output_file_path, audio, samplerate=sample_rate)
     # Clean up unnecessary files
     for audio_file in audio_files:
@@ -487,12 +528,19 @@ def voice_preview(string):
     output_file = Path(params["output_folder_wav"]) / "voice_preview.wav"
     # Generate the audio
     language_code = languages.get(params["language"])
+    temperature = params["local_temperature"]
+    repetition_penalty = params["local_repetition_penalty"]
     # Convert the WindowsPath object to a string before using it in JSON payload
     output_file_str = output_file.as_posix()
     # Lock before making the generate request
     with process_lock:
         generate_response = send_generate_request(
-            string, params["voice"], language_code, output_file_str
+            string,
+            params["voice"],
+            language_code,
+            temperature,
+            repetition_penalty,
+            output_file_str,
         )
     # Check if lock is already acquired
     if process_lock.locked():
@@ -514,7 +562,7 @@ def process_text(text):
     text = html.unescape(text)
 
     # Replace ellipsis with a single dot
-    text = re.sub(r'\.{3,}', '.', text)
+    text = re.sub(r"\.{3,}", ".", text)
 
     # Pattern to identify combined narrator and character speech
     combined_pattern = r'(\*[^*"]+\*|"[^"*]+")'
@@ -529,22 +577,22 @@ def process_text(text):
     for match in re.finditer(combined_pattern, text):
         # Add the text before the match, if any, as ambiguous
         if start < match.start():
-            ambiguous_text = text[start:match.start()].strip()
+            ambiguous_text = text[start : match.start()].strip()
             if ambiguous_text:
-                ordered_parts.append(('ambiguous', ambiguous_text))
+                ordered_parts.append(("ambiguous", ambiguous_text))
 
         # Add the matched part as either narrator or character
         matched_text = match.group(0)
-        if matched_text.startswith('*') and matched_text.endswith('*'):
+        if matched_text.startswith("*") and matched_text.endswith("*"):
-            ordered_parts.append(('narrator', matched_text.strip('*').strip()))
+            ordered_parts.append(("narrator", matched_text.strip("*").strip()))
         elif matched_text.startswith('"') and matched_text.endswith('"'):
-            ordered_parts.append(('character', matched_text.strip('"').strip()))
+            ordered_parts.append(("character", matched_text.strip('"').strip()))
         else:
             # In case of mixed or improperly formatted parts
-            if '*' in matched_text:
+            if "*" in matched_text:
-                ordered_parts.append(('narrator', matched_text.strip('*').strip('"')))
+                ordered_parts.append(("narrator", matched_text.strip("*").strip('"')))
             else:
-                ordered_parts.append(('character', matched_text.strip('"').strip('*')))
+                ordered_parts.append(("character", matched_text.strip('"').strip("*")))
 
         # Update the start of the next segment
         start = match.end()
@@ -553,10 +601,11 @@ def process_text(text):
     if start < len(text):
         ambiguous_text = text[start:].strip()
         if ambiguous_text:
-            ordered_parts.append(('ambiguous', ambiguous_text))
+            ordered_parts.append(("ambiguous", ambiguous_text))
 
     return ordered_parts
 
+
 #################################
 #### TTS STANDARD GENERATION ####
 #################################
@@ -565,12 +614,14 @@ def output_modifier(string, state):
     if not params["activate"]:
         return string
     original_string = string
-    #print("ORIGINAL STRING IS:", original_string)
+    # print("ORIGINAL STRING IS:", original_string)
     cleaned_string = before_audio_generation(string, params)
     if cleaned_string is None:
         return
     string = cleaned_string
     language_code = languages.get(params["language"])
+    temperature = params["local_temperature"]
+    repetition_penalty = params["local_repetition_penalty"]
     # Create a list to store generated audio paths
     audio_files = []
     if process_lock.acquire(blocking=False):
@@ -585,29 +636,46 @@ def output_modifier(string, state):
                         continue
 
                     # Determine the voice to use based on the part type
-                    if part_type == 'narrator':
+                    if part_type == "narrator":
                         voice_to_use = params["narrator_voice"]
-                        print(f"[{params['branding']}TTSGen] \033[92mNarrator\033[0m")  # Green
+                        print(
-                    elif part_type == 'character':
+                            f"[{params['branding']}TTSGen] \033[92mNarrator\033[0m"
+                        )  # Green
+                    elif part_type == "character":
                         voice_to_use = params["voice"]
-                        print(f"[{params['branding']}TTSGen] \033[36mCharacter\033[0m")  # Yellow
+                        print(
+                            f"[{params['branding']}TTSGen] \033[36mCharacter\033[0m"
+                        )  # Yellow
                     else:
                         # Handle ambiguous parts based on user preference
-                        voice_to_use = params["voice"] if non_quoted_text_is else params["narrator_voice"]
+                        voice_to_use = (
-                        voice_description = "\033[36mCharacter (Text-not-inside)\033[0m" if non_quoted_text_is else "\033[92mNarrator (Text-not-inside)\033[0m"
+                            params["voice"]
+                            if non_quoted_text_is
+                            else params["narrator_voice"]
+                        )
+                        voice_description = (
+                            "\033[36mCharacter (Text-not-inside)\033[0m"
+                            if non_quoted_text_is
+                            else "\033[92mNarrator (Text-not-inside)\033[0m"
+                        )
                         print(f"[{params['branding']}TTSGen] {voice_description}")
 
                     # Replace multiple exclamation marks, question marks, or other punctuation with a single instance
-                    cleaned_part = re.sub(r'([!?.])\1+', r'\1', part)
+                    cleaned_part = re.sub(r"([!?.])\1+", r"\1", part)
                     # Further clean to remove any other unwanted characters
-                    cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\$]', '', cleaned_part)
+                    cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0100-\u017F\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u4E00-\u9FFF\u3400-\u4DBF\u20000-\u2A6DF\u3000-\u303F\$]', '', cleaned_part)
                     # Remove all newline characters (single or multiple)
-                    cleaned_part = re.sub(r'\n+', ' ', cleaned_part)
+                    cleaned_part = re.sub(r"\n+", " ", cleaned_part)
 
                     # Generate TTS and output to a file
                     output_filename = get_output_filename(state)
                     generate_response = send_generate_request(
-                        cleaned_part, voice_to_use, language_code, output_filename
+                        cleaned_part,
+                        voice_to_use,
+                        language_code,
+                        temperature,
+                        repetition_penalty,
+                        output_filename,
                     )
                     audio_path = generate_response.get("data", {}).get("audio_path")
                     audio_files_all_paragraphs.append(audio_path)
@@ -620,20 +688,29 @@ def output_modifier(string, state):
                 # Decode HTML entities first
                 cleaned_part = html.unescape(original_string)
                 # Replace multiple instances of certain punctuation marks with a single instance
-                cleaned_part = re.sub(r'([!?.])\1+', r'\1', cleaned_part)
+                cleaned_part = re.sub(r"([!?.])\1+", r"\1", cleaned_part)
                 # Further clean to remove any other unwanted characters
-                cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\$]', '', cleaned_part)
+                cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0100-\u017F\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\u4E00-\u9FFF\u3400-\u4DBF\u20000-\u2A6DF\u3000-\u303F\$]', '', cleaned_part)
                 # Remove all newline characters (single or multiple)
-                cleaned_part = re.sub(r'\n+', ' ', cleaned_part)
+                cleaned_part = re.sub(r"\n+", " ", cleaned_part)
                 # Process the part and give it a non-character name if being used vai API or standalone.
                 if "character_menu" in state:
-                    output_file = Path(f'{params["output_folder_wav"]}/{state["character_menu"]}_{int(time.time())}.wav')
+                    output_file = Path(
+                        f'{params["output_folder_wav"]}/{state["character_menu"]}_{int(time.time())}.wav'
+                    )
                 else:
-                    output_file = Path(f'{params["output_folder_wav"]}/TTSOUT_{int(time.time())}.wav')
+                    output_file = Path(
+                        f'{params["output_folder_wav"]}/TTSOUT_{int(time.time())}.wav'
+                    )
                 output_file_str = output_file.as_posix()
                 output_file = get_output_filename(state)
                 generate_response = send_generate_request(
-                    cleaned_part, params["voice"], language_code, output_file_str
+                    cleaned_part,
+                    params["voice"],
+                    language_code,
+                    temperature,
+                    repetition_penalty,
+                    output_file_str,
                 )
                 audio_path = generate_response.get("data", {}).get("audio_path")
                 final_output_file = audio_path
@@ -674,20 +751,28 @@ def output_modifier(string, state):
 
 def get_output_filename(state):
     if "character_menu" in state:
-        return Path(f'{params["output_folder_wav"]}/{state["character_menu"]}_{str(uuid.uuid4())[:8]}.wav').as_posix()
+        return Path(
+            f'{params["output_folder_wav"]}/{state["character_menu"]}_{str(uuid.uuid4())[:8]}.wav'
+        ).as_posix()
     else:
-        return Path(f'{params["output_folder_wav"]}/TTSOUT_{str(uuid.uuid4())[:8]}.wav').as_posix()
+        return Path(
+            f'{params["output_folder_wav"]}/TTSOUT_{str(uuid.uuid4())[:8]}.wav'
+        ).as_posix()
 
 
 ###############################################
 #### SEND GENERATION REQUEST TO TTS ENGINE ####
 ###############################################
-def send_generate_request(text, voice, language, output_file):
+def send_generate_request(
+    text, voice, language, temperature, repetition_penalty, output_file
+):
     url = f"{base_url}/api/generate"
     payload = {
         "text": text,
         "voice": voice,
         "language": language,
+        "temperature": temperature,
+        "repetition_penalty": repetition_penalty,
         "output_file": output_file,
     }
     headers = {"Content-Type": "application/json"}
@@ -712,12 +797,14 @@ def state_modifier(state):
     state["stream"] = False
     return state
 
+
 def update_narrator_enabled(value):
     if value == "Enabled":
         params["narrator_enabled"] = True
     elif value == "Disabled":
         params["narrator_enabled"] = False
 
+
 def update_non_quoted_text_is(value):
     global non_quoted_text_is
     if value == "Narrator":
@@ -725,6 +812,7 @@ def update_non_quoted_text_is(value):
     elif value == "Char":
         non_quoted_text_is = True
 
+
 def input_modifier(string, state):
     if not params["activate"]:
         return string
@@ -735,35 +823,53 @@ def input_modifier(string, state):
 
 def ui():
     with gr.Accordion(params["branding"] + " TTS (XTTSv2)"):
+        # Activate alltalk_tts, Enable autoplay, Show text
         with gr.Row():
-            activate = gr.Checkbox(value=params["activate"], label="Activate TTS")
+            activate = gr.Checkbox(value=params["activate"], label="Enable TTS")
-            autoplay = gr.Checkbox(
+            autoplay = gr.Checkbox(value=params["autoplay"], label="Autoplay TTS")
-                value=params["autoplay"], label="Play TTS automatically"
+            show_text = gr.Checkbox(value=params["show_text"], label="Show Text")
-            )
 
+        # Low vram enable, Deepspeed enable, Remove trailing dots
         with gr.Row():
-            show_text = gr.Checkbox(
+            low_vram = gr.Checkbox(
-                value=params["show_text"], label="Show message text under audio player"
+                value=params["low_vram"], label="Enable Low VRAM Mode"
             )
+            low_vram_play = gr.HTML(visible=False)
+            deepspeed_checkbox = gr.Checkbox(
+                value=params["deepspeed_activate"],
+                label="Enable DeepSpeed",
+                visible=deepspeed_installed,
+            )
+            deepspeed_checkbox_play = gr.HTML(visible=False)
             remove_trailing_dots = gr.Checkbox(
-                value=params["remove_trailing_dots"],
+                value=params["remove_trailing_dots"], label='Remove trailing "."'
-                label='Remove trailing "." from text segments before generation',
             )
 
+        # TTS method, Character voice selection
         with gr.Row():
+            model_loader_choices = ["API TTS", "API Local", "XTTSv2 Local"]
+            if finetuned_model:
+                model_loader_choices.append("XTTSv2 FT")
+            tts_radio_buttons = gr.Radio(
+                choices=model_loader_choices,
+                label="TTS Method (Each method sounds slightly different)",
+                value=gr_modelchoice,  # Set the default value
+            )
+            tts_radio_buttons_play = gr.HTML(visible=False)
             with gr.Row():
                 available_voices = get_available_voices()
-                default_voice = params["voice"]
+                default_voice = params[
-                # Check if the default voice is in the list of available voices
+                    "voice"
+                ]  # Check if the default voice is in the list of available voices
+
                 if default_voice not in available_voices:
-                    # Handle the case where the default voice is not in the list (choose a default value or update it)
                     default_voice = available_voices[
                         0
                     ]  # Choose the first available voice as the default
                 # Add allow_custom_value=True to the Dropdown
                 voice = gr.Dropdown(
                     available_voices,
-                    label="Default Voice",
+                    label="Character Voice",
                     value=default_voice,
                     allow_custom_value=True,
                 )
@@ -777,14 +883,11 @@ def ui():
                     "refresh-button",
                 )
 
-            language = gr.Dropdown(
+        # Language, Narrator voice
-                languages.keys(),
-                label="Language",
-                allow_custom_value=True,
-                value=params["language"],
-            )
-
         with gr.Row():
+            language = gr.Dropdown(
+                languages.keys(), label="Language", value=params["language"]
+            )
             with gr.Row():
                 narrator_voice_gr = gr.Dropdown(
                     get_available_voices(),
@@ -801,43 +904,42 @@ def ui():
                     },
                     "refresh-button",
                 )
+
+        # Temperature, Repetition Penalty
+        with gr.Row():
+            local_temperature_gr = gr.Slider(
+                minimum=0.05,
+                maximum=1,
+                step=0.05,
+                label="Temperature",
+                value=params["local_temperature"],
+            )
+            local_repetition_penalty_gr = gr.Slider(
+                minimum=0.5,
+                maximum=20,
+                step=0.5,
+                label="Repetition Penalty",
+                value=params["local_repetition_penalty"],
+            )
+
+        # Narrator enable, Non quoted text, Explanation text
+        with gr.Row():
+            with gr.Row():
                 narrator_enabled_gr = gr.Radio(
                     choices={"Enabled": "true", "Disabled": "false"},
-                    label="Narrator Activation",
+                    label="Narrator",
                     value="Enabled" if params.get("narrator_enabled") else "Disabled",
                 )
                 non_quoted_text_is_gr = gr.Radio(
-                    choices={"Char": "true", "Narrator": "false"},
+                    choices={"Character": "true", "Narrator": "false"},
-                    label='Text NOT inside of * or " is',
+                    label='Unmarked text NOT inside of * or " is',
-                    value="Char" if non_quoted_text_is else "Narrator",
+                    value="Character" if non_quoted_text_is else "Narrator",
+                )
+                explanation_text = gr.HTML(
+                    f"<p>⚙️ <a href='http://{params['ip_address']}:{params['port_number']}'>Settings and Documentation Page</a><a href='http://{params['ip_address']}:{params['port_number']}'></a>⚙️<br>- Low VRAM Mode and Deepspeed take 15 seconds to be enabled or disabled.<br>- The DeepSpeed checkbox is only visible if DeepSpeed is present.</p>"
                 )
 
-        with gr.Row():
+        # Preview speech
-            low_vram = gr.Checkbox(
-                value=params["low_vram"], label="Low VRAM mode (Read NOTE)"
-            )
-            low_vram_play = gr.HTML(visible=False)
-            deepspeed_checkbox = gr.Checkbox(
-                value=params["deepspeed_activate"],
-                label="Activate DeepSpeed (Read NOTE)",
-                visible=deepspeed_installed,
-            )
-            deepspeed_checkbox_play = gr.HTML(visible=False)
-
-        with gr.Row():
-            model_loader_choices=["API TTS", "API Local", "XTTSv2 Local"]
-            if finetuned_model:
-                model_loader_choices.append("XTTSv2 FT")
-            tts_radio_buttons = gr.Radio(
-                choices=model_loader_choices,
-                label="Select TTS Generation Method (Read NOTE)",
-                value=gr_modelchoice,  # Set the default value
-            )
-            tts_radio_buttons_play = gr.HTML(visible=False)
-            explanation_text = gr.HTML(
-                f"<p>⚙️ <a href='http://{params['ip_address']}:{params['port_number']}'>Click here for the Settings page, help & instructions</a><a href='http://{params['ip_address']}:{params['port_number']}'></a>⚙️<br>NOTE: Switching Model Type, Low VRAM & DeepSpeed, each takes 15 seconds. Each TTS generation method has a slightly different sound. DeepSpeed checkbox is only visible if DeepSpeed is installed on your system."
-            )
-
         with gr.Row():
             preview_text = gr.Text(
                 show_label=False,
@@ -907,18 +1009,34 @@ def ui():
     autoplay.change(lambda x: params.update({"autoplay": x}), autoplay, None)
     low_vram.change(lambda x: params.update({"low_vram": x}), low_vram, None)
     low_vram.change(lambda x: send_lowvram_request(x), low_vram, low_vram_play, None)
-    tts_radio_buttons.change(send_reload_request, tts_radio_buttons, tts_radio_buttons_play, None)
+    tts_radio_buttons.change(
-    deepspeed_checkbox.change(send_deepspeed_request, deepspeed_checkbox, deepspeed_checkbox_play, None)
+        send_reload_request, tts_radio_buttons, tts_radio_buttons_play, None
+    )
+    deepspeed_checkbox.change(
+        send_deepspeed_request, deepspeed_checkbox, deepspeed_checkbox_play, None
+    )
     remove_trailing_dots.change(
         lambda x: params.update({"remove_trailing_dots": x}), remove_trailing_dots, None
     )
     voice.change(lambda x: params.update({"voice": x}), voice, None)
     language.change(lambda x: params.update({"language": x}), language, None)
 
+    # TSS Settings
+    local_temperature_gr.change(
+        lambda x: params.update({"local_temperature": x}), local_temperature_gr, None
+    )
+    local_repetition_penalty_gr.change(
+        lambda x: params.update({"local_repetition_penalty": x}),
+        local_repetition_penalty_gr,
+        None,
+    )
+
     # Narrator selection actions
     narrator_enabled_gr.change(update_narrator_enabled, narrator_enabled_gr, None)
     non_quoted_text_is_gr.change(update_non_quoted_text_is, non_quoted_text_is_gr, None)
-    narrator_voice_gr.change(lambda x: params.update({"narrator_voice": x}), narrator_voice_gr, None)
+    narrator_voice_gr.change(
+        lambda x: params.update({"narrator_voice": x}), narrator_voice_gr, None
+    )
 
     # Play preview
     preview_text.submit(voice_preview, preview_text, preview_audio)

templates/STfiles/alltalk.js

@@ -0,0 +1,833 @@
+import { doExtrasFetch, getApiUrl, modules } from '../../extensions.js';
+import { saveTtsProviderSettings } from './index.js';
+
+export { AllTalkTtsProvider };
+
+class AllTalkTtsProvider {
+    //########//
+    // Config //
+    //########//
+
+    settings = {};
+    constructor() {
+        // Initialize with default settings if they are not already set
+        this.settings = {
+            provider_endpoint: this.settings.provider_endpoint || 'http://localhost:7851',
+            language: this.settings.language || 'en',
+            voiceMap: this.settings.voiceMap || {},
+            at_generation_method: this.settings.at_generation_method || 'standard_generation',
+            narrator_enabled: this.settings.narrator_enabled || 'false',
+            at_narrator_text_not_inside: this.settings.at_narrator_text_not_inside || 'narrator',
+            narrator_voice_gen: this.settings.narrator_voice_gen || 'female_01.wav',
+            finetuned_model: this.settings.finetuned_model || 'false'
+        };
+        // Separate property for dynamically updated settings from the server
+        this.dynamicSettings = {
+            modelsAvailable: [],
+            currentModel: '',
+            deepspeed_available: false,
+            deepSpeedEnabled: false,
+            lowVramEnabled: false,
+        };
+    }
+    ready = false;
+    voices = [];
+    separator = '. ';
+    audioElement = document.createElement('audio');
+
+    languageLabels = {
+        'Arabic': 'ar',
+        'Brazilian Portuguese': 'pt',
+        'Chinese': 'zh-cn',
+        'Czech': 'cs',
+        'Dutch': 'nl',
+        'English': 'en',
+        'French': 'fr',
+        'German': 'de',
+        'Italian': 'it',
+        'Polish': 'pl',
+        'Russian': 'ru',
+        'Spanish': 'es',
+        'Turkish': 'tr',
+        'Japanese': 'ja',
+        'Korean': 'ko',
+        'Hungarian': 'hu',
+        'Hindi': 'hi',
+    };
+
+    get settingsHtml() {
+        let html = `<div class="at-settings-separator">AllTalk Settings</div>`;
+
+        html += `<div class="at-settings-row">
+
+        <div class="at-settings-option">
+            <label for="at_generation_method">AllTalk TTS Generation Method</label>
+                <select id="at_generation_method">
+                <option value="standard_generation">Standard Audio Generation (AT Narrator - Optional)</option>
+                <option value="streaming_enabled">Streaming Audio Generation (AT Narrator - Disabled)</option>
+        </select>
+        </div>
+        </div>`;
+
+        html += `<div class="at-settings-row">
+
+        <div class="at-settings-option">
+            <label for="at_narrator_enabled">AT Narrator</label>
+                <select id="at_narrator_enabled">
+                <option value="true">Enabled</option>
+                <option value="false">Disabled</option>
+        </select>
+        </div>
+
+        <div class="at-settings-option">
+            <label for="at_narrator_text_not_inside">Text Not Inside * or " is</label>
+                <select id="at_narrator_text_not_inside">
+                <option value="narrator">Narrator</option>
+                <option value="character">Character</option>
+        </select>
+        </div>
+
+    </div>`;
+
+        html += `<div class="at-settings-row">
+        <div class="at-settings-option">
+            <label for="narrator_voice">Narrator Voice</label>
+            <select id="narrator_voice">`;
+        if (this.voices) {
+            for (let voice of this.voices) {
+                html += `<option value="${voice.voice_id}">${voice.name}</option>`;
+            }
+        }
+        html += `</select>
+        </div>
+        <div class="at-settings-option">
+            <label for="language_options">Language</label>
+            <select id="language_options">`;
+        for (let language in this.languageLabels) {
+            html += `<option value="${this.languageLabels[language]}" ${this.languageLabels[language] === this.settings?.language ? 'selected="selected"' : ''}>${language}</option>`;
+        }
+        html += `</select>
+        </div>
+    </div>`;
+
+
+        html += `<div class="at-model-endpoint-row">
+    <div class="at-model-option">
+            <label for="switch_model">Switch Model</label>
+            <select id="switch_model">
+            <option value="api_tts">API TTS</option>
+            <option value="api_local">API Local</option>
+            <option value="xttsv2_local">XTTSv2 Local</option>
+        </select>
+        </div>
+
+        <div class="at-endpoint-option">
+            <label for="at_server">AllTalk Endpoint:</label>
+            <input id="at_server" type="text" class="text_pole" maxlength="80" value="${this.settings.provider_endpoint}"/>
+        </div>
+   </div>`;
+
+
+        html += `<div class="at-model-endpoint-row">
+    <div class="at-settings-option">
+        <label for="low_vram">Low VRAM</label>
+        <input id="low_vram" type="checkbox"/>
+    </div>
+    <div class="at-settings-option">
+        <label for="deepspeed">DeepSpeed</label>
+        <input id="deepspeed" type="checkbox"/>
+    </div>
+    <div class="at-settings-option status-option">
+        <span>Status: <span id="status_info">Ready</span></span>
+    </div>
+    <div class="at-settings-option empty-option">
+        <!-- This div remains empty for spacing -->
+    </div>
+</div>`;
+
+
+        html += `<div class="at-website-row">
+        <div class="at-website-option">
+        <span>AllTalk <a target="_blank" href="${this.settings.provider_endpoint}">Config & Docs</a>.</span>
+    </div>
+
+    <div class="at-website-option">
+        <span>AllTalk <a target="_blank" href="https://github.com/erew123/alltalk_tts/">Website</a>.</span>
+    </div>
+</div>`;
+
+        html += `<div class="at-website-row">
+<div class="at-website-option">
+<span><strong>Text-generation-webui</strong> users - Uncheck <strong>Enable TTS</strong> in Text-generation-webui.</span>
+</div>
+</div>`;
+
+        return html;
+    }
+
+
+    //#################//
+    // Startup ST & AT //
+    //#################//
+
+    async loadSettings(settings) {
+        updateStatus('Offline');
+
+        if (Object.keys(settings).length === 0) {
+            console.info('Using default AllTalk TTS Provider settings');
+        } else {
+            // Populate settings with provided values, ignoring server-provided settings
+            for (const key in settings) {
+                if (key in this.settings) {
+                    this.settings[key] = settings[key];
+                } else {
+                    console.debug(`Ignoring non-user-configurable setting: ${key}`);
+                }
+            }
+        }
+
+        // Update UI elements to reflect the loaded settings
+        $('#at_server').val(this.settings.provider_endpoint);
+        $('#language_options').val(this.settings.language);
+        //$('#voicemap').val(this.settings.voiceMap);
+        $('#at_generation_method').val(this.settings.at_generation_method);
+        $('#at_narrator_enabled').val(this.settings.narrator_enabled);
+        $('#at_narrator_text_not_inside').val(this.settings.at_narrator_text_not_inside);
+        $('#narrator_voice').val(this.settings.narrator_voice_gen);
+
+        console.debug('AllTalkTTS: Settings loaded');
+        try {
+            // Check if TTS provider is ready
+            await this.checkReady();
+            await this.updateSettingsFromServer(); // Fetch dynamic settings from the TTS server
+            await this.fetchTtsVoiceObjects(); // Fetch voices only if service is ready
+            this.updateNarratorVoicesDropdown();
+            this.updateLanguageDropdown();
+            this.setupEventListeners();
+            this.applySettingsToHTML();
+            updateStatus('Ready');
+        } catch (error) {
+            console.error("Error loading settings:", error);
+            updateStatus('Offline');
+        }
+    }
+
+    applySettingsToHTML() {
+        // Apply loaded settings or use defaults
+        const narratorVoiceSelect = document.getElementById('narrator_voice');
+        const atNarratorSelect = document.getElementById('at_narrator_enabled');
+        const textNotInsideSelect = document.getElementById('at_narrator_text_not_inside');
+        const generationMethodSelect = document.getElementById('at_generation_method');
+        this.settings.narrator_voice = this.settings.narrator_voice_gen;
+        // Apply settings to Narrator Voice dropdown
+        if (narratorVoiceSelect && this.settings.narrator_voice) {
+            narratorVoiceSelect.value = this.settings.narrator_voice.replace('.wav', '');
+        }
+        // Apply settings to AT Narrator Enabled dropdown
+        if (atNarratorSelect) {
+            // Sync the state with the checkbox in index.js
+            const ttsPassAsterisksCheckbox = document.getElementById('tts_pass_asterisks'); // Access the checkbox from index.js
+            const ttsNarrateQuotedCheckbox = document.getElementById('tts_narrate_quoted'); // Access the checkbox from index.js
+            const ttsNarrateDialoguesCheckbox = document.getElementById('tts_narrate_dialogues'); // Access the checkbox from index.js
+            // Sync the state with the checkbox in index.js
+            if (this.settings.narrator_enabled) {
+                ttsPassAsterisksCheckbox.checked = false;
+                $('#tts_pass_asterisks').click(); // Simulate a click event
+                $('#tts_pass_asterisks').trigger('change');
+            }
+            if (!this.settings.narrator_enabled) {
+                ttsPassAsterisksCheckbox.checked = true;
+                $('#tts_pass_asterisks').click(); // Simulate a click event
+                $('#tts_pass_asterisks').trigger('change');
+            }
+            // Uncheck and set tts_narrate_quoted to false if narrator is enabled
+            if (this.settings.narrator_enabledd) {
+                ttsNarrateQuotedCheckbox.checked = true;
+                ttsNarrateDialoguesCheckbox.checked = true;
+                // Trigger click events instead of change events
+                $('#tts_narrate_quoted').click();
+                $('#tts_narrate_quoted').trigger('change');
+                $('#tts_narrate_dialogues').click();
+                $('#tts_narrate_dialogues').trigger('change');
+            }
+            atNarratorSelect.value = this.settings.narrator_enabled.toString();
+            this.settings.narrator_enabled = this.settings.narrator_enabled.toString();
+        }
+        // Apply settings to the Language dropdown
+        const languageSelect = document.getElementById('language_options');
+        if (languageSelect && this.settings.language) {
+            languageSelect.value = this.settings.language;
+        }
+        // Apply settings to Text Not Inside dropdown
+        if (textNotInsideSelect && this.settings.text_not_inside) {
+            textNotInsideSelect.value = this.settings.text_not_inside;
+            this.settings.at_narrator_text_not_inside = this.settings.text_not_inside;
+        }
+        // Apply settings to Generation Method dropdown
+        if (generationMethodSelect && this.settings.at_generation_method) {
+            generationMethodSelect.value = this.settings.at_generation_method;
+        }
+        // Additional logic to disable/enable dropdowns based on the selected generation method
+        const isStreamingEnabled = this.settings.at_generation_method === 'streaming_enabled';
+        if (isStreamingEnabled) {
+            // Disable certain dropdowns when streaming is enabled
+            if (atNarratorSelect) atNarratorSelect.disabled = true;
+            if (textNotInsideSelect) textNotInsideSelect.disabled = true;
+            if (narratorVoiceSelect) narratorVoiceSelect.disabled = true;
+        } else {
+            // Enable dropdowns for standard generation
+            if (atNarratorSelect) atNarratorSelect.disabled = false;
+            if (textNotInsideSelect) textNotInsideSelect.disabled = !this.settings.narrator_enabled;
+            if (narratorVoiceSelect) narratorVoiceSelect.disabled = !this.settings.narrator_enabled;
+        }
+        const modelSelect = document.getElementById('switch_model');
+        if (this.settings.finetuned_model === 'true') {
+            const ftOption = document.createElement('option');
+            ftOption.value = 'XTTSv2 FT';
+            ftOption.textContent = 'XTTSv2 FT';
+            modelSelect.appendChild(ftOption);
+        }
+    }
+
+    //##############################//
+    // Check AT Server is Available //
+    //##############################//
+
+    async checkReady() {
+        try {
+            const response = await fetch(`${this.settings.provider_endpoint}/api/ready`);
+            // Check if the HTTP request was successful
+            if (!response.ok) {
+                throw new Error(`HTTP Error Response: ${response.status} ${response.statusText}`);
+            }
+            const statusText = await response.text();
+            // Check if the response is 'Ready'
+            if (statusText === 'Ready') {
+                this.ready = true; // Set the ready flag to true
+                console.log('TTS service is ready.');
+            } else {
+                this.ready = false;
+                console.log('TTS service is not ready.');
+            }
+        } catch (error) {
+            console.error('Error checking TTS service readiness:', error);
+            this.ready = false; // Ensure ready flag is set to false in case of error
+        }
+    }
+
+    //######################//
+    // Get Available Voices //
+    //######################//
+
+    async fetchTtsVoiceObjects() {
+        const response = await fetch(`${this.settings.provider_endpoint}/api/voices`);
+        if (!response.ok) {
+            const errorText = await response.text();
+            throw new Error(`HTTP ${response.status}: ${errorText}`);
+        }
+        const data = await response.json();
+        const voices = data.voices.map(filename => {
+            const voiceName = filename.replace('.wav', '');
+            return {
+                name: voiceName,
+                voice_id: voiceName,
+                preview_url: null, // Preview URL will be dynamically generated
+                lang: 'en' // Default language
+            };
+        });
+        this.voices = voices; // Assign to the class property
+        return voices; // Also return this list
+    }
+
+    //##########################################//
+    // Get Current AT Server Config & Update ST //
+    //##########################################//
+
+    async updateSettingsFromServer() {
+        try {
+            // Fetch current settings
+            const response = await fetch(`${this.settings.provider_endpoint}/api/currentsettings`);
+            if (!response.ok) {
+                throw new Error(`Failed to fetch current settings: ${response.statusText}`);
+            }
+            const currentSettings = await response.json();
+            // Update internal settings
+            this.settings.modelsAvailable = currentSettings.models_available;
+            this.settings.currentModel = currentSettings.current_model_loaded;
+            this.settings.deepspeed_available = currentSettings.deepspeed_available;
+            this.settings.deepSpeedEnabled = currentSettings.deepspeed_status;
+            this.settings.lowVramEnabled = currentSettings.low_vram_status;
+            this.settings.finetuned_model = currentSettings.finetuned_model
+            // Update HTML elements
+            this.updateModelDropdown();
+            this.updateCheckboxes();
+        } catch (error) {
+            console.error(`Error updating settings from server: ${error}`);
+        }
+    }
+
+    //###################################################//
+    // Get Current AT Server Config & Update ST (Models) //
+    //###################################################//
+
+    updateModelDropdown() {
+        const modelSelect = document.getElementById('switch_model');
+        if (modelSelect) {
+            modelSelect.innerHTML = ''; // Clear existing options
+            this.settings.modelsAvailable.forEach(model => {
+                const option = document.createElement('option');
+                option.value = model.model_name;
+                option.textContent = model.model_name; // Use model_name instead of name
+                option.selected = model.model_name === this.settings.currentModel;
+                modelSelect.appendChild(option);
+            });
+        }
+    }
+
+    //#######################################################//
+    // Get Current AT Server Config & Update ST (DS and LVR) //
+    //#######################################################//
+
+    updateCheckboxes() {
+        const deepspeedCheckbox = document.getElementById('deepspeed');
+        const lowVramCheckbox = document.getElementById('low_vram');
+        if (lowVramCheckbox) lowVramCheckbox.checked = this.settings.lowVramEnabled;
+        if (deepspeedCheckbox) {
+            deepspeedCheckbox.checked = this.settings.deepSpeedEnabled;
+            deepspeedCheckbox.disabled = !this.settings.deepspeed_available; // Disable checkbox if deepspeed is not available
+        }
+    }
+
+    //###############################################################//
+    // Get Current AT Server Config & Update ST (AT Narrator Voices) //
+    //###############################################################//
+
+    updateNarratorVoicesDropdown() {
+        const narratorVoiceSelect = document.getElementById('narrator_voice');
+        if (narratorVoiceSelect && this.voices) {
+            // Clear existing options
+            narratorVoiceSelect.innerHTML = '';
+            // Add new options
+            for (let voice of this.voices) {
+                const option = document.createElement('option');
+                option.value = voice.voice_id;
+                option.textContent = voice.name;
+                narratorVoiceSelect.appendChild(option);
+            }
+        }
+    }
+
+    //######################################################//
+    // Get Current AT Server Config & Update ST (Languages) //
+    //######################################################//
+
+    updateLanguageDropdown() {
+        const languageSelect = document.getElementById('language_options');
+        if (languageSelect) {
+            // Ensure default language is set
+            this.settings.language = this.settings.language;
+
+            languageSelect.innerHTML = '';
+            for (let language in this.languageLabels) {
+                const option = document.createElement('option');
+                option.value = this.languageLabels[language];
+                option.textContent = language;
+                if (this.languageLabels[language] === this.settings.language) {
+                    option.selected = true;
+                }
+                languageSelect.appendChild(option);
+            }
+        }
+    }
+
+    //########################################//
+    // Start AT TTS extenstion page listeners //
+    //########################################//
+
+    setupEventListeners() {
+
+        let debounceTimeout;
+        const debounceDelay = 500; // Milliseconds
+
+        // Define the event handler function
+        const onModelSelectChange = async (event) => {
+            console.log("Model select change event triggered"); // Debugging statement
+            const selectedModel = event.target.value;
+            console.log(`Selected model: ${selectedModel}`); // Debugging statement 
+            // Set status to Processing
+            updateStatus('Processing');
+            try {
+                const response = await fetch(`${this.settings.provider_endpoint}/api/reload?tts_method=${encodeURIComponent(selectedModel)}`, {
+                    method: 'POST'
+                });
+                if (!response.ok) {
+                    throw new Error(`HTTP Error: ${response.status}`);
+                }
+                const data = await response.json();
+                console.log("POST response data:", data); // Debugging statement 
+                // Set status to Ready if successful
+                updateStatus('Ready');
+            } catch (error) {
+                console.error("POST request error:", error); // Debugging statement
+                // Set status to Error in case of failure
+                updateStatus('Error');
+            }
+
+            // Handle response or error
+        };
+
+        const debouncedModelSelectChange = (event) => {
+            clearTimeout(debounceTimeout);
+            debounceTimeout = setTimeout(() => {
+                onModelSelectChange(event);
+            }, debounceDelay);
+        };
+
+        // Switch Model Listener
+        const modelSelect = document.getElementById('switch_model');
+        if (modelSelect) {
+            // Remove the event listener if it was previously added
+            modelSelect.removeEventListener('change', debouncedModelSelectChange);
+            // Add the debounced event listener
+            modelSelect.addEventListener('change', debouncedModelSelectChange);
+        }
+
+        // DeepSpeed Listener
+        const deepspeedCheckbox = document.getElementById('deepspeed');
+        if (deepspeedCheckbox) {
+            deepspeedCheckbox.addEventListener('change', async (event) => {
+                const deepSpeedValue = event.target.checked ? 'True' : 'False';
+                // Set status to Processing
+                updateStatus('Processing');
+                try {
+                    const response = await fetch(`${this.settings.provider_endpoint}/api/deepspeed?new_deepspeed_value=${deepSpeedValue}`, {
+                        method: 'POST'
+                    });
+                    if (!response.ok) {
+                        throw new Error(`HTTP Error: ${response.status}`);
+                    }
+                    const data = await response.json();
+                    console.log("POST response data:", data); // Debugging statement
+                    // Set status to Ready if successful
+                    updateStatus('Ready');
+                } catch (error) {
+                    console.error("POST request error:", error); // Debugging statement
+                    // Set status to Error in case of failure
+                    updateStatus('Error');
+                }
+            });
+        }
+
+        // Low VRAM Listener
+        const lowVramCheckbox = document.getElementById('low_vram');
+        if (lowVramCheckbox) {
+            lowVramCheckbox.addEventListener('change', async (event) => {
+                const lowVramValue = event.target.checked ? 'True' : 'False';
+                // Set status to Processing
+                updateStatus('Processing');
+                try {
+                    const response = await fetch(`${this.settings.provider_endpoint}/api/lowvramsetting?new_low_vram_value=${lowVramValue}`, {
+                        method: 'POST'
+                    });
+                    if (!response.ok) {
+                        throw new Error(`HTTP Error: ${response.status}`);
+                    }
+                    const data = await response.json();
+                    console.log("POST response data:", data); // Debugging statement
+                    // Set status to Ready if successful
+                    updateStatus('Ready');
+                } catch (error) {
+                    console.error("POST request error:", error); // Debugging statement
+                    // Set status to Error in case of failure
+                    updateStatus('Error');
+                }
+            });
+        }
+
+        // Narrator Voice Dropdown Listener
+        const narratorVoiceSelect = document.getElementById('narrator_voice');
+        if (narratorVoiceSelect) {
+            narratorVoiceSelect.addEventListener('change', (event) => {
+                this.settings.narrator_voice_gen = `${event.target.value}.wav`;
+                this.onSettingsChange(); // Save the settings after change
+            });
+        }
+
+        const textNotInsideSelect = document.getElementById('at_narrator_text_not_inside');
+        if (textNotInsideSelect) {
+            textNotInsideSelect.addEventListener('change', (event) => {
+                this.settings.text_not_inside = event.target.value;
+                this.onSettingsChange(); // Save the settings after change
+            });
+        }
+
+        // AT Narrator Dropdown Listener
+        const atNarratorSelect = document.getElementById('at_narrator_enabled');
+        const ttsPassAsterisksCheckbox = document.getElementById('tts_pass_asterisks'); // Access the checkbox from index.js
+        const ttsNarrateQuotedCheckbox = document.getElementById('tts_narrate_quoted'); // Access the checkbox from index.js
+        const ttsNarrateDialoguesCheckbox = document.getElementById('tts_narrate_dialogues'); // Access the checkbox from index.js
+
+        if (atNarratorSelect && textNotInsideSelect && narratorVoiceSelect) {
+            atNarratorSelect.addEventListener('change', (event) => {
+                const isNarratorEnabled = event.target.value === 'true';
+                this.settings.narrator_enabled = isNarratorEnabled; // Update the setting here
+                textNotInsideSelect.disabled = !isNarratorEnabled;
+                narratorVoiceSelect.disabled = !isNarratorEnabled;
+
+                // Sync the state with the checkbox in index.js
+                if (isNarratorEnabled) {
+                    ttsPassAsterisksCheckbox.checked = false;
+                    $('#tts_pass_asterisks').click(); // Simulate a click event
+                    $('#tts_pass_asterisks').trigger('change');
+                }
+                if (!isNarratorEnabled) {
+                    ttsPassAsterisksCheckbox.checked = true;
+                    $('#tts_pass_asterisks').click(); // Simulate a click event
+                    $('#tts_pass_asterisks').trigger('change');
+                }
+                // Uncheck and set tts_narrate_quoted to false if narrator is enabled
+                if (isNarratorEnabled) {
+                    ttsNarrateQuotedCheckbox.checked = true;
+                    ttsNarrateDialoguesCheckbox.checked = true;
+                    // Trigger click events instead of change events
+                    $('#tts_narrate_quoted').click();
+                    $('#tts_narrate_quoted').trigger('change');
+                    $('#tts_narrate_dialogues').click();
+                    $('#tts_narrate_dialogues').trigger('change');
+                }
+                this.onSettingsChange(); // Save the settings after change
+            });
+        }
+
+
+        // Event Listener for AT Generation Method Dropdown
+        const atGenerationMethodSelect = document.getElementById('at_generation_method');
+        const atNarratorEnabledSelect = document.getElementById('at_narrator_enabled');
+        if (atGenerationMethodSelect) {
+            atGenerationMethodSelect.addEventListener('change', (event) => {
+                const selectedMethod = event.target.value;
+
+                if (selectedMethod === 'streaming_enabled') {
+                    // Disable and unselect AT Narrator
+                    atNarratorEnabledSelect.disabled = true;
+                    atNarratorEnabledSelect.value = 'false';
+                    textNotInsideSelect.disabled = true;
+                    narratorVoiceSelect.disabled = true;
+                } else if (selectedMethod === 'standard_generation') {
+                    // Enable AT Narrator
+                    atNarratorEnabledSelect.disabled = false;
+                }
+                this.settings.at_generation_method = selectedMethod; // Update the setting here
+                this.onSettingsChange(); // Save the settings after change
+            });
+        }
+
+        // Listener for Language Dropdown
+        const languageSelect = document.getElementById('language_options');
+        if (languageSelect) {
+            languageSelect.addEventListener('change', (event) => {
+                this.settings.language = event.target.value;
+                this.onSettingsChange(); // Save the settings after change
+            });
+        }
+
+        // Listener for AllTalk Endpoint Input
+        const atServerInput = document.getElementById('at_server');
+        if (atServerInput) {
+            atServerInput.addEventListener('input', (event) => {
+                this.settings.provider_endpoint = event.target.value;
+                this.onSettingsChange(); // Save the settings after change
+            });
+        }
+
+    }
+
+    //#############################//
+    // Store ST interface settings //
+    //#############################//
+
+    onSettingsChange() {
+        // Update settings based on the UI elements
+        //this.settings.provider_endpoint = $('#at_server').val();
+        this.settings.language = $('#language_options').val();
+        //this.settings.voiceMap = $('#voicemap').val();
+        this.settings.at_generation_method = $('#at_generation_method').val();
+        this.settings.narrator_enabled = $('#at_narrator_enabled').val();
+        this.settings.at_narrator_text_not_inside = $('#at_narrator_text_not_inside').val();
+        this.settings.narrator_voice_gen = $('#narrator_voice').val();
+        // Save the updated settings
+        saveTtsProviderSettings();
+    }
+
+    //#########################//
+    // ST Handle Reload button //
+    //#########################//
+
+    async onRefreshClick() {
+        await this.checkReady(); // Check if the TTS provider is ready
+        await this.loadSettings(this.settings); // Reload the settings
+        // Additional actions as needed
+    }
+
+    //##################//
+    // Preview AT Voice //
+    //##################//
+
+    async previewTtsVoice(voiceName) {
+        try {
+            // Prepare data for POST request
+            const postData = new URLSearchParams();
+            postData.append("voice", `${voiceName}.wav`);
+            // Making the POST request
+            const response = await fetch(`${this.settings.provider_endpoint}/api/previewvoice/`, {
+                method: "POST",
+                headers: {
+                    'Content-Type': 'application/x-www-form-urlencoded'
+                },
+                body: postData,
+            });
+            if (!response.ok) {
+                const errorText = await response.text();
+                console.error(`[previewTtsVoice] Error Response Text:`, errorText);
+                throw new Error(`HTTP ${response.status}: ${errorText}`);
+            }
+            // Assuming the server returns a URL to the .wav file
+            const data = await response.json();
+            if (data.output_file_url) {
+                // Use an audio element to play the .wav file
+                const audioElement = new Audio(data.output_file_url);
+                audioElement.play().catch(e => console.error("Error playing audio:", e));
+            } else {
+                console.warn("[previewTtsVoice] No output file URL received in the response");
+                throw new Error("No output file URL received in the response");
+            }
+
+        } catch (error) {
+            console.error("[previewTtsVoice] Exception caught during preview generation:", error);
+            throw error;
+        }
+    }
+
+    //#####################//
+    //  Populate ST voices //
+    //#####################//
+
+    async getVoice(voiceName, generatePreview = false) {
+        // Ensure this.voices is populated
+        if (this.voices.length === 0) {
+            // Fetch voice objects logic
+        }
+        // Find the object where the name matches voiceName
+        const match = this.voices.find(voice => voice.name === voiceName);
+        if (!match) {
+            // Error handling
+        }
+        // Generate preview URL only if requested
+        if (!match.preview_url && generatePreview) {
+            // Generate preview logic
+        }
+        return match; // Return the found voice object
+    }
+
+    //##########################################//
+    //  Generate TTS Streaming or call Standard //
+    //##########################################//
+
+    async generateTts(inputText, voiceId) {
+        try {
+            if (this.settings.at_generation_method === 'streaming_enabled') {
+                // Construct the streaming URL
+                const streamingUrl = `${this.settings.provider_endpoint}/api/tts-generate-streaming?text=${encodeURIComponent(inputText)}&voice=${encodeURIComponent(voiceId)}.wav&language=${encodeURIComponent(this.settings.language)}&output_file=stream_output.wav`;
+                console.log("Streaming URL:", streamingUrl);
+        
+                // Return the streaming URL directly
+                return streamingUrl; 
+            } else {
+                // For standard method
+                const outputUrl = await this.fetchTtsGeneration(inputText, voiceId);
+                const audioResponse = await fetch(outputUrl);
+                if (!audioResponse.ok) {
+                    throw new Error(`HTTP ${audioResponse.status}: Failed to fetch audio data`);
+                }
+                return audioResponse; // Return the fetch response directly
+            }
+        } catch (error) {
+            console.error("Error in generateTts:", error);
+            throw error;
+        }
+    }
+
+
+    //####################//
+    //  Generate Standard //
+    //####################//
+
+    async fetchTtsGeneration(inputText, voiceId) {
+        // Prepare the request payload
+        const requestBody = new URLSearchParams({
+            'text_input': inputText,
+            'text_filtering': "standard",
+            'character_voice_gen': voiceId + ".wav",
+            'narrator_enabled': this.settings.narrator_enabled,
+            'narrator_voice_gen': this.settings.narrator_voice_gen + ".wav",
+            'text_not_inside': this.settings.at_narrator_text_not_inside,
+            'language': this.settings.language,
+            'output_file_name': "st_output",
+            'output_file_timestamp': "true",
+            'autoplay': "false",
+            'autoplay_volume': "0.8"
+        }).toString();
+
+        try {
+            const response = await doExtrasFetch(
+                `${this.settings.provider_endpoint}/api/tts-generate`,
+                {
+                    method: 'POST',
+                    headers: {
+                        'Content-Type': 'application/x-www-form-urlencoded',
+                        'Cache-Control': 'no-cache',
+                    },
+                    body: requestBody
+                }
+            );
+
+            if (!response.ok) {
+                const errorText = await response.text();
+                console.error(`[fetchTtsGeneration] Error Response Text:`, errorText);
+                // toastr.error(response.statusText, 'TTS Generation Failed');
+                throw new Error(`HTTP ${response.status}: ${errorText}`);
+            }
+            const data = await response.json();
+            const outputUrl = data.output_file_url;
+            return outputUrl; // Return only the output_file_url
+        } catch (error) {
+            console.error("[fetchTtsGeneration] Exception caught:", error);
+            throw error; // Rethrow the error for further handling
+        }
+    }
+}
+
+//#########################//
+//  Update Status Messages //
+//#########################//
+
+function updateStatus(message) {
+    const statusElement = document.getElementById('status_info');
+    if (statusElement) {
+        statusElement.textContent = message;
+        switch (message) {
+            case 'Offline':
+                statusElement.style.color = 'red';
+                break;
+            case 'Ready':
+                statusElement.style.color = 'lightgreen';
+                break;
+            case 'Processing':
+                statusElement.style.color = 'blue';
+                break;
+            case 'Error':
+                statusElement.style.color = 'red';
+                break;
+        }
+    }
+}

templates/STfiles/style.css

@@ -0,0 +1,159 @@
+#tts_media_control {
+    /* order: 100; */
+    /*     width: 40px;
+    height: 40px;
+    margin: 0;
+    padding: 1px; */
+    outline: none;
+    border: none;
+    cursor: pointer;
+    /*     transition: 0.3s;
+    opacity: 0.7; */
+    display: flex;
+    align-items: center;
+    /* justify-content: center; */
+
+}
+
+#ttsExtensionMenuItem {
+    transition: 0.3s;
+    opacity: 0.7;
+}
+
+#ttsExtensionMenuItem:hover {
+    opacity: 1;
+    filter: brightness(1.2);
+}
+
+#tts_media_control:hover {
+    opacity: 1;
+    filter: brightness(1.2);
+}
+
+.voice_preview {
+    margin: 0.25rem 0.5rem;
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    gap: 0.5rem;
+}
+
+.voice_preview .voice_name {
+    text-align: left;
+    flex: 1;
+}
+
+.voice_preview .voice_lang {
+    width: 4rem;
+    text-align: left;
+}
+
+.voice_preview .fa-play {
+    cursor: pointer;
+}
+
+.tts-button {
+    margin: 0;
+    outline: none;
+    border: none;
+    cursor: pointer;
+    transition: 0.3s;
+    opacity: 0.7;
+    align-items: center;
+    justify-content: center;
+
+}
+
+.tts-button:hover {
+    opacity: 1;
+}
+
+.tts_block {
+    display: flex;
+    align-items: baseline;
+    column-gap: 5px;
+    flex-wrap: wrap;
+}
+
+.tts_custom_voices {
+    display: flex;
+    align-items: baseline;
+    gap: 5px;
+}
+
+.novel_tts_hints {
+    font-size: calc(0.9 * var(--mainFontSize));
+    display: flex;
+    flex-direction: column;
+    gap: 5px;
+    margin-bottom: 5px;
+}
+
+.at-settings-row {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    width: 100%;
+}
+
+.at-settings-option {
+    flex: 1;
+    margin: 0 10px;
+}
+
+.at-endpoint-option {
+    flex: 1; 
+    margin: 0 10px;
+    margin-right: 25px;
+    width: 38%;
+}
+
+.at-website-row {
+    display: flex;
+    justify-content: start;
+    align-items: center;
+    margin-top: 10px; 
+    margin-bottom: 10px;
+}
+
+.at-website-option {
+    flex: 1; 
+    margin-right: 10px; 
+    margin-left: 10px; 
+}
+
+.at-settings-separator {
+    margin-top: 10px;
+    margin-bottom: 10px;
+    padding: 18x;
+    font-weight: bold;
+    border-top: 1px solid #e1e1e1; /* Grey line */
+    border-bottom: 1px solid #e1e1e1; /* Grey line */
+    text-align: center;
+}
+
+.at-status-message {
+    flex: 1;
+    margin: 0 10px;
+}
+
+.at-model-endpoint-row {
+    display: flex;
+    justify-content: space-between;
+    align-items: center;
+    width: 100%;
+}
+
+.at-model-option, .endpoint-option {
+    flex: 1;
+    margin: 0 10px;
+    margin-left: 10px; 
+}
+
+.at-endpoint-option {
+    width: 38%;
+}
+
+#at-status_info {
+    color: lightgreen; 
+}

templates/admin.html

@@ -222,6 +222,7 @@
         <li><a href="#using-voice-samples">Using Voice Samples</a></li>
         <li><a href="#text-not-inside">Text Not inside</a></li>
         <li><a href="#low-vram">Low VRAM</a></li>
+        <li><a href="#sillytavern-support">Silly Tavern Support</a></li>
         <li><a href="#finetune">Finetuning (Training the model)</a></li>
         <li><a href="#deepspeed">DeepSpeed</a>
             <ul>
@@ -272,8 +273,8 @@
             here</a><br />Update instructions <a href="https://github.com/erew123/alltalk_tts?#-updating"
             target="_blank" rel="noopener">link here</a><br />Help and issues <a
             href="https://github.com/erew123/alltalk_tts?#-help-with-problems" target="_blank" rel="noopener">link
-            here</a><br />TTS Generator <a
+            here</a><br />TTS Generator <a href="http://127.0.0.1:7851/static/tts_chunk_player/tts_chunk_player.html"
-            href="http://127.0.0.1:7851/static/tts_chunk_player/tts_chunk_player.html" target="_blank" rel="noopener">link
+            target="_blank" rel="noopener">link
             here<br /><br /></a><span style="text-decoration: underline;"><strong>Text generation webUI</strong></span>
         <br />Web interface&nbsp;<a href="http://{{ params.ip_address }}:7860" target="_blank" rel="noopener">link
             here</a> <br />Documentation <a href="https://github.com/oobabooga/text-generation-webui/wiki"
@@ -291,7 +292,8 @@
     <p style="padding-left: 30px;"><a href="#toc">Back to top of page</a></p>
 
     <h2 id="demotesttts">Demo/Test TTS</h2>
-    <p style="padding-left: 30px;">If you are wanting to generate bulk quantites of TTS and have control over them, please see the <a href="#tts-generator">AllTalk TTS Generator</a> below.</p>
+    <p style="padding-left: 30px;">If you are wanting to generate bulk quantities of TTS and have control over them,
+        please see the <a href="#tts-generator">AllTalk TTS Generator</a> below.</p>
     <div id="container">
         <form method="post" action="/tts-demo-request" id="ttsForm">
             <label for="text">Text:</label>
@@ -420,7 +422,8 @@
             let cleanedText = textInput.replace(/ \- | \– /g, ' '); // Replace hyphens
             cleanedText = cleanedText.replace(/%/g, " percent");
             //cleanedText = cleanedText.replace(/([!?.])\1+/g, '$1');
-            cleanedText = cleanedText.replace(/[^a-zA-Z0-9\s\.,;:!?\-\'"À-ÿ\u0400-\u04FF]/g, '');
+            //cleanedText = cleanedText.replace(/[^a-zA-Z0-9\s\.,;:!?\-\'"À-ÿ\u0400-\u04FF]/g, '');
+            cleanedText = cleanedText.replace(/[^a-zA-Z0-9\s\.,;:!?\-\'"À-ÿ\u0400-\u04FF]\$/g, '')
             cleanedText = cleanedText.replace(/\n+/g, ' ');
             cleanedText = cleanedText.replace(/\.\s'/g, ".'"); // Remove space between period and single quote
             //cleanedText = cleanedText.replace(/'/g, ""); // Remove all single quotes
@@ -433,11 +436,11 @@
             if (formData.get('streaming') === 'true') {
                 // For streaming, update the audio player src
                 const searchParams = new URLSearchParams(formData).toString();
-                audioPlayer.src = baseurl + "/tts-demo-request?" + searchParams;
+                audioPlayer.src = baseurl + "/api/tts-generate-streaming?" + searchParams;
                 audioPlayer.load(); // Reload the audio player
             } else {
                 // For non-streaming, send a POST request
-                const response = await fetch('/tts-demo-request', {
+                const response = await fetch('/api/tts-generate-streaming', {
                     method: 'POST',
                     body: formData,
                     cache: "no-store"
@@ -657,6 +660,113 @@
 
     <p style="padding-left: 30px;"><a href="#toc">Back to top of page</a></p>
 
+    <h2 id="sillytavern-support"><strong>SillyTavern Support</strong></h2>
+    <h4>Important note for Text-generation-webui users</h4>
+    <p style="padding-left: 30px;">You <strong><span style="color: #3366ff;">HAVE</span></strong> to disable
+        <strong>Enable TTS</strong> within the Text-generation-webui AllTalk interface,
+        otherwise&nbsp;Text-generation-webui will also generate TTS due to the way it sends out text. You can do this
+        each time you start up&nbsp;Text-generation-webui or set it in the start-up settings at the top of this page.
+    </p>
+    <h4>Quick Tips</h4>
+    <ul>
+        <li>Only change DeepSpeed, Low VRAM or Model one at a time. Wait for it to say Ready before changing something
+            else.</li>
+        <li>You can permanently change the AllTalk startup settings or DeepSpeed, Low VRAM and Model at the top of this
+            page.</li>
+        <li>Different AI models use quotes and asterisks differently, so you may need to change "Text not inside"
+            depending on model.</li>
+        <li>Add new voice samples to the voices folder. You can Finetune a model to make it sound even closer to the
+            original sample.</li>
+        <li>DeepSpeed will improve processing time to TTS to be 2-3x faster.</li>
+        <li>Low VRAM can be very beneficial if you don't have much memory left after loading your LLM.</li>
+    </ul>
+    <h4>TTS Generation Methods in SilllyTavern</h4>
+    <p style="padding-left: 30px;">You have 2 types of audio generation options, Streaming and Standard.</p>
+    <p style="padding-left: 30px; text-align: justify;">The Streaming Audio Generation method is designed for speed and
+        is best suited for situations where you just want quick audio playback. This method, however, is limited to
+        using just one voice per TTS generation request. This means a limitation of the Streaming method is the
+        inability to utilize the AllTalk narrator function, making it a straightforward but less nuanced option.</p>
+    <p style="padding-left: 30px; text-align: justify;">On the other hand, the Standard Audio Generation method provides
+        a richer auditory experience. It's slightly slower than the Streaming method but compensates for this with its
+        ability to split text into multiple voices. This functionality is particularly useful in scenarios where
+        differentiating between character dialogues and narration can enhance the storytelling and delivery. The
+        inclusion of the AllTalk narrator functionality in the Standard method allows for a more layered and immersive
+        experience, making it ideal for content where depth and variety in voice narration add significant value.</p>
+    <p style="padding-left: 30px; text-align: justify;">In summary, the choice between Streaming and Standard methods in
+        AllTalk TTS depends on what you want. Streaming is great for quick and simple audio generation, while Standard
+        is preferable for a more dynamic and engaging audio experience.</p>
+    <ul>
+        <li><strong>AllTalk TTS Generation Method:</strong>
+            <ul>
+                <li>Select between Standard and Streaming Audio Generation methods.</li>
+                <li>This setting impacts the AllTalk narrator functionality.</li>
+            </ul>
+        </li>
+        <li><strong>Language Selection:</strong><br />
+            <ul>
+                <li>Select your preferred TTS generation language from the "Language" dropdown.</li>
+            </ul>
+        </li>
+        <li><strong>Model Switching:</strong>
+            <ul>
+                <li>Switch between different TTS models like API TTS, API Local, XTTSv2 Local, and optionally XTTSv2 FT
+                    if you have a finetuned model available.</li>
+                <li>Fine-tuned model availability (XTTSv2 FT) will only show when a finetuned model is detected by
+                    AllTalk.</li>
+                <li>See TTS Models/Methods for more information (though most people will want to stick with XTTSv2
+                    Local).</li>
+            </ul>
+        </li>
+        <li><strong>DeepSpeed and Low VRAM Options:</strong>
+            <ul>
+                <li>Optimize performance with DeepSpeed and Low VRAM settings.</li>
+                <li>DeepSpeed can offer a 2-3x performance boost on TTS generation. (Requires installation)</li>
+                <li>See the relevant sections in this documentation for details.</li>
+            </ul>
+        </li>
+    </ul>
+    <p style="padding-left: 30px;">Changing model or DeepSpeed or Low VRAM <span
+            style="color: #0000ff;"><strong>each</strong></span> take about 15 seconds so you should only change one at
+        a time and wait for <span style="color: #99cc00;">Ready</span> before changing the next setting. To set these
+        options long term you can apply the settings at the top of this page.</p>
+    <h4>AllTalk Narrator</h4>
+    <p style="padding-left: 30px;">Only available on the Standard Audo Generation method.</p>
+    <ul>
+        <li><strong>Narrator Voice Selection:</strong>
+            <ul>
+                <li>Allows users to choose different narrator voices.</li>
+                <li>Access via the "Narrator Voice" dropdown.</li>
+            </ul>
+        </li>
+        <li><strong>AllTalk Narrator:</strong>
+            <ul>
+                <li>Toggle the AllTalk narrator feature.</li>
+                <li>Access via "AT Narrator" dropdown with Enabled/Disabled options.</li>
+            </ul>
+        </li>
+        <li><strong>Text Outside Asterisks Handling:</strong>
+            <ul>
+                <li>Choose how text outside asterisks is interpreted (as Narrator or Character voice).</li>
+                <li>Managed via the "Text Not Inside * or "" dropdown.</li>
+                <li>Note, only available when the AllTalk Narrator is enabled.</li>
+            </ul>
+        </li>
+    </ul>
+    <h4>Usage Notes:</h4>
+    <ul>
+        <li>On startup of SillyTavern, it will pull your current settings from AllTalk (Current model, DeepSpeed status,
+            Low VRAM status and Finetuned model availability).</li>
+        <li>Enabling the narrator automatically unchecks certain checkboxes related to text handling.</li>
+        <li>Changes in model or settings might trigger multiple requests to the server; patience is advised.</li>
+    </ul>
+    <h4>Troubleshooting:</h4>
+    <ul>
+        <li>If experiencing issues, use the Reload button in SillyTavern's TTS extension to reinitialize the connection
+            to AllTalk and check if AllTalk is started correctly.</li>
+    </ul>
+
+    <p style="padding-left: 30px;"><a href="#toc">Back to top of page</a></p>
+
     <h2 id="finetune"><strong>Finetuning (Training the model)</strong></h2>
     <p style="margin-left:40px; text-align:justify">If you have a voice that the model doesnt quite reproduce correctly,
         or indeed you just want to improve the reproduced voice, then finetuning is a way to train your &quot;XTTSv2
@@ -836,6 +946,8 @@
 
     <h3 id="deepspeed-windows">DeepSpeed Setup - Windows</h3>
     <p style="padding-left: 30px;">➡️DeepSpeed requires an Nvidia Graphics card!⬅️</p>
+    <p style="padding-left: 30px;">The atsetup utility for Windows can install DeepSpeed for you (Stanalone users whom
+        installed via the atsetup utility will already have DeepSpeed installed).</p>
     <p style="padding-left: 30px;">DeepSpeed v11.2 will work on the current default text-generation-webui Python 3.11
         environment! You have 2x options for how to setup DeepSpeed on Windows. A quick way <span
             style="color: #339966;"><strong>Option 1</strong></span>&nbsp;and a long way <span

templates/tts_chunk_player/tts_chunk_player.html

@@ -6,7 +6,6 @@
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
     <link rel="icon" href="./favicon.ico" type="image/x-icon">
     <title>AllTalk TTS Generator</title>
-
     <style>
         body,
         textarea,
@@ -175,27 +174,32 @@
         }
 
         .progress-overlay {
-    position: absolute;
+            position: absolute;
-    top: 10px;
+            top: 10px;
-    right: 10px;
+            right: 10px;
-    background: rgba(255, 255, 255, 0.9);
+            background: rgba(255, 255, 255, 0.9);
-    border-radius: 5px;
+            border-radius: 5px;
-    padding: 10px;
+            padding: 10px;
-    display: flex;
+            display: flex;
-    flex-direction: column; /* Stack items vertically */
+            flex-direction: column;
-    align-items: center; /* Center items horizontally within the container */
+            /* Stack items vertically */
-    justify-content: center; /* Center items vertically within the container */
+            align-items: center;
-    z-index: 10;
+            /* Center items horizontally within the container */
-}
+            justify-content: center;
+            /* Center items vertically within the container */
+            z-index: 10;
+        }
 
-/* Ensure the text is wrapped in a container with a class, e.g., .progress-text */
+        /* Ensure the text is wrapped in a container with a class, e.g., .progress-text */
-.progress-text {
+        .progress-text {
-    text-align: right; /* Center the text horizontally */
+            text-align: right;
-    margin-top: 10px; /* Add space between the spinner and the text */
+            /* Center the text horizontally */
-}
+            margin-top: 10px;
+            /* Add space between the spinner and the text */
+        }
 
 
-#progressIndicator {
+        #progressIndicator {
             /* Adjust this if you want to position the spinning disk differently */
             display: inline-block;
             margin-left: 20px;
@@ -413,6 +417,78 @@
             margin-left: 45px;
             /* Adjust the value as needed */
         }
+
+        /* Pagination Buttons Styling */
+        .pagination-btn {
+            padding: 5px 10px;
+            /* Adjust padding to reduce height */
+            font-size: 0.8em;
+            /* Adjust font size for smaller buttons */
+            line-height: 1;
+            /* Adjust line height to match the smaller size */
+            margin: 2px;
+            /* Optional: adjust spacing between buttons */
+        }
+
+        /* Smaller input field for jump-to-page */
+        .pagination-input {
+            height: 20px;
+            /* Adjust height for smaller input field */
+            padding: 2px 5px;
+            /* Adjust padding for smaller input field */
+            font-size: 0.8em;
+            /* Adjust font size for smaller input field */
+            line-height: 1;
+            /* Adjust line height to match the smaller size */
+            vertical-align: middle;
+            /* Align with buttons if necessary */
+        }
+
+        /* Apply the styles to your pagination controls */
+        #paginationControls button {
+            /* Apply the button styling */
+            height: auto;
+            /* Let padding control the height */
+            min-height: 20px;
+            /* Set a minimum height if needed */
+        }
+
+        #paginationControls input[type="number"] {
+            /* Apply the input styling */
+        }
+
+        /* Smaller input field for jump-to-page */
+        .pagination-input {
+            height: 2px;
+            /* Reduce the height */
+            padding: 0px 0px;
+            /* Reduce the padding to decrease overall height */
+            font-size: 0.8em;
+            /* Optionally reduce the font size */
+            margin-bottom: 13px;
+            margin-top: 2px;
+            border: 0px solid #ccc;
+            /* Adjust border styling if needed */
+            line-height: normal;
+            /* Adjust line height to match the new size */
+            vertical-align: top;
+            /* Align vertically with buttons */
+        }
+
+        /* Apply the styles to your pagination controls */
+        #paginationControls1 button {
+            /* Apply the button styling */
+            height: auto;
+            /* Let padding control the height */
+            min-height: 20px;
+            /* Set a minimum height if needed */
+            margin-top: 15px
+        }
+
+        #paginationControls1 input[type="number"] {
+            /* Apply the input styling */
+            margin-top: 15px
+        }
     </style>
 
 
@@ -469,6 +545,7 @@
             <select id="playMode" name="playMode" class="fixed-size-dropdown">
                 <option value="local" selected>In Browser</option>
                 <option value="remote">On Server</option>
+                <option value="none">No Playback</option>
             </select>
         </div>
 
@@ -524,54 +601,93 @@
     <button onclick="exportToJSON()" style="margin-right: 10px;">Export List as JSON</button>
     <button onclick="importFromJSON()" style="margin-right: 10px;">Import JSON to list</button>
     <button onclick="exportMP3()" style="margin-right: 10px;">Export to Wav</button>
+    <label for="splitEvery">Split every:</label>
+    <select id="splitEvery" name="splitEvery">
+        <option value="100">100</option>
+        <option value="200">200</option>
+        <option value="300">300</option>
+        <option value="400">400</option>
+        <option value="500" selected>500</option>
+        <option value="600">600</option>
+    </select>
+    <div id="paginationControls">
+        <button id="prevPage" class="pagination-btn">Previous</button>
+        <span id="pageIndicator">Page 1 of X</span>
+        <button id="nextPage" class="pagination-btn">Next</button>
+        <input type="number" id="jumpToPage" class="pagination-input" min="1" placeholder="Jump to Page">
+        <button id="jumpButton" class="pagination-btn">Go</button>
+    </div>
     <div id="ttsListDisplay" class="tts-list-display">
         <!-- Dynamically populated TTS details will go here -->
     </div>
+    <div id="paginationControls1">
+        <button id="prevPage1" class="pagination-btn">Previous</button>
+        <span id="pageIndicator1">Page 1 of X</span>
+        <button id="nextPage1" class="pagination-btn">Next</button>
+        <input type="number" id="jumpToPage1" class="pagination-input" min="1" placeholder="Jump to Page">
+        <button id="jumpButton1" class="pagination-btn">Go</button>
+    </div>
 </div>
 </div>
 
 <!-- Howler.js script inclusion -->
 <script src="./howler.min.js"></script>
 <script type="module">
-    // Import Crunker from the CDN
     import Crunker from './crunker.esm.js';
 
     async function exportMP3() {
-    const crunker = new Crunker();
+        const crunker = new Crunker();
-    const fileUrls = ttsList.map(item => item.fileUrl);
+        const fileUrls = ttsList.map(item => item.fileUrl);
-    const progressIndicator = document.getElementById('progressIndicator');
+        const splitEvery = parseInt(document.getElementById('splitEvery').value) || 500;
-    const progressText = document.getElementById('progressText');
+        const progressIndicator = document.getElementById('progressIndicator');
+        const progressText = document.getElementById('progressText');
 
-    // Show progress indicator and update text
+        if (progressIndicator && progressText) {
-    if (progressIndicator && progressText) {
+            progressIndicator.style.display = 'block';
-        progressText.textContent = 'Export';
+            progressText.textContent = 'Starting export...';
-        progressText.style.color = 'black'; // Set the text color to black
-        progressIndicator.style.display = 'block';
-    }
-
-    try {
-        const audioBuffers = await crunker.fetchAudio(...fileUrls);
-        const combined = crunker.concatAudio(audioBuffers);
-        const output = crunker.export(combined, "audio/wav");
-        crunker.download(output.blob, "combined_audio"); // This will download the file as 'combined_audio.mp3'
-    } catch (error) {
-        console.error('Error combining files:', error);
-        if (progressText) {
-            progressText.textContent = 'Error during export!';
         }
-    } finally {
+
-        // Hide progress indicator after completion or error
+        try {
-        if (progressIndicator) {
+            for (let i = 0; i < fileUrls.length; i += splitEvery) {
-            progressIndicator.style.display = 'none';
+                const currentBatch = Math.floor(i / splitEvery) + 1;
+                const totalBatches = Math.ceil(fileUrls.length / splitEvery);
+                if (progressText) {
+                    progressText.textContent = `Processing batch ${currentBatch} of ${totalBatches}`;
+                    progressText.style.color = 'black'; // Set the text color to black
+                }
+
+                const batchUrls = fileUrls.slice(i, Math.min(i + splitEvery, fileUrls.length));
+                const audioBuffers = await crunker.fetchAudio(...batchUrls);
+                const combined = crunker.concatAudio(audioBuffers);
+                const output = crunker.export(combined, "audio/wav");
+                crunker.download(output.blob, `combined_audio_part_${currentBatch}.wav`);
+
+                // Clear audioBuffers array to free up memory
+                audioBuffers.length = 0;
+
+                console.log(`Exported batch ${currentBatch} of ${totalBatches}`);
+            }
+        } catch (error) {
+            console.error('Error combining files:', error);
+            if (progressText) {
+                progressText.textContent = 'Error during export!';
+            }
+        } finally {
+            if (progressIndicator && progressText) {
+                progressIndicator.style.display = 'none';
+                progressText.textContent = ''; // Reset progress text
+            }
         }
     }
-}
 
-    // Attach exportMP3 to the window object to make it globally accessible
     window.exportMP3 = exportMP3;
+
+
+
 </script>
 
 
+
 <script>
 
     /////////////////////////////////////////
@@ -582,7 +698,7 @@
     let audioQueue = [];
     let currentlyPlayingIndex = 0;
     let isPlaying = false;
-    let playModeValue = 'local';
+    let playModeValue = localStorage.getItem('playMode') || 'local';
     let currentSound = null;
     let preloadThreshold = 2; // Number of files to preload before starting playback
     let isStreamInitialized = false;
@@ -591,6 +707,12 @@
     const howlInstances = {};
     let listPlaying = false;
     let listPlayIndex = 0;
+    let currentPage = 1;
+    let itemsPerPage = 100; // Adjust as needed
+    var protocol = window.location.protocol;
+    var host = window.location.hostname;
+    var port = window.location.port;
+    var baseUrl = protocol + "//" + host + (port ? ':' + port : '');
 
     ////////////////////////////////////
     //////// Progress Indicator ////////
@@ -602,7 +724,7 @@
 
         if (progressIndicator && generationProgress) {
             let message = '';
-            console.log("PlayType is:", playType);
+            //console.log("PlayType is:", playType);
             if (playType === 'stream') {
                 // When streaming, display a different message
                 message = '<span class="highlight-count">&nbsp&nbsp&nbsp&nbsp&nbsp&nbspStreaming...</span>';
@@ -650,13 +772,13 @@
             const volume = parseFloat(document.getElementById("volume").value);
             const chunkSize = parseInt(document.getElementById("chunkSize").value);
             const playType = document.getElementById('playType').value; // Play type (chunk or stream)
+            playModeValue = document.getElementById('playMode').value;
 
             let cleanedText = textInput.replace(/ \- | \– /g, ' ');
             cleanedText = cleanedText.replace(/%/g, " percent");
             cleanedText = cleanedText.replace(/\.\s'/g, ".'");
-            cleanedText = cleanedText.replace(/[^a-zA-Z0-9\s\.,;:!?\-\'"À-ÿ\u0400-\u04FF\u0150\u0151\u0170\u0171]/g, '');
+            cleanedText = cleanedText.replace(/[^a-zA-Z0-9\s\.,;:!?\-\'"À-ÿ\u0400-\u04FF\u0150\u0151\u0170\u0171]\$/g, '');
-            //let sentences = cleanedText.match(/("[^"]+"|[^.!?]+[.!?]+)/g);
+            let sentences = cleanedText.split(/(?<=[.!?:])\s+/);
-            let sentences = cleanedText.match(/(?:\d+\.\d+|[^\d.!?])+\b[.!?]+(?=\s|$)/g);
 
             if (!sentences) {
                 console.error("No sentences found in the input text.");
@@ -686,9 +808,14 @@
                     if (stopTTSGeneration) break;
                     showProgress(i + 1, totalChunks, playType);
                     if (playModeValue === 'local') {
+                        // Generate the chunk and play it locally
                         await generateAndCache(chunks[i], language, characterVoice, volume);
-                    } else {
+                    } else if (playModeValue === 'remote') {
+                        // Generate the chunk and play it remotely
                         await generateAndPlayRemote(chunks[i], language, characterVoice, volume);
+                    } else if (playModeValue === 'none') {
+                        // Generate the chunk but do not play it
+                        await generateWithoutPlayback(chunks[i], language, characterVoice);
                     }
                 }
             }
@@ -726,7 +853,7 @@
                 autoplay_volume: volume
             });
 
-            const response = await fetch("http://127.0.0.1:7851/api/tts-generate", {
+            const response = await fetch(baseUrl + "/api/tts-generate", {
                 method: "POST",
                 headers: {
                     "Content-Type": "application/x-www-form-urlencoded",
@@ -736,6 +863,7 @@
 
             const result = await response.json();
             if (result.output_file_url) {
+                //console.log('TTS Generation Result:', result);
                 // If an ID was passed in, we're regenerating an existing item
                 if (id !== null) {
                     let itemIndex = ttsList.findIndex(item => item.id === id);
@@ -749,6 +877,15 @@
                     // No ID was passed in, so we add a new item to the list
                     addToTTSList(result.output_file_url, chunk, characterVoice, language);
                 }
+                const newPage = Math.ceil(ttsList.length / itemsPerPage);
+                //console.log('New Page Calculated:', newPage);
+                if (currentPage !== newPage) {
+                    currentPage = newPage; // Move to the new page where the item was added
+                    //console.log('Updating Current Page to:', currentPage);
+                }
+
+                // Refresh the list display to reflect the new pagination state
+                updateUIList();
 
                 // Update the audio queue and UI
                 const sound = new Howl({
@@ -770,6 +907,56 @@
         }
     }
 
+    async function generateWithoutPlayback(chunk, language, characterVoice, id = null) {
+        // Perform the generation process as usual but do not play the audio
+        try {
+            const data = new URLSearchParams({
+                text_input: chunk.trim(),
+                text_filtering: "standard",
+                character_voice_gen: characterVoice,
+                narrator_enabled: "false",
+                narrator_voice_gen: characterVoice,
+                text_not_inside: "character",
+                language: language,
+                output_file_name: "TTS",
+                output_file_timestamp: "true",
+                autoplay: "false",
+                autoplay_volume: "0.1"
+            });
+            const response = await fetch(baseUrl + "/api/tts-generate", {
+                method: "POST",
+                headers: {
+                    "Content-Type": "application/x-www-form-urlencoded",
+                },
+                body: data,
+            });
+            const result = await response.json();
+            if (result.output_file_url) {
+                // If an ID was passed in, we're regenerating an existing item
+                if (id !== null) {
+                    let itemIndex = ttsList.findIndex(item => item.id === id);
+                    if (itemIndex !== -1) {
+                        ttsList[itemIndex].fileUrl = result.output_file_url;
+                        // Other properties can be updated as needed, e.g., in case the language or voice has changed
+                        ttsList[itemIndex].language = language;
+                        ttsList[itemIndex].characterVoice = characterVoice;
+                    }
+                } else {
+                    // No ID was passed in, so we add a new item to the list
+                    addToTTSList(result.output_file_url, chunk, characterVoice, language);
+                }
+                const newPage = Math.ceil(ttsList.length / itemsPerPage);
+                if (currentPage !== newPage) {
+                    currentPage = newPage; // Move to the new page where the item was added
+                }
+                updateUIList();
+            }
+        } catch (error) {
+            console.error("Error in generateWithoutPlayback:", error);
+        }
+    }
+
+
     function addToTTSList(fileUrl, text, characterVoice, language) {
         try {
             ttsList.push({
@@ -785,6 +972,7 @@
         }
     }
 
+
     async function regenerateTTS(id) {
         // Find the details of the TTS to regenerate
         const ttsDetails = ttsList.find(item => item.id === id);
@@ -805,7 +993,13 @@
         }
         listDisplay.innerHTML = ''; // Clear the current list
 
-        ttsList.forEach(item => {
+        // Determine the range of items to display for pagination
+        const start = (currentPage - 1) * itemsPerPage;
+        const end = start + itemsPerPage;
+        const paginatedItems = ttsList.slice(start, end);
+
+        // Add items to the display for the current page
+        paginatedItems.forEach(item => {
             // Extract just the file name from the URL
             const wavFileName = item.fileUrl.split('/').pop();
 
@@ -815,30 +1009,36 @@
             const entryDiv = document.createElement('div');
             entryDiv.id = `item-${item.id}`; // Assign an ID to the div for highlighting
             entryDiv.classList.add('ttsListItem'); // Add a class for styling
-            entryDiv.id = `item-${item.id}`; // Make sure this is unique and correct
 
             // Update the Play/Stop button's onclick to call a function that handles playing and highlighting
             entryDiv.innerHTML = `
-            <button onclick="regenerateTTS(${item.id})">Regenerate</button>
+        <button onclick="regenerateTTS(${item.id})">Regenerate</button>
-            <button onclick="playSound('${item.fileUrl}', ${item.id})">Play/Stop</button>
+        <button onclick="playSound('${item.fileUrl}', ${item.id})">Play/Stop</button>
-            <span class="label">ID:</span> <span class="value">${item.id}</span>
+        <span class="label">ID:</span> <span class="value">${item.id}</span>
-            <span class="label">Voice:</span> <span class="value">${item.characterVoice}</span>
+        <span class="label">Voice:</span> <span class="value">${item.characterVoice}</span>
-            <span class="label">Language:</span> <span class="value">${item.language}</span>
+        <span class="label">Language:</span> <span class="value">${item.language}</span>
-            <span class="label">Wav:</span> <span class="value">${wavFileName}</span>
+        <span class="label">Wav:</span> <span class="value">${wavFileName}</span>
-            <button id="edit-btn-${item.id}" class="edit-btn" onclick="editText(${item.id})">Edit</button>
+        <button id="edit-btn-${item.id}" class="edit-btn" onclick="editText(${item.id})">Edit</button>
-            <span class="item-field text-preview value" title="${item.text}" data-fulltext="${item.text}">${displayText}</span>
+        <span class="item-field text-preview value" title="${item.text}" data-fulltext="${item.text}">${displayText}</span>
         `;
             listDisplay.appendChild(entryDiv);
         });
+
+        // Update pagination controls
+        const lastPage = Math.ceil(ttsList.length / itemsPerPage);
+        document.getElementById('pageIndicator').innerText = `Page ${currentPage} of ${lastPage}`;
+        document.getElementById('pageIndicator1').innerText = `Page ${currentPage} of ${lastPage}`;
+        document.getElementById('prevPage').disabled = (currentPage === 1);
+        document.getElementById('nextPage').disabled = (currentPage === lastPage);
     }
 
+
     async function generateAndPlayRemote(chunk, language, characterVoice, volume) {
         try {
             if (stopTTSGeneration) {
                 console.log("TTS generation stopped.");
                 return; // Early return if stop flag is set
             }
-            console.log("generateAndPlayRemote:", chunk);
             const data = new URLSearchParams({
                 text_input: chunk.trim(),
                 text_filtering: "standard",
@@ -853,7 +1053,7 @@
                 autoplay_volume: volume,
             });
 
-            const response = await fetch("http://127.0.0.1:7851/api/tts-generate", {
+            const response = await fetch(baseUrl + "/api/tts-generate", {
                 method: "POST",
                 headers: {
                     "Content-Type": "application/x-www-form-urlencoded",
@@ -883,8 +1083,9 @@
             });
 
             // Reinitialize currentSound every time
+            var srcUrl = baseUrl + "/tts-demo-request?" + queryParams.toString();
             currentSound = new Howl({
-                src: [`http://127.0.0.1:7851/tts-demo-request?${queryParams.toString()}`],
+                src: [srcUrl],
                 volume: volume,
                 html5: true // Force HTML5 Audio to enable streaming
             });
@@ -914,13 +1115,10 @@
                 src: [fileUrl],
                 volume: parseFloat(document.getElementById("volume").value),
                 onplay: function () {
-                    console.log('Playback started for', fileUrl);
                 },
                 onend: function () {
-                    console.log('Playback finished for', fileUrl);
                 },
                 onpause: function () {
-                    console.log('Playback paused for', fileUrl);
                 },
                 onloaderror: function (e) {
                     console.error('Load error for', fileUrl, ':', e);
@@ -946,7 +1144,7 @@
             const formData = new FormData();
             formData.append("voice", characterVoice);
 
-            const response = await fetch("http://127.0.0.1:7851/api/previewvoice/", {
+            const response = await fetch(baseUrl + "/api/previewvoice/", {
                 method: "POST",
                 body: formData,
             });
@@ -1055,15 +1253,26 @@
     function playNextLocalChunk() {
         if (audioQueue.length > 0 && currentlyPlayingIndex < audioQueue.length) {
             isPlaying = true;
-            audioQueue[currentlyPlayingIndex++].play();
+            let currentSound = audioQueue[currentlyPlayingIndex];
+            currentSound.play();
+
+            // Once a sound finishes playing, unload it
+            currentSound.on('end', () => {
+                currentSound.unload();
+            });
+
+            currentlyPlayingIndex++;
         } else {
             isPlaying = false;
         }
     }
 
+
     function stopPlayback() {
         Howler.stop();
         audioQueue = [];
+        // Unload each sound in the queue
+        audioQueue.forEach(sound => sound.unload());
         currentlyPlayingIndex = 0;
         isPlaying = false;
     }
@@ -1103,7 +1312,6 @@
         const startFromIdElement = document.getElementById('startFromId');
         if (startFromIdElement) {
             startFromIdElement.setAttribute('value', '1');
-            console.log('Start From ID set to 1');
         }
         // Other initializations...
     });
@@ -1123,6 +1331,7 @@
             // and highlight the corresponding item
             playListFromIndex(startIndex);
             highlightPlaying(startIndex + 1); // Assuming the list items are 1-indexed
+            updateCurrentPage(startIndex + 1); // Update the current page based on the playing item
         } else {
             // If list is set to pause, pause the current item
             // and remove highlighting
@@ -1155,6 +1364,26 @@
         if (currentItem) {
             currentItem.classList.add('highlight');
         }
+        updateCurrentPage(id);
+    }
+
+
+    function updateCurrentPage(itemIndex) {
+        // Calculate the page number based on the item index
+        // Note: Ensure that the itemIndex is 1-based; if it's 0-based, add 1.
+        const newPage = Math.ceil(itemIndex / itemsPerPage);
+
+        // Update the current page and UI if the new page is different from the current page
+        if (currentPage !== newPage) {
+            currentPage = newPage; // Set the new current page
+            updateUIList(); // Refresh the list display to show the correct page
+        }
+
+        // Optionally, update the 'Jump to Page' input to reflect the current page
+        const jumpToPageInput = document.getElementById('jumpToPage');
+        if (jumpToPageInput) {
+            jumpToPageInput.value = currentPage;
+        }
     }
 
 
@@ -1192,6 +1421,7 @@
             console.log('Index is out of bounds, stopping playback.');
             // Clear any highlights if out of bounds
             highlightPlaying(null);
+            updateUIList();
         }
     }
 
@@ -1213,6 +1443,14 @@
         if (startFromIdElement) {
             startFromIdElement.value = '1';
         }
+        const pageIndicator = document.getElementById('pageIndicator');
+        if (pageIndicator) {
+            pageIndicator.textContent = 'Page 1 of 1';
+        }
+        const pageIndicator1 = document.getElementById('pageIndicator1');
+        if (pageIndicator1) {
+            pageIndicator1.textContent = 'Page 1 of 1';
+        }
     }
 
     function editText(id) {
@@ -1300,7 +1538,7 @@
         input.type = 'file';
         input.accept = '.json';
 
-        input.onchange = (e) => {
+        input.onchange = async (e) => {
             const file = e.target.files[0];
             if (file) {
                 const reader = new FileReader();
@@ -1308,13 +1546,11 @@
                 reader.onload = (e) => {
                     try {
                         const jsonData = JSON.parse(e.target.result);
-                        console.log('JSON data imported:', jsonData);
 
-                        // Update the ttsList with the imported data
                         ttsList = jsonData;
-
+                        currentPage = 1; // Reset to the first page
-                        // Refresh the on-screen list
+                        updateUIList();
-                        updateUIList(); // This function updates the UI with the contents of ttsList
+                        updatePaginationControls(); // Update pagination controls
                     } catch (error) {
                         console.error('Error parsing JSON:', error);
                     }
@@ -1325,6 +1561,32 @@
         input.click();
     }
 
+    function updatePaginationControls() {
+        const lastPage = Math.ceil(ttsList.length / itemsPerPage);
+        const pageIndicator = document.getElementById('pageIndicator');
+        if (pageIndicator) {
+            pageIndicator.textContent = `Page ${currentPage} of ${lastPage}`;
+        }
+
+        const prevPageButton = document.getElementById('prevPage');
+        if (prevPageButton) {
+            prevPageButton.disabled = (currentPage === 1);
+        }
+
+        const nextPageButton = document.getElementById('nextPage');
+        if (nextPageButton) {
+            nextPageButton.disabled = (currentPage === lastPage);
+        }
+
+        // Similar updates for any additional pagination controls if you have them
+        // ...
+    }
+
+
+
+
+
+
     //////////////////////////////
     //////// Other Things ////////
     //////////////////////////////
@@ -1374,7 +1636,7 @@
 
     async function fetchVoices() {
         try {
-            const response = await fetch("http://127.0.0.1:7851/api/voices");
+            const response = await fetch(baseUrl + "/api/voices");
             const result = await response.json();
             const characterVoiceSelect = document.getElementById("character_voice_gen");
 
@@ -1425,6 +1687,70 @@
     //////// General Dcoument Listeners ////////
     ////////////////////////////////////////////
 
+    // Event listeners for pagination controls
+    document.getElementById('prevPage').addEventListener('click', () => {
+        if (currentPage > 1) {
+            currentPage--;
+            updateUIList();
+        }
+    });
+
+    document.getElementById('nextPage').addEventListener('click', () => {
+        const lastPage = Math.ceil(ttsList.length / itemsPerPage);
+        if (currentPage < lastPage) {
+            currentPage++;
+            updateUIList();
+        }
+    });
+
+    // Initialize the list on page load
+    document.addEventListener('DOMContentLoaded', updateUIList);
+
+
+    // For the 'Previous' button at the bottom
+    document.getElementById('prevPage1').addEventListener('click', () => {
+        if (currentPage > 1) {
+            currentPage--;
+            updateUIList();
+        }
+    });
+
+    // For the 'Next' button at the bottom
+    document.getElementById('nextPage1').addEventListener('click', () => {
+        let lastPage = Math.ceil(ttsList.length / itemsPerPage);
+        if (currentPage < lastPage) {
+            currentPage++;
+            updateUIList();
+        }
+    });
+
+    function handleJumpButtonClick(event) {
+        // Determine which set of controls to use based on the button that was clicked
+        const suffix = event.target.id === 'jumpButton' ? '' : '1';
+        const jumpToInput = document.getElementById(`jumpToPage${suffix}`);
+        const jumpToValue = jumpToInput.value.trim(); // Get the trimmed value
+        const jumpTo = parseInt(jumpToValue, 10); // Parse the value as an integer
+
+        if (!isNaN(jumpTo)) {
+            let lastPage = Math.ceil(ttsList.length / itemsPerPage);
+
+            if (jumpTo >= 1 && jumpTo <= lastPage) {
+                currentPage = jumpTo;
+                updateUIList();
+            } else {
+                alert(`Please enter a valid page number between 1 and ${lastPage}`);
+            }
+        } else {
+            alert("Please enter a number to jump to.");
+        }
+    }
+
+    // Set up the event listener for both jump buttons
+    document.getElementById('jumpButton').addEventListener('click', handleJumpButtonClick);
+    document.getElementById('jumpButton1').addEventListener('click', handleJumpButtonClick);
+
+
+
     // Event listener for changing play type
     document.getElementById('playType').addEventListener('change', function () {
         isStreamingMode = this.value === 'stream';
@@ -1546,11 +1872,13 @@
             adjustPlaybackAndChunkSize(savedPlayType); // Adjust selectability on page load
         }
 
-        // Initialize playback based on preference
+        document.addEventListener('DOMContentLoaded', function () {
-        const savedPlayMode = localStorage.getItem('playMode');
+            const savedPlayMode = localStorage.getItem('playMode');
-        if (savedPlayMode) {
+            if (savedPlayMode) {
-            document.getElementById('playMode').value = savedPlayMode;
+                document.getElementById('playMode').value = savedPlayMode;
-        }
+            }
+            playModeValue = savedPlayMode || 'local'; // Default to 'local' if nothing is saved
+        });
 
         // Initialize chunk size based on preference
         const savedChunkSize = localStorage.getItem('chunkSize');
@@ -1660,9 +1988,11 @@
     window.onload = function () {
         setupPage();
         hideProgress(); // Ensure the progress indicator is hidden on page load
+        if (window.location.protocol !== 'http:' && window.location.protocol !== 'https:') {
+                alert('AllTalk TTS Generator is not designed to be run from your disk folder. Please run it from the correct URL e.g. http://127.0.0.1:7851/static/tts_chunk_player/tts_chunk_player.html');
+            }
     };
 
-
 </script>
 </body>
 

tts_server.py

@@ -57,6 +57,10 @@ params = load_config(configfile_path)
 # check someone hasnt enabled lowvram on a system thats not cuda enabled
 params["low_vram"] = "false" if not torch.cuda.is_available() else params["low_vram"]
 
+# Load values for temperature and repetition_penalty
+temperature = params["local_temperature"]
+repetition_penalty = params["local_repetition_penalty"]
+
 # Define the path to the JSON file
 config_file_path = this_dir / "modeldownload.json"
 
@@ -81,6 +85,17 @@ else:
         f"[{params['branding']}Startup] \033[91mWarning\033[0m modeldownload.config is missing so please re-download it and save it in the alltalk_tts main folder."
     )
 
+##################################################
+#### Check to see if a finetuned model exists ####
+##################################################
+# Set the path to the directory
+trained_model_directory = this_dir / "models" / "trainedmodel"
+# Check if the directory "trainedmodel" exists
+finetuned_model = trained_model_directory.exists()
+# If the directory exists, check for the existence of the required files
+if finetuned_model:
+    required_files = ["model.pth", "config.json", "vocab.json"]
+    finetuned_model = all((trained_model_directory / file).exists() for file in required_files)
 
 ########################
 #### STARTUP CHECKS ####
@@ -98,19 +113,17 @@ except ModuleNotFoundError:
     raise
 
 # DEEPSPEED Import - Check for DeepSpeed and import it if it exists
+deepspeed_available = False
 try:
     import deepspeed
-
+    deepspeed_available = True
-    deepspeed_installed = True
-    print(f"[{params['branding']}Startup] DeepSpeed \033[93mDetected\033[0m")
-    print(
-        f"[{params['branding']}Startup] Activate DeepSpeed in {params['branding']} settings"
-    )
 except ImportError:
-    deepspeed_installed = False
+    pass
-    print(
+if deepspeed_available:
-        f"[{params['branding']}Startup] DeepSpeed \033[93mNot Detected\033[0m. See https://github.com/microsoft/DeepSpeed"
+    print(f"[{params['branding']}Startup] DeepSpeed \033[93mDetected\033[0m")
-    )
+    print(f"[{params['branding']}Startup] Activate DeepSpeed in {params['branding']}settings")
+else:
+    print(f"[{params['branding']}Startup] DeepSpeed \033[93mNot Detected\033[0m. See https://github.com/microsoft/DeepSpeed")
 
 
 @asynccontextmanager
@@ -464,16 +477,16 @@ async def deepspeed(request: Request, new_deepspeed_value: bool):
 ########################
 
 # TTS VOICE GENERATION METHODS (called from voice_preview and output_modifer)
-async def generate_audio(text, voice, language, output_file, streaming=False):
+async def generate_audio(text, voice, language, temperature, repetition_penalty, output_file, streaming=False):
     # Get the async generator from the internal function
-    response = generate_audio_internal(text, voice, language, output_file, streaming)
+    response = generate_audio_internal(text, voice, language, temperature, repetition_penalty, output_file, streaming)
     # If streaming, then return the generator as-is, otherwise just exhaust it and return
     if streaming:
         return response
     async for _ in response:
         pass
     
-async def generate_audio_internal(text, voice, language, output_file, streaming):
+async def generate_audio_internal(text, voice, language, temperature, repetition_penalty, output_file, streaming):
     global model
     if params["low_vram"] and device == "cpu":
         await switch_device()
@@ -495,9 +508,9 @@ async def generate_audio_internal(text, voice, language, output_file, streaming)
             "language": language,
             "gpt_cond_latent": gpt_cond_latent,
             "speaker_embedding": speaker_embedding,
-            "temperature": float(params["local_temperature"]),
+            "temperature": float(temperature),
             "length_penalty": float(model.config.length_penalty),
-            "repetition_penalty": float(params["local_repetition_penalty"]),
+            "repetition_penalty": float(repetition_penalty),
             "top_k": int(model.config.top_k),
             "top_p": float(model.config.top_p),
             "enable_text_splitting": True
@@ -551,9 +564,9 @@ async def generate_audio_internal(text, voice, language, output_file, streaming)
             file_path=output_file,
             speaker_wav=[f"{this_dir}/voices/{voice}"],
             language=language,
-            temperature=float(params["local_temperature"]),
+            temperature=temperature,
             length_penalty=model.config.length_penalty,
-            repetition_penalty=float(params["local_repetition_penalty"]),
+            repetition_penalty=repetition_penalty,
             top_k=model.config.top_k,
             top_p=model.config.top_p,
         )
@@ -593,10 +606,12 @@ async def generate(request: Request):
         text = data["text"]
         voice = data["voice"]
         language = data["language"]
+        temperature = data["temperature"]
+        repetition_penalty = data["repetition_penalty"]
         output_file = data["output_file"]
         streaming = False
         # Generation logic
-        response = await generate_audio(text, voice, language, output_file, streaming)
+        response = await generate_audio(text, voice, language, temperature, repetition_penalty, output_file, streaming)
         if streaming:
             return StreamingResponse(response, media_type="audio/wav")
         return JSONResponse(
@@ -713,7 +728,7 @@ async def update_settings(
 async def tts_demo_request_streaming(text: str, voice: str, language: str, output_file: str):
     try:
         output_file_path = this_dir / "outputs" / output_file
-        stream = await generate_audio(text, voice, language, output_file_path, streaming=True)
+        stream = await generate_audio(text, voice, language, temperature, repetition_penalty, output_file_path, streaming=True)
         return StreamingResponse(stream, media_type="audio/wav")
     except Exception as e:
         print(f"An error occurred: {e}")
@@ -723,12 +738,17 @@ async def tts_demo_request_streaming(text: str, voice: str, language: str, outpu
 async def tts_demo_request(request: Request, text: str = Form(...), voice: str = Form(...), language: str = Form(...), output_file: str = Form(...)):
     try:
         output_file_path = this_dir / "outputs" / output_file
-        await generate_audio(text, voice, language, output_file_path, streaming=False)
+        await generate_audio(text, voice, language, temperature, repetition_penalty, output_file_path, streaming=False)
         return JSONResponse(content={"output_file_path": str(output_file)}, status_code=200)
     except Exception as e:
         print(f"An error occurred: {e}")
         return JSONResponse(content={"error": "An error occurred"}, status_code=500)
 
+
+#####################
+#### Audio feeds ####
+#####################
+
 # Gives web access to the output files
 @app.get("/audio/{filename}")
 async def get_audio(filename: str):
@@ -780,7 +800,7 @@ async def preview_voice(request: Request, voice: str = Form(...)):
 
         # Generate the audio
         output_file_path = this_dir / "outputs" / f"{output_file_name}.wav"
-        await generate_audio(text, voice, language, output_file_path, streaming=False)
+        await generate_audio(text, voice, language, temperature, repetition_penalty, output_file_path, streaming=False)
 
         # Generate the URL
         output_file_url = f'http://{params["ip_address"]}:{params["port_number"]}/audio/{output_file_name}.wav'
@@ -807,6 +827,35 @@ import uuid
 import numpy as np
 import soundfile as sf
 import sys
+import hashlib
+
+##############################
+#### Streaming Generation ####
+##############################
+
+@app.get("/api/tts-generate-streaming", response_class=StreamingResponse)
+async def tts_generate_streaming(text: str, voice: str, language: str, output_file: str):
+    try:
+        output_file_path = this_dir / "outputs" / output_file
+        stream = await generate_audio(text, voice, language, temperature, repetition_penalty, output_file_path, streaming=True)
+        return StreamingResponse(stream, media_type="audio/wav")
+    except Exception as e:
+        print(f"An error occurred: {e}")
+        return JSONResponse(content={"error": "An error occurred"}, status_code=500)
+
+@app.post("/api/tts-generate-streaming", response_class=JSONResponse)
+async def tts_generate_streaming(request: Request, text: str = Form(...), voice: str = Form(...), language: str = Form(...), output_file: str = Form(...)):
+    try:
+        output_file_path = this_dir / "outputs" / output_file
+        await generate_audio(text, voice, language, temperature, repetition_penalty, output_file_path, streaming=False)
+        return JSONResponse(content={"output_file_path": str(output_file)}, status_code=200)
+    except Exception as e:
+        print(f"An error occurred: {e}")
+        return JSONResponse(content={"error": "An error occurred"}, status_code=500)
+
+##############################
+#### Standard Generation ####
+##############################
 
 # Check for PortAudio library on Linux
 try:
@@ -834,7 +883,7 @@ class Request(BaseModel):
     pass
 
 class JSONInput(BaseModel):
-    text_input: str = Field(..., max_length=1000, description="text_input needs to be 1000 characters or less.")
+    text_input: str = Field(..., max_length=2000, description="text_input needs to be 2000 characters or less.")
     text_filtering: str = Field(..., pattern="^(none|standard|html)$", description="text_filtering needs to be 'none', 'standard' or 'html'.")
     character_voice_gen: str = Field(..., pattern="^.*\.wav$", description="character_voice_gen needs to be the name of a wav file e.g. mysample.wav.")
     narrator_enabled: bool = Field(..., description="narrator_enabled needs to be true or false.")
@@ -936,8 +985,8 @@ def combine(output_file_timestamp, output_file_name, audio_files):
         output_cache_url = f'http://{params["ip_address"]}:{params["port_number"]}/audiocache/{output_file_name}_{timestamp}_combined.wav'
     else:
         output_file_path = os.path.join(this_dir / "outputs" / f'{output_file_name}_combined.wav')
-        output_file_url = f'http://{params["ip_address"]}:{params["port_number"]}/audio/{output_file_name}.wav'
+        output_file_url = f'http://{params["ip_address"]}:{params["port_number"]}/audio/{output_file_name}_combined.wav'
-        output_cache_url = f'http://{params["ip_address"]}:{params["port_number"]}/audiocache/{output_file_name}.wav'
+        output_cache_url = f'http://{params["ip_address"]}:{params["port_number"]}/audiocache/{output_file_name}_combined.wav'
     try:
         sf.write(output_file_path, audio, samplerate=sample_rate)
         # Clean up unnecessary files
@@ -1006,12 +1055,12 @@ async def tts_generate(
                 # Replace multiple exclamation marks, question marks, or other punctuation with a single instance
                 cleaned_part = re.sub(r'([!?.])\1+', r'\1', part)
                 # Further clean to remove any other unwanted characters
-                cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\$]', '', cleaned_part)
+                cleaned_part = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171]\$', '', cleaned_part)
                 # Remove all newline characters (single or multiple)
                 cleaned_part = re.sub(r'\n+', ' ', cleaned_part)
                 output_file = this_dir / "outputs" / f"{output_file_name}_{uuid.uuid4()}_{int(time.time())}.wav"
                 output_file_str = output_file.as_posix()
-                response = await generate_audio(cleaned_part, voice_to_use, language, output_file_str, streaming)
+                response = await generate_audio(cleaned_part, voice_to_use, language,temperature, repetition_penalty, output_file_str, streaming)
                 audio_path = output_file_str
                 audio_files_all_paragraphs.append(audio_path)
             # Combine audio files across paragraphs
@@ -1019,29 +1068,36 @@ async def tts_generate(
         else:
             if output_file_timestamp:
                 timestamp = int(time.time())
-                output_file_path = this_dir / "outputs" / f"{output_file_name}_{timestamp}.wav"
+                # Generate a standard UUID
-                output_file_url = f'http://{params["ip_address"]}:{params["port_number"]}/audio/{output_file_name}_{timestamp}.wav'
+                original_uuid = uuid.uuid4()
-                output_cache_url = f'http://{params["ip_address"]}:{params["port_number"]}/audiocache/{output_file_name}_{timestamp}.wav'
+                # Hash the UUID using SHA-256
+                hash_object = hashlib.sha256(str(original_uuid).encode())
+                hashed_uuid = hash_object.hexdigest()
+                # Truncate to the desired length, for example, 16 characters
+                short_uuid = hashed_uuid[:5]
+                output_file_path = this_dir / "outputs" / f"{output_file_name}_{timestamp}{short_uuid}.wav"
+                output_file_url = f'http://{params["ip_address"]}:{params["port_number"]}/audio/{output_file_name}_{timestamp}{short_uuid}.wav'
+                output_cache_url = f'http://{params["ip_address"]}:{params["port_number"]}/audiocache/{output_file_name}_{timestamp}{short_uuid}.wav'
             else:
                 output_file_path = this_dir / "outputs" / f"{output_file_name}.wav"
                 output_file_url = f'http://{params["ip_address"]}:{params["port_number"]}/audio/{output_file_name}.wav'
-                output_cache_url = f'http://{params["ip_address"]}:{params["port_number"]}/audiocache/{output_file_name}_{timestamp}.wav'
+                output_cache_url = f'http://{params["ip_address"]}:{params["port_number"]}/audiocache/{output_file_name}.wav'
             if text_filtering == "html":
                 cleaned_string = html.unescape(standard_filtering(text_input))
                 cleaned_string = re.sub(r'([!?.])\1+', r'\1', text_input)
                 # Further clean to remove any other unwanted characters
-                cleaned_string = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\$]', '', cleaned_string)
+                cleaned_string = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171]\$', '', cleaned_string)
                 # Remove all newline characters (single or multiple)
                 cleaned_string = re.sub(r'\n+', ' ', cleaned_string)
             elif text_filtering == "standard":
                 cleaned_string = re.sub(r'([!?.])\1+', r'\1', text_input)
                 # Further clean to remove any other unwanted characters
-                cleaned_string = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171\$]', '', cleaned_string)
+                cleaned_string = re.sub(r'[^a-zA-Z0-9\s\.,;:!?\-\'"\u0400-\u04FFÀ-ÿ\u0150\u0151\u0170\u0171]\$', '', cleaned_string)
                 # Remove all newline characters (single or multiple)
                 cleaned_string = re.sub(r'\n+', ' ', cleaned_string)
             else:
                 cleaned_string = text_input
-            response = await generate_audio(cleaned_string, character_voice_gen, language, output_file_path, streaming)
+            response = await generate_audio(cleaned_string, character_voice_gen, language, temperature, repetition_penalty, output_file_path, streaming)
         if sounddevice_installed == False or streaming == True:
             autoplay = False
         if autoplay:
@@ -1053,6 +1109,38 @@ async def tts_generate(
         return JSONResponse(content={"status": "generate-failure", "error": "An error occurred"}, status_code=500)
 
 
+##########################
+#### Current Settings ####
+##########################
+# Define the available models
+models_available = [
+    {"name": "Coqui", "model_name": "API TTS"},
+    {"name": "Coqui", "model_name": "API Local"},
+    {"name": "Coqui", "model_name": "XTTSv2 Local"}
+]
+
+@app.get('/api/currentsettings')
+def get_current_settings():
+    # Determine the current model loaded
+    if params["tts_method_api_tts"]:
+        current_model_loaded = "API TTS"
+    elif params["tts_method_api_local"]:
+        current_model_loaded = "API Local"
+    elif params["tts_method_xtts_local"]:
+        current_model_loaded = "XTTSv2 Local"
+    else:
+        current_model_loaded = None  # or a default value if no method is active
+
+    settings = {
+        "models_available": models_available,
+        "current_model_loaded": current_model_loaded,
+        "deepspeed_available": deepspeed_available,
+        "deepspeed_status": params["deepspeed_activate"],
+        "low_vram_status": params["low_vram"],
+        "finetuned_model": finetuned_model
+    }
+    return settings  # Automatically converted to JSON by Fas
+
 #############################
 #### Word Add-in Sharing ####
 #############################