From 102424669bea46588712e98fd8cf611d9c287afb Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sat, 13 Jan 2024 11:31:22 +0000
Subject: [PATCH 01/44] Update tts_server.py - URL file path no timestamp

---
 tts_server.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tts_server.py b/tts_server.py
index 55adf7e..e41e1ee 100644
--- a/tts_server.py
+++ b/tts_server.py
@@ -936,8 +936,8 @@ 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_cache_url = f'http://{params["ip_address"]}:{params["port_number"]}/audiocache/{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}_combined.wav'
     try:
         sf.write(output_file_path, audio, samplerate=sample_rate)
         # Clean up unnecessary files

From e43c58a56e3667d49a6554c17399d90de032a77d Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sat, 13 Jan 2024 13:09:20 +0000
Subject: [PATCH 02/44] Delete atstart.sh

---
 atstart.sh | 381 -----------------------------------------------------
 1 file changed, 381 deletions(-)
 delete mode 100644 atstart.sh

diff --git a/atstart.sh b/atstart.sh
deleted file mode 100644
index 6785cf4..0000000
--- a/atstart.sh
+++ /dev/null
@@ -1,381 +0,0 @@
-#!/bin/bash
-
-# ANSI color codes
-RED='\033[1;34m'
-GREEN='\033[1;32m'
-YELLOW='\033[1;33m'
-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 "Welcome to the AllTalk Setup Utility"
-        echo
-        echo "Please select an option:"
-        echo
-        echo "    1) I am using AllTalk as part of Text-generation-webui"
-        echo "    2) I am using AllTalk as a Standalone Application"
-        echo
-        echo "    9) Exit/Quit"
-        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 "You have selected Text-generation-webui."
-        echo
-        echo -e "Please ensure you have started your Text-generation-webui Python environment."
-        echo -e "If you have NOT done this, please run ${GREEN}/cmd_linux.sh${NC} in the ${GREEN}text-generation-webui${NC} folder and then re-run this script."
-        echo
-        echo "    1) Install the requirements for a Nvidia machine."
-        echo "    2) Install the requirements for an AMD or MAC machine."
-        echo "    3) Install the Finetuning requirements."
-        echo "    4) Install DeepSpeed."
-        echo "    5) Uninstall DeepSpeed."
-        echo "    6) Generate a diagnostics file."
-        echo
-        echo "    9) Back to Main Menu"
-        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) break ;;
-            *) 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 "Finetune requirements installed successfully."
-    read -p "Press any key to continue. " -n 1
-    echo
-}
-
-# Function to install DeepSpeed
-install_deepspeed() {
-    clear
-    echo -e "${YELLOW}DeepSpeed Installation Prerequisites:${NC}"
-    echo
-    echo -e "     1. NVIDIA CUDA Toolkit must be installed from ${GREEN}https://developer.nvidia.com/cuda-toolkit-archive${NC} or your ${GREEN}Linux package manager${NC}."
-    echo -e "     2. ${GREEN}libaio-dev${NC} must be installed."
-    echo -e "     3. The environment variable ${GREEN}CUDA_HOME${NC} must be set (e.g. export CUDA_HOME=/usr/local/cuda)."
-
-    echo -e "\n${RED}Please confirm that you have completed these steps before continuing with the DeepSpeed installation.${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 "You have selected Standalone Application Setup."
-        echo
-        echo "    1) Install AllTalk's custom Python environment (Setup AllTalk as a standalone Application)"
-        echo "    2) Delete AllTalk's custom Python environment"
-        echo "    3) Install the Finetuning requirements"
-        echo "    4) Install DeepSpeed."
-        echo "    5) Generate a diagnostics file"
-        echo
-        echo "    9) Back to Main Menu"
-        echo
-        read -p "Enter your choice: " standalone_option
-
-        case $standalone_option in
-            1) install_custom_standalone ;;
-            2) delete_custom_standalone ;;
-            3) install_finetune_standalone ;;
-            4) install_deepspeed ;;
-            5) generate_diagnostics_standalone ;;
-            9) break ;;
-            *) echo "Invalid option"; sleep 2 ;;
-        esac
-    done
-}
-
-install_custom_standalone() {
-    cd "$(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 "${INSTALL_ENV_DIR}"
-
-    echo
-    echo "Choose the type of requirements to install:"
-    echo
-    echo "     1. Nvidia graphics card machines"
-    echo "     2. Other machines (mac, amd, etc)"
-    echo
-    read -p "Enter your choice (1 or 2): " user_choice
-
-    if [ "$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 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
-    else
-        pip install -r requirements_other.txt
-    fi
-
-    # 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
-    echo
-    echo
-    echo "start_alltalk.sh has been created."
-    echo -e "You can now start AllTalk with ${YELLOW}./start_alltalk.sh${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 "Finetune requirements installed successfully."
-    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

From b8292da92f4d809ccd11a4732a7d93db812c2829 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sat, 13 Jan 2024 21:47:49 +0000
Subject: [PATCH 03/44] Update README.md

---
 README.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index aa312d7..b5dd62a 100644
--- a/README.md
+++ b/README.md
@@ -765,6 +765,7 @@ Generate a preview of a specified voice with hardcoded settings.
    JSON return `{"status": "lowvram-success"}`
 
 ### 🟠 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>
 
@@ -872,7 +873,7 @@ 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"}`
 
-### 🟠 Example command lines (Streaming Generation)
+### 🟠 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>

From 62d1cc05d32b50d324a93960c8258b95ade8bc8c Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sat, 13 Jan 2024 22:43:41 +0000
Subject: [PATCH 04/44] Added cutlet and unidic-lite for Japanese

---
 atsetup.bat             | 2 ++
 requirements_nvidia.txt | 2 ++
 requirements_other.txt  | 2 ++
 3 files changed, 6 insertions(+)

diff --git a/atsetup.bat b/atsetup.bat
index b996754..21e4ce9 100644
--- a/atsetup.bat
+++ b/atsetup.bat
@@ -351,6 +351,8 @@ if "%UserChoice%" == "1" (
     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...
diff --git a/requirements_nvidia.txt b/requirements_nvidia.txt
index b8d22e9..51d6d2a 100644
--- a/requirements_nvidia.txt
+++ b/requirements_nvidia.txt
@@ -13,3 +13,5 @@ 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
\ No newline at end of file
diff --git a/requirements_other.txt b/requirements_other.txt
index 6566ced..e0363f2 100644
--- a/requirements_other.txt
+++ b/requirements_other.txt
@@ -13,3 +13,5 @@ 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
\ No newline at end of file

From ad0eab1224455af01239876a8be068948bc57077 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sat, 13 Jan 2024 22:45:01 +0000
Subject: [PATCH 05/44] Update atsetup.sh

added cutlet and unidic-lite
---
 atsetup.sh | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/atsetup.sh b/atsetup.sh
index 3700b82..2fded23 100644
--- a/atsetup.sh
+++ b/atsetup.sh
@@ -311,6 +311,8 @@ install_custom_standalone() {
     	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

From d52dcf86d56286ade6272e92bc937db8fef2e28f Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sat, 13 Jan 2024 23:43:15 +0000
Subject: [PATCH 06/44] Update README.md

---
 README.md | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/README.md b/README.md
index b5dd62a..85e4c7a 100644
--- a/README.md
+++ b/README.md
@@ -406,6 +406,14 @@ 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. 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)

From 893747c9a92e7814b84623cc955ff34cf917fed1 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sun, 14 Jan 2024 12:48:49 +0000
Subject: [PATCH 07/44] Add files via upload

---
 .github/ISSUE_TEMPLATE/FUNDING.yml | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 .github/ISSUE_TEMPLATE/FUNDING.yml

diff --git a/.github/ISSUE_TEMPLATE/FUNDING.yml b/.github/ISSUE_TEMPLATE/FUNDING.yml
new file mode 100644
index 0000000..6132bf2
--- /dev/null
+++ b/.github/ISSUE_TEMPLATE/FUNDING.yml
@@ -0,0 +1 @@
+ko_fi: erew123

From 04e08c58b8a4d1a209fd0a1f40a14f1aa38ab1e8 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sun, 14 Jan 2024 12:50:57 +0000
Subject: [PATCH 08/44] Delete .github/ISSUE_TEMPLATE/FUNDING.yml

---
 .github/ISSUE_TEMPLATE/FUNDING.yml | 1 -
 1 file changed, 1 deletion(-)
 delete mode 100644 .github/ISSUE_TEMPLATE/FUNDING.yml

diff --git a/.github/ISSUE_TEMPLATE/FUNDING.yml b/.github/ISSUE_TEMPLATE/FUNDING.yml
deleted file mode 100644
index 6132bf2..0000000
--- a/.github/ISSUE_TEMPLATE/FUNDING.yml
+++ /dev/null
@@ -1 +0,0 @@
-ko_fi: erew123

From c78927b80a52a2718f7caa5df134c04918742970 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sun, 14 Jan 2024 12:51:41 +0000
Subject: [PATCH 09/44] Create FND

---
 .github/FUNDING.yml | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 .github/FUNDING.yml

diff --git a/.github/FUNDING.yml b/.github/FUNDING.yml
new file mode 100644
index 0000000..6132bf2
--- /dev/null
+++ b/.github/FUNDING.yml
@@ -0,0 +1 @@
+ko_fi: erew123

From 08a04ba506864be27707edc60db91d82c5484a68 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 15 Jan 2024 11:36:29 +0000
Subject: [PATCH 10/44] Added warning about starting from disk location

---
 .../tts_chunk_player/tts_chunk_player.html    | 167 +++++++++---------
 1 file changed, 84 insertions(+), 83 deletions(-)

diff --git a/templates/tts_chunk_player/tts_chunk_player.html b/templates/tts_chunk_player/tts_chunk_player.html
index 4c5f7ec..61c36bd 100644
--- a/templates/tts_chunk_player/tts_chunk_player.html
+++ b/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,
@@ -637,51 +636,51 @@
     import Crunker from './crunker.esm.js';
 
     async function exportMP3() {
-    const crunker = new Crunker();
-    const fileUrls = ttsList.map(item => item.fileUrl);
-    const splitEvery = parseInt(document.getElementById('splitEvery').value) || 500;
-    const progressIndicator = document.getElementById('progressIndicator');
-    const progressText = document.getElementById('progressText');
+        const crunker = new Crunker();
+        const fileUrls = ttsList.map(item => item.fileUrl);
+        const splitEvery = parseInt(document.getElementById('splitEvery').value) || 500;
+        const progressIndicator = document.getElementById('progressIndicator');
+        const progressText = document.getElementById('progressText');
 
-    if (progressIndicator && progressText) {
-        progressIndicator.style.display = 'block';
-        progressText.textContent = 'Starting export...';
-    }
-
-    try {
-        for (let i = 0; i < fileUrls.length; i += splitEvery) {
-            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
+            progressIndicator.style.display = 'block';
+            progressText.textContent = 'Starting export...';
+        }
+
+        try {
+            for (let i = 0; i < fileUrls.length; i += splitEvery) {
+                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
+            }
         }
     }
-}
 
-window.exportMP3 = exportMP3;
+    window.exportMP3 = exportMP3;
 
 
 
@@ -1531,54 +1530,54 @@ window.exportMP3 = exportMP3;
     }
 
     function importFromJSON() {
-    const input = document.createElement('input');
-    input.type = 'file';
-    input.accept = '.json';
+        const input = document.createElement('input');
+        input.type = 'file';
+        input.accept = '.json';
 
-    input.onchange = async (e) => {
-        const file = e.target.files[0];
-        if (file) {
-            const reader = new FileReader();
-            reader.readAsText(file);
-            reader.onload = (e) => {
-                try {
-                    const jsonData = JSON.parse(e.target.result);
+        input.onchange = async (e) => {
+            const file = e.target.files[0];
+            if (file) {
+                const reader = new FileReader();
+                reader.readAsText(file);
+                reader.onload = (e) => {
+                    try {
+                        const jsonData = JSON.parse(e.target.result);
 
-                    ttsList = jsonData;
-                    currentPage = 1; // Reset to the first page
-                    updateUIList();
-                    updatePaginationControls(); // Update pagination controls
-                } catch (error) {
-                    console.error('Error parsing JSON:', error);
-                }
-            };
+                        ttsList = jsonData;
+                        currentPage = 1; // Reset to the first page
+                        updateUIList();
+                        updatePaginationControls(); // Update pagination controls
+                    } catch (error) {
+                        console.error('Error parsing JSON:', error);
+                    }
+                };
+            }
+        };
+
+        input.click();
+    }
+
+    function updatePaginationControls() {
+        const lastPage = Math.ceil(ttsList.length / itemsPerPage);
+        const pageIndicator = document.getElementById('pageIndicator');
+        if (pageIndicator) {
+            pageIndicator.textContent = `Page ${currentPage} of ${lastPage}`;
         }
-    };
 
-    input.click();
-}
+        const prevPageButton = document.getElementById('prevPage');
+        if (prevPageButton) {
+            prevPageButton.disabled = (currentPage === 1);
+        }
 
-function updatePaginationControls() {
-    const lastPage = Math.ceil(ttsList.length / itemsPerPage);
-    const pageIndicator = document.getElementById('pageIndicator');
-    if (pageIndicator) {
-        pageIndicator.textContent = `Page ${currentPage} of ${lastPage}`;
+        const nextPageButton = document.getElementById('nextPage');
+        if (nextPageButton) {
+            nextPageButton.disabled = (currentPage === lastPage);
+        }
+
+        // Similar updates for any additional pagination controls if you have them
+        // ...
     }
 
-    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
-    // ...
-}
-
 
 
 
@@ -1985,9 +1984,11 @@ function updatePaginationControls() {
     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>
 

From 631ea6dd8aada10efae04976c06b4b3d7588ef78 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 15 Jan 2024 13:38:00 +0000
Subject: [PATCH 11/44] Update README.md

---
 README.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 85e4c7a..f4393f1 100644
--- a/README.md
+++ b/README.md
@@ -27,9 +27,10 @@ AllTalk is an updated version of the Coqui_tts extension for Text Generation web
 - 🟠 [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 & Bug fixes
+## 🔄 Feature reqests, Updates & Bug fixes
 Please check the below link to find a list of all recent updates and changes.
 #### &nbsp;&nbsp;&nbsp;&nbsp;🔄 **Updates list & bug fixes list** can be found [here](https://github.com/erew123/alltalk_tts/issues/25)
+#### &nbsp;&nbsp;&nbsp;&nbsp;🔄 **Current Feature request list** can be found [here](https://github.com/erew123/alltalk_tts/discussions/74)
 
 ## 🟩 Quick Setup (Text-generation-webui & Standalone Installation)
 For Windows 10/11 and Linux machines there is a quick setup script. Click to expand the correct section below:

From f5e99a5e7250551798c73b3ffb006d888780a4c0 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 15 Jan 2024 13:38:28 +0000
Subject: [PATCH 12/44] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index f4393f1..05c1c9a 100644
--- a/README.md
+++ b/README.md
@@ -27,7 +27,7 @@ AllTalk is an updated version of the Coqui_tts extension for Text Generation web
 - 🟠 [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)
 
-## 🔄 Feature reqests, Updates & Bug fixes
+## 🔄 Feature requests, Updates & Bug fixes
 Please check the below link to find a list of all recent updates and changes.
 #### &nbsp;&nbsp;&nbsp;&nbsp;🔄 **Updates list & bug fixes list** can be found [here](https://github.com/erew123/alltalk_tts/issues/25)
 #### &nbsp;&nbsp;&nbsp;&nbsp;🔄 **Current Feature request list** can be found [here](https://github.com/erew123/alltalk_tts/discussions/74)

From bec4e905d33f4e87d7355a5214c61c02c2ecc437 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 15 Jan 2024 16:38:37 +0000
Subject: [PATCH 13/44] Push JS mimetype on /static

Push JS files with mimetype of application/javascript

From cefd1e045baf15c68fbdcac15fb1978850f8987f Mon Sep 17 00:00:00 2001
From: S95Sedan <89262821+S95Sedan@users.noreply.github.com>
Date: Mon, 15 Jan 2024 21:51:00 +0100
Subject: [PATCH 14/44] Temperature and Repetition_penalty modification

Modified script.py to enable temperature and repetition_penalty to be parsed and tts_server.py to recieve those variables.
---
 script.py     | 37 ++++++++++++++++++++++++-------------
 tts_server.py | 18 ++++++++++--------
 2 files changed, 34 insertions(+), 21 deletions(-)

diff --git a/script.py b/script.py
index 677dd2d..e569ff8 100644
--- a/script.py
+++ b/script.py
@@ -489,12 +489,14 @@ 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():
@@ -573,6 +575,8 @@ def output_modifier(string, state):
         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):
@@ -635,7 +639,7 @@ def output_modifier(string, state):
                 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
@@ -684,12 +688,14 @@ def get_output_filename(state):
 ###############################################
 #### 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"}
@@ -737,11 +743,13 @@ 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='Enable TTS')
             autoplay = gr.Checkbox(value=params['autoplay'], label='Autoplay TTS')
             show_text = gr.Checkbox(value=params['show_text'], label='Show Text')
-            
+
+        # Low vram enable, Deepspeed enable, Remove trailing dots
         with gr.Row():
             low_vram = gr.Checkbox(value=params['low_vram'], label='Enable Low VRAM Mode')
             low_vram_play = gr.HTML(visible=False)
@@ -749,6 +757,7 @@ def ui():
             deepspeed_checkbox_play = gr.HTML(visible=False)
             remove_trailing_dots = gr.Checkbox(value=params['remove_trailing_dots'], label='Remove trailing "."')
 
+        # TTS method, Character voice selection
         with gr.Row():
             model_loader_choices=["API TTS", "API Local", "XTTSv2 Local"]
             if finetuned_model:
@@ -769,17 +778,19 @@ def ui():
                 voice = gr.Dropdown(available_voices, label="Character Voice", value=default_voice, allow_custom_value=True, )
                 create_refresh_button(voice, lambda: None, lambda: {"choices": get_available_voices(), "value": params["voice"],}, "refresh-button",)
 
+        # Language, Narrator voice
         with gr.Row():
             language = gr.Dropdown(languages.keys(), label="Language", value=params["language"])
             with gr.Row():
                 narrator_voice_gr = gr.Dropdown(get_available_voices(), label="Narrator Voice", allow_custom_value=True, value=params["narrator_voice"])
                 create_refresh_button(narrator_voice_gr, lambda: None, lambda: {"choices": get_available_voices(), "value": params["narrator_voice"],}, "refresh-button")
 
-        # Temperature and Repetition Penalty (Not yet parsed to api/implemented)
-        # with gr.Row():
-        #     local_temperature_gr = gr.Slider(minimum=0, maximum=1, step=0.05, label="Temperature", value=params["local_temperature"])
-        #     local_repetition_penalty_gr = gr.Slider(minimum=0, maximum=20, step=0.5, label="Repetition Penalty", value=params["local_repetition_penalty"])
+        # 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", value="Enabled" if params.get("narrator_enabled") else "Disabled")
@@ -787,6 +798,7 @@ def ui():
                 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>")
 
+        # Preview speech
         with gr.Row():
             preview_text = gr.Text(
                 show_label=False,
@@ -795,7 +807,7 @@ def ui():
             )
             preview_play = gr.Button("Preview")
             preview_audio = gr.HTML(visible=False)
-
+        
         with gr.Row():
             convert = gr.Button("Permanently replace audios with the message texts")
             convert_cancel = gr.Button("Cancel", visible=False)
@@ -864,10 +876,9 @@ def ui():
     voice.change(lambda x: params.update({"voice": x}), voice, None)
     language.change(lambda x: params.update({"language": x}), language, None)
 
-
-    # TS Settings (Not yet parsed to api/implemented)
-    # 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)
+    # 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)
diff --git a/tts_server.py b/tts_server.py
index 4d2c48b..c431f40 100644
--- a/tts_server.py
+++ b/tts_server.py
@@ -473,16 +473,16 @@ 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()
@@ -504,9 +504,9 @@ 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
@@ -560,9 +560,9 @@ 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,
         )
@@ -602,10 +602,12 @@ 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(

From 5d406fbbfb1010610f3f7c62da9b716003c722ad Mon Sep 17 00:00:00 2001
From: S95Sedan <89262821+S95Sedan@users.noreply.github.com>
Date: Tue, 16 Jan 2024 00:37:10 +0100
Subject: [PATCH 15/44] Load variables fix

Load temp/repetition variables in tts_server incase of API only usage.
---
 tts_server.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tts_server.py b/tts_server.py
index c431f40..0f99f06 100644
--- a/tts_server.py
+++ b/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"
 

From a91a83268f741186f6f1751d95cfd0cdeb3723ca Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 15 Jan 2024 23:55:54 +0000
Subject: [PATCH 16/44] eval % option

---
 finetune.py | 18 ++++++++++++++----
 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/finetune.py b/finetune.py
index 5583137..f35fc43 100644
--- a/finetune.py
+++ b/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")
@@ -968,6 +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:"
             )
@@ -979,14 +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()
@@ -1274,6 +1283,7 @@ if __name__ == "__main__":
                     lang,
                     whisper_model,
                     out_path,
+                    eval_split_number,
                 ],
                 outputs=[
                     progress_data,

From 2731a559f45de0e7808a8e1f1329a41a480f7654 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Tue, 16 Jan 2024 00:12:54 +0000
Subject: [PATCH 17/44] Update README.md

---
 README.md | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/README.md b/README.md
index 05c1c9a..0a4dedb 100644
--- a/README.md
+++ b/README.md
@@ -464,6 +464,19 @@ 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/`.

From 64cffcdf80157decd9907ded61078e150a6e246a Mon Sep 17 00:00:00 2001
From: S95Sedan <89262821+S95Sedan@users.noreply.github.com>
Date: Tue, 16 Jan 2024 01:47:29 +0100
Subject: [PATCH 18/44] Updated tts_server.py

With changes in: https://github.com/S95Sedan/alltalk_tts/commit/cefd1e045baf15c68fbdcac15fb1978850f8987f#commitcomment-137124105
---
 tts_server.py | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/tts_server.py b/tts_server.py
index 0f99f06..8d831b7 100644
--- a/tts_server.py
+++ b/tts_server.py
@@ -728,7 +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}")
@@ -738,7 +738,7 @@ 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}")
@@ -800,7 +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'
@@ -837,7 +837,7 @@ import hashlib
 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, 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}")
@@ -847,7 +847,7 @@ async def tts_generate_streaming(text: str, voice: str, language: str, output_fi
 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, 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}")
@@ -1060,7 +1060,7 @@ async def tts_generate(
                 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
@@ -1097,7 +1097,7 @@ async def tts_generate(
                 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:

From f34ebbd675f57ff006c6a55b2d3174bc1a1cfa70 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Tue, 16 Jan 2024 01:00:48 +0000
Subject: [PATCH 19/44] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 0a4dedb..c4b1551 100644
--- a/README.md
+++ b/README.md
@@ -921,6 +921,6 @@ audioElement.play(); // Play the audio stream directly
 <br>
 
 ### 🔴 Future to-do list
+- 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).
-- Tagging support within text.
 - Have a break!

From 8c6fc4853d865cbebda8e163c7d22452f3085924 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Wed, 17 Jan 2024 22:01:51 +0000
Subject: [PATCH 20/44] Updated ST files

---
 templates/STfiles/alltalk.js |  315 ++----
 templates/STfiles/index.js   | 2074 +++++++++++++++++-----------------
 templates/STfiles/style.css  |  159 +++
 3 files changed, 1310 insertions(+), 1238 deletions(-)
 create mode 100644 templates/STfiles/style.css

diff --git a/templates/STfiles/alltalk.js b/templates/STfiles/alltalk.js
index e44b312..f70daf5 100644
--- a/templates/STfiles/alltalk.js
+++ b/templates/STfiles/alltalk.js
@@ -3,92 +3,33 @@ import { saveTtsProviderSettings } from './index.js';
 
 export { AllTalkTtsProvider };
 
-const css = `
-.settings-row {
-    display: flex;
-    justify-content: space-between; /* Distribute space evenly between the children */
-    align-items: center;
-    width: 100%; /* Full width to spread out the children */
-}
-
-.settings-option {
-    flex: 1; /* Each child will take equal space */
-    margin: 0 10px; /* Adjust spacing as needed */
-}
-
-.endpoint-option {
-    flex: 1; /* Each child will take equal space */
-    margin: 0 10px; /* Adjust spacing as needed */
-    margin-right: 25px;
-    width: 38%; /* Full width to spread out the children */
-}
-
-.website-row {
-    display: flex;
-    justify-content: start; /* Aligns items to the start of the row */
-    align-items: center;
-    margin-top: 10px; /* Top margin */
-    margin-bottom: 10px; /* Bottom margin */
-}
-
-.website-option {
-    flex: 1; /* Allows each option to take equal space */
-    margin-right: 10px; /* Spacing between the two options, adjust as needed */
-    margin-left: 10px; /* Adjust this value to align as desired */
-    /* Remove the individual margin top and bottom declarations if they are set globally on the .settings-row */
-}
-
-.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;
-}
-
-.status-message {
-    flex: 1; /* Adjust as needed */
-    margin: 0 10px;
-    /* Additional styling */
-}
-
-.model-endpoint-row {
-    display: flex;
-    justify-content: space-between;
-    align-items: center;
-    width: 100%;
-}
-
-.model-option, .endpoint-option {
-    flex: 1;
-    margin: 0 10px;
-    margin-left: 10px; /* Adjust this value to align as desired */
-    /* Adjust width as needed to fit in one line */
-}
-
-.endpoint-option {
-    /* Adjust width to align with model dropdown */
-    width: 38%;
-}
-
-#status_info {
-    color: lightgreen; /* Or any specific shade of green you prefer */
-}
-`;
-
-const style = document.createElement('style');
-style.type = 'text/css';
-style.appendChild(document.createTextNode(css));
-document.head.appendChild(style);
-
 class AllTalkTtsProvider {
     //########//
     // Config //
     //########//
 
-    settings;
+    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 = '. ';
@@ -114,23 +55,12 @@ class AllTalkTtsProvider {
         'Hindi': 'hi',
     };
 
-    Settings = {
-        provider_endpoint: 'http://localhost:7851',
-        language: 'en',
-        voiceMap: {},
-        at_generation_method: 'standard_generation',
-        narrator_enabled: 'false',
-        at_narrator_text_not_inside: 'narrator',
-        narrator_voice_gen: 'female_01.wav',
-        finetuned_model: 'false'
-    };
-
     get settingsHtml() {
-        let html = `<div class="settings-separator">AllTalk Settings</div>`;
+        let html = `<div class="at-settings-separator">AllTalk Settings</div>`;
 
-        html += `<div class="settings-row">
+        html += `<div class="at-settings-row">
 
-        <div class="settings-option">
+        <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>
@@ -139,9 +69,9 @@ class AllTalkTtsProvider {
         </div>
         </div>`;
 
-        html += `<div class="settings-row">
+        html += `<div class="at-settings-row">
 
-        <div class="settings-option">
+        <div class="at-settings-option">
             <label for="at_narrator_enabled">AT Narrator</label>
                 <select id="at_narrator_enabled">
                 <option value="true">Enabled</option>
@@ -149,7 +79,7 @@ class AllTalkTtsProvider {
         </select>
         </div>
 
-        <div class="settings-option">
+        <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>
@@ -159,8 +89,8 @@ class AllTalkTtsProvider {
 
     </div>`;
 
-        html += `<div class="settings-row">
-        <div class="settings-option">
+        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) {
@@ -170,7 +100,7 @@ class AllTalkTtsProvider {
         }
         html += `</select>
         </div>
-        <div class="settings-option">
+        <div class="at-settings-option">
             <label for="language_options">Language</label>
             <select id="language_options">`;
         for (let language in this.languageLabels) {
@@ -181,8 +111,8 @@ class AllTalkTtsProvider {
     </div>`;
 
 
-        html += `<div class="model-endpoint-row">
-    <div class="model-option">
+        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>
@@ -191,49 +121,47 @@ class AllTalkTtsProvider {
         </select>
         </div>
 
-        <div class="endpoint-option">
+        <div class="at-endpoint-option">
             <label for="at_server">AllTalk Endpoint:</label>
-            <input id="at_server" type="text" class="text_pole" maxlength="80" value="${this.Settings.provider_endpoint}"/>
+            <input id="at_server" type="text" class="text_pole" maxlength="80" value="${this.settings.provider_endpoint}"/>
         </div>
    </div>`;
 
 
-        html += `<div class="model-endpoint-row">
-    <div class="settings-option">
+        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="settings-option">
+    <div class="at-settings-option">
         <label for="deepspeed">DeepSpeed</label>
         <input id="deepspeed" type="checkbox"/>
     </div>
-    <div class="settings-option status-option">
+    <div class="at-settings-option status-option">
         <span>Status: <span id="status_info">Ready</span></span>
     </div>
-    <div class="settings-option empty-option">
+    <div class="at-settings-option empty-option">
         <!-- This div remains empty for spacing -->
     </div>
 </div>`;
 
 
-        html += `<div class="website-row">
-        <div class="website-option">
-        <span>AllTalk <a target="_blank" href="${this.Settings.provider_endpoint}">Config & Docs</a>.</span>
+        html += `<div class="at-website-row">
+        <div class="at-website-option">
+        <span>AllTalk <a target="_blank" href="${this.settings.provider_endpoint}">Config & Docs</a>.</span>
     </div>
 
-    <div class="website-option">
+    <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="website-row">
-<div class="website-option">
+        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;
     }
 
@@ -244,14 +172,35 @@ html += `<div class="website-row">
 
     async loadSettings(settings) {
         updateStatus('Offline');
-        // Use default settings if no settings are provided
-        this.settings = Object.keys(settings).length === 0 ? this.Settings : settings;
 
+        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
-            await this.updateSettingsFromServer();
             this.updateNarratorVoicesDropdown();
             this.updateLanguageDropdown();
             this.setupEventListeners();
@@ -259,29 +208,23 @@ html += `<div class="website-row">
             updateStatus('Ready');
         } catch (error) {
             console.error("Error loading settings:", error);
-            // Set status to Error if there is an issue in loading settings
             updateStatus('Offline');
         }
     }
 
     applySettingsToHTML() {
-        // Load AllTalk specific settings first
-        const loadedSettings = loadAllTalkSettings();
         // Apply loaded settings or use defaults
-        this.settings = loadedSettings ? { ...this.Settings, ...loadedSettings } : this.Settings;
         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', '');
-            this.settings.narrator_voice_gen = this.settings.narrator_voice;
-            //console.log(this.settings.narrator_voice_gen)
         }
         // Apply settings to AT Narrator Enabled dropdown
         if (atNarratorSelect) {
-            //console.log(this.settings.narrator_enabled)
             // 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
@@ -314,18 +257,15 @@ html += `<div class="website-row">
         const languageSelect = document.getElementById('language_options');
         if (languageSelect && this.settings.language) {
             languageSelect.value = this.settings.language;
-            //console.log(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;
-            //console.log(this.settings.at_narrator_text_not_inside)
         }
         // Apply settings to Generation Method dropdown
         if (generationMethodSelect && this.settings.at_generation_method) {
             generationMethodSelect.value = this.settings.at_generation_method;
-            //console.log(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';
@@ -347,7 +287,6 @@ html += `<div class="website-row">
             ftOption.textContent = 'XTTSv2 FT';
             modelSelect.appendChild(ftOption);
         }
-        //console.log("Settings applied to HTML.");
     }
 
     //##############################//
@@ -486,7 +425,7 @@ html += `<div class="website-row">
         const languageSelect = document.getElementById('language_options');
         if (languageSelect) {
             // Ensure default language is set
-            this.settings.language = this.Settings.language;
+            this.settings.language = this.settings.language;
 
             languageSelect.innerHTML = '';
             for (let language in this.languageLabels) {
@@ -610,7 +549,7 @@ html += `<div class="website-row">
         if (narratorVoiceSelect) {
             narratorVoiceSelect.addEventListener('change', (event) => {
                 this.settings.narrator_voice_gen = `${event.target.value}.wav`;
-                this.onSettingsChangeAllTalk(); // Save the settings after change
+                this.onSettingsChange(); // Save the settings after change
             });
         }
 
@@ -618,7 +557,7 @@ html += `<div class="website-row">
         if (textNotInsideSelect) {
             textNotInsideSelect.addEventListener('change', (event) => {
                 this.settings.text_not_inside = event.target.value;
-                this.onSettingsChangeAllTalk(); // Save the settings after change
+                this.onSettingsChange(); // Save the settings after change
             });
         }
 
@@ -656,12 +595,11 @@ html += `<div class="website-row">
                     $('#tts_narrate_dialogues').click();
                     $('#tts_narrate_dialogues').trigger('change');
                 }
-                this.onSettingsChangeAllTalk(); // Save the settings after 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');
@@ -680,7 +618,7 @@ html += `<div class="website-row">
                     atNarratorEnabledSelect.disabled = false;
                 }
                 this.settings.at_generation_method = selectedMethod; // Update the setting here
-                this.onSettingsChangeAllTalk(); // Save the settings after change
+                this.onSettingsChange(); // Save the settings after change
             });
         }
 
@@ -689,9 +627,19 @@ html += `<div class="website-row">
         if (languageSelect) {
             languageSelect.addEventListener('change', (event) => {
                 this.settings.language = event.target.value;
-                this.onSettingsChangeAllTalk(); // Save the settings after change
+                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
+            });
+        }
+
     }
 
     //#############################//
@@ -699,30 +647,16 @@ html += `<div class="website-row">
     //#############################//
 
     onSettingsChange() {
-        // Update settings that SillyTavern will save
-        this.settings.provider_endpoint = $('#at_server').val();
+        // Update settings based on the UI elements
+        //this.settings.provider_endpoint = $('#at_server').val();
         this.settings.language = $('#language_options').val();
-        saveTtsProviderSettings(); // This function should save settings handled by SillyTavern
-        // Call the function to handle AllTalk specific settings
-        this.onSettingsChangeAllTalk(); // Save the settings after change
-    }
-
-    onSettingsChangeAllTalk() {
-        // Update AllTalk specific settings and save to localStorage
-        this.settings.narrator_enabled = $('#at_narrator_enabled').val() === 'true';
-        this.settings.narrator_voice = $('#narrator_voice').val() + '.wav'; // assuming you need to append .wav
-        this.settings.text_not_inside = $('#at_narrator_text_not_inside').val(); // "character" or "narrator"
-        this.settings.at_generation_method = $('#at_generation_method').val(); // Streaming or standard
-        this.settings.language = $('#language_options').val(); // Streaming or standard
-
-        // Call the save function with the current settings
-        saveAllTalkSettings({
-            narrator_voice: this.settings.narrator_voice,
-            narrator_enabled: this.settings.narrator_enabled,
-            text_not_inside: this.settings.text_not_inside,
-            at_generation_method: this.settings.at_generation_method,
-            language: this.settings.language
-        });
+        //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();
     }
 
     //#########################//
@@ -802,38 +736,20 @@ html += `<div class="website-row">
     async generateTts(inputText, voiceId) {
         try {
             if (this.settings.at_generation_method === 'streaming_enabled') {
-                // For streaming method
+                // 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`;
-                const audioElement = new Audio(streamingUrl);
-                audioElement.play(); // Play the audio stream directly
                 console.log("Streaming URL:", streamingUrl);
-                return new Response(null, {
-                    status: 200,
-                    statusText: "OK",
-                    headers: {
-                        "Content-Type": "audio/wav",
-                        "Content-Location": streamingUrl
-                    }
-                });
+        
+                // Return the streaming URL directly
+                return streamingUrl; 
             } else {
                 // For standard method
                 const outputUrl = await this.fetchTtsGeneration(inputText, voiceId);
-                // Fetch the audio data as a blob from the URL
                 const audioResponse = await fetch(outputUrl);
                 if (!audioResponse.ok) {
                     throw new Error(`HTTP ${audioResponse.status}: Failed to fetch audio data`);
                 }
-                const audioBlob = await audioResponse.blob();
-                if (!audioBlob.type.startsWith('audio/')) {
-                    throw new Error(`Invalid audio data format. Expecting audio/*, got ${audioBlob.type}`);
-                }
-                return new Response(audioBlob, {
-                    status: 200,
-                    statusText: "OK",
-                    headers: {
-                        "Content-Type": audioBlob.type
-                    }
-                });
+                return audioResponse; // Return the fetch response directly
             }
         } catch (error) {
             console.error("Error in generateTts:", error);
@@ -841,6 +757,7 @@ html += `<div class="website-row">
         }
     }
 
+
     //####################//
     //  Generate Standard //
     //####################//
@@ -852,8 +769,8 @@ html += `<div class="website-row">
             'text_filtering': "standard",
             'character_voice_gen': voiceId + ".wav",
             'narrator_enabled': this.settings.narrator_enabled,
-            'narrator_voice_gen': this.settings.narrator_voice_gen,
-            'text_not_inside': this.settings.text_not_inside,
+            '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",
@@ -877,7 +794,6 @@ html += `<div class="website-row">
             if (!response.ok) {
                 const errorText = await response.text();
                 console.error(`[fetchTtsGeneration] Error Response Text:`, errorText);
-                // Uncomment the following line if you have a UI element for displaying errors
                 // toastr.error(response.statusText, 'TTS Generation Failed');
                 throw new Error(`HTTP ${response.status}: ${errorText}`);
             }
@@ -912,27 +828,6 @@ function updateStatus(message) {
             case 'Error':
                 statusElement.style.color = 'red';
                 break;
-            // Add more cases as needed
         }
     }
-}
-
-//########################//
-//  Save/load AT Settings //
-//########################//
-
-function saveAllTalkSettings(settingsToSave) {
-    // Save the specific settings to localStorage
-    console.log("settings", settingsToSave)
-    localStorage.setItem('AllTalkSettings', JSON.stringify(settingsToSave));
-}
-
-function loadAllTalkSettings() {
-    // Retrieve the settings from localStorage
-    const settings = localStorage.getItem('AllTalkSettings');
-    // If settings exist, parse them back into an object
-    if (settings) {
-        return JSON.parse(settings);
-    }
-    return null;
-}
+}
\ No newline at end of file
diff --git a/templates/STfiles/index.js b/templates/STfiles/index.js
index d07aea6..dd84a22 100644
--- a/templates/STfiles/index.js
+++ b/templates/STfiles/index.js
@@ -1,1028 +1,1046 @@
-import { callPopup, cancelTtsPlay, eventSource, event_types, name2, saveSettingsDebounced } from '../../../script.js';
-import { ModuleWorkerWrapper, doExtrasFetch, extension_settings, getApiUrl, getContext, modules } from '../../extensions.js';
-import { delay, escapeRegex, getStringHash } from '../../utils.js';
-import { EdgeTtsProvider } from './edge.js';
-import { ElevenLabsTtsProvider } from './elevenlabs.js';
-import { SileroTtsProvider } from './silerotts.js';
-import { CoquiTtsProvider } from './coqui.js';
-import { SystemTtsProvider } from './system.js';
-import { NovelTtsProvider } from './novel.js';
-import { power_user } from '../../power-user.js';
-import { registerSlashCommand } from '../../slash-commands.js';
-import { OpenAITtsProvider } from './openai.js';
-import { XTTSTtsProvider } from './xtts.js';
-import { AllTalkTtsProvider } from './alltalk.js';
-export { talkingAnimation };
-
-const UPDATE_INTERVAL = 1000;
-
-let voiceMapEntries = [];
-let voiceMap = {}; // {charName:voiceid, charName2:voiceid2}
-let storedvalue = false;
-let lastChatId = null;
-let lastMessageHash = null;
-
-const DEFAULT_VOICE_MARKER = '[Default Voice]';
-const DISABLED_VOICE_MARKER = 'disabled';
-
-export function getPreviewString(lang) {
-    const previewStrings = {
-        'en-US': 'The quick brown fox jumps over the lazy dog',
-        'en-GB': 'Sphinx of black quartz, judge my vow',
-        'fr-FR': 'Portez ce vieux whisky au juge blond qui fume',
-        'de-DE': 'Victor jagt zwölf Boxkämpfer quer über den großen Sylter Deich',
-        'it-IT': 'Pranzo d\'acqua fa volti sghembi',
-        'es-ES': 'Quiere la boca exhausta vid, kiwi, piña y fugaz jamón',
-        'es-MX': 'Fabio me exige, sin tapujos, que añada cerveza al whisky',
-        'ru-RU': 'В чащах юга жил бы цитрус? Да, но фальшивый экземпляр!',
-        'pt-BR': 'Vejo xá gritando que fez show sem playback.',
-        'pt-PR': 'Todo pajé vulgar faz boquinha sexy com kiwi.',
-        'uk-UA': 'Фабрикуймо гідність, лящім їжею, ґав хапаймо, з\'єднавці чаш!',
-        'pl-PL': 'Pchnąć w tę łódź jeża lub ośm skrzyń fig',
-        'cs-CZ': 'Příliš žluťoučký kůň úpěl ďábelské ódy',
-        'sk-SK': 'Vyhŕňme si rukávy a vyprážajme čínske ryžové cestoviny',
-        'hu-HU': 'Árvíztűrő tükörfúrógép',
-        'tr-TR': 'Pijamalı hasta yağız şoföre çabucak güvendi',
-        'nl-NL': 'De waard heeft een kalfje en een pinkje opgegeten',
-        'sv-SE': 'Yxskaftbud, ge vårbygd, zinkqvarn',
-        'da-DK': 'Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen Walther spillede på xylofon',
-        'ja-JP': 'いろはにほへと　ちりぬるを　わかよたれそ　つねならむ　うゐのおくやま　けふこえて　あさきゆめみし　ゑひもせす',
-        'ko-KR': '가나다라마바사아자차카타파하',
-        'zh-CN': '我能吞下玻璃而不伤身体',
-        'ro-RO': 'Muzicologă în bej vând whisky și tequila, preț fix',
-        'bg-BG': 'Щъркелите се разпръснаха по цялото небе',
-        'el-GR': 'Ταχίστη αλώπηξ βαφής ψημένη γη, δρασκελίζει υπέρ νωθρού κυνός',
-        'fi-FI': 'Voi veljet, miksi juuri teille myin nämä vehkeet?',
-        'he-IL': 'הקצינים צעקו: "כל הכבוד לצבא הצבאות!"',
-        'id-ID': 'Jangkrik itu memang enak, apalagi kalau digoreng',
-        'ms-MY': 'Muzik penyanyi wanita itu menggambarkan kehidupan yang penuh dengan duka nestapa',
-        'th-TH': 'เป็นไงบ้างครับ ผมชอบกินข้าวผัดกระเพราหมูกรอบ',
-        'vi-VN': 'Cô bé quàng khăn đỏ đang ngồi trên bãi cỏ xanh',
-        'ar-SA': 'أَبْجَدِيَّة عَرَبِيَّة',
-        'hi-IN': 'श्वेता ने श्वेता के श्वेते हाथों में श्वेता का श्वेता चावल पकड़ा',
-    };
-    const fallbackPreview = 'Neque porro quisquam est qui dolorem ipsum quia dolor sit amet';
-
-    return previewStrings[lang] ?? fallbackPreview;
-}
-
-let ttsProviders = {
-    ElevenLabs: ElevenLabsTtsProvider,
-    Silero: SileroTtsProvider,
-    XTTSv2: XTTSTtsProvider,
-    System: SystemTtsProvider,
-    Coqui: CoquiTtsProvider,
-    Edge: EdgeTtsProvider,
-    Novel: NovelTtsProvider,
-    OpenAI: OpenAITtsProvider,
-    AllTalk: AllTalkTtsProvider,
-};
-let ttsProvider;
-let ttsProviderName;
-
-let ttsLastMessage = null;
-
-async function onNarrateOneMessage() {
-    audioElement.src = '/sounds/silence.mp3';
-    const context = getContext();
-    const id = $(this).closest('.mes').attr('mesid');
-    const message = context.chat[id];
-
-    if (!message) {
-        return;
-    }
-
-    resetTtsPlayback();
-    ttsJobQueue.push(message);
-    moduleWorker();
-}
-
-async function onNarrateText(args, text) {
-    if (!text) {
-        return;
-    }
-
-    audioElement.src = '/sounds/silence.mp3';
-
-    // To load all characters in the voice map, set unrestricted to true
-    await initVoiceMap(true);
-
-    const baseName = args?.voice || name2;
-    const name = (baseName === 'SillyTavern System' ? DEFAULT_VOICE_MARKER : baseName) || DEFAULT_VOICE_MARKER;
-
-    const voiceMapEntry = voiceMap[name] === DEFAULT_VOICE_MARKER
-        ? voiceMap[DEFAULT_VOICE_MARKER]
-        : voiceMap[name];
-
-    if (!voiceMapEntry || voiceMapEntry === DISABLED_VOICE_MARKER) {
-        toastr.info(`Specified voice for ${name} was not found. Check the TTS extension settings.`);
-        return;
-    }
-
-    resetTtsPlayback();
-    ttsJobQueue.push({ mes: text, name: name });
-    await moduleWorker();
-
-    // Return back to the chat voices
-    await initVoiceMap(false);
-}
-
-async function moduleWorker() {
-    // Primarily determining when to add new chat to the TTS queue
-    const enabled = $('#tts_enabled').is(':checked');
-    $('body').toggleClass('tts', enabled);
-    if (!enabled) {
-        return;
-    }
-
-    const context = getContext();
-    const chat = context.chat;
-
-    processTtsQueue();
-    processAudioJobQueue();
-    updateUiAudioPlayState();
-
-    // Auto generation is disabled
-    if (extension_settings.tts.auto_generation == false) {
-        return;
-    }
-
-    // no characters or group selected
-    if (!context.groupId && context.characterId === undefined) {
-        return;
-    }
-
-    // Chat changed
-    if (
-        context.chatId !== lastChatId
-    ) {
-        currentMessageNumber = context.chat.length ? context.chat.length : 0;
-        saveLastValues();
-
-        // Force to speak on the first message in the new chat
-        if (context.chat.length === 1) {
-            lastMessageHash = -1;
-        }
-
-        return;
-    }
-
-    // take the count of messages
-    let lastMessageNumber = context.chat.length ? context.chat.length : 0;
-
-    // There's no new messages
-    let diff = lastMessageNumber - currentMessageNumber;
-    let hashNew = getStringHash((chat.length && chat[chat.length - 1].mes) ?? '');
-
-    // if messages got deleted, diff will be < 0
-    if (diff < 0) {
-        // necessary actions will be taken by the onChatDeleted() handler
-        return;
-    }
-
-    // if no new messages, or same message, or same message hash, do nothing
-    if (diff == 0 && hashNew === lastMessageHash) {
-        return;
-    }
-
-    // If streaming, wait for streaming to finish before processing new messages
-    if (context.streamingProcessor && !context.streamingProcessor.isFinished) {
-        return;
-    }
-
-    // clone message object, as things go haywire if message object is altered below (it's passed by reference)
-    const message = structuredClone(chat[chat.length - 1]);
-
-    // if last message within current message, message got extended. only send diff to TTS.
-    if (ttsLastMessage !== null && message.mes.indexOf(ttsLastMessage) !== -1) {
-        let tmp = message.mes;
-        message.mes = message.mes.replace(ttsLastMessage, '');
-        ttsLastMessage = tmp;
-    } else {
-        ttsLastMessage = message.mes;
-    }
-
-    // We're currently swiping. Don't generate voice
-    if (!message || message.mes === '...' || message.mes === '') {
-        return;
-    }
-
-    // Don't generate if message doesn't have a display text
-    if (extension_settings.tts.narrate_translated_only && !(message?.extra?.display_text)) {
-        return;
-    }
-
-    // Don't generate if message is a user message and user message narration is disabled
-    if (message.is_user && !extension_settings.tts.narrate_user) {
-        return;
-    }
-
-    // New messages, add new chat to history
-    lastMessageHash = hashNew;
-    currentMessageNumber = lastMessageNumber;
-
-    console.debug(
-        `Adding message from ${message.name} for TTS processing: "${message.mes}"`,
-    );
-    ttsJobQueue.push(message);
-}
-
-function talkingAnimation(switchValue) {
-    if (!modules.includes('talkinghead')) {
-        console.debug('Talking Animation module not loaded');
-        return;
-    }
-
-    const apiUrl = getApiUrl();
-    const animationType = switchValue ? 'start' : 'stop';
-
-    if (switchValue !== storedvalue) {
-        try {
-            console.log(animationType + ' Talking Animation');
-            doExtrasFetch(`${apiUrl}/api/talkinghead/${animationType}_talking`);
-            storedvalue = switchValue; // Update the storedvalue to the current switchValue
-        } catch (error) {
-            // Handle the error here or simply ignore it to prevent logging
-        }
-    }
-    updateUiAudioPlayState();
-}
-
-function resetTtsPlayback() {
-    // Stop system TTS utterance
-    cancelTtsPlay();
-
-    // Clear currently processing jobs
-    currentTtsJob = null;
-    currentAudioJob = null;
-
-    // Reset audio element
-    audioElement.currentTime = 0;
-    audioElement.src = '';
-
-    // Clear any queue items
-    ttsJobQueue.splice(0, ttsJobQueue.length);
-    audioJobQueue.splice(0, audioJobQueue.length);
-
-    // Set audio ready to process again
-    audioQueueProcessorReady = true;
-}
-
-function isTtsProcessing() {
-    let processing = false;
-
-    // Check job queues
-    if (ttsJobQueue.length > 0 || audioJobQueue.length > 0) {
-        processing = true;
-    }
-    // Check current jobs
-    if (currentTtsJob != null || currentAudioJob != null) {
-        processing = true;
-    }
-    return processing;
-}
-
-function debugTtsPlayback() {
-    console.log(JSON.stringify(
-        {
-            'ttsProviderName': ttsProviderName,
-            'voiceMap': voiceMap,
-            'currentMessageNumber': currentMessageNumber,
-            'audioPaused': audioPaused,
-            'audioJobQueue': audioJobQueue,
-            'currentAudioJob': currentAudioJob,
-            'audioQueueProcessorReady': audioQueueProcessorReady,
-            'ttsJobQueue': ttsJobQueue,
-            'currentTtsJob': currentTtsJob,
-            'ttsConfig': extension_settings.tts,
-        },
-    ));
-}
-window.debugTtsPlayback = debugTtsPlayback;
-
-//##################//
-//   Audio Control  //
-//##################//
-
-let audioElement = new Audio();
-audioElement.id = 'tts_audio';
-audioElement.autoplay = true;
-
-let audioJobQueue = [];
-let currentAudioJob;
-let audioPaused = false;
-let audioQueueProcessorReady = true;
-
-async function playAudioData(audioBlob) {
-    // Since current audio job can be cancelled, don't playback if it is null
-    if (currentAudioJob == null) {
-        console.log('Cancelled TTS playback because currentAudioJob was null');
-    }
-    const reader = new FileReader();
-    reader.onload = function (e) {
-        const srcUrl = e.target.result;
-        audioElement.src = srcUrl;
-    };
-    reader.readAsDataURL(audioBlob);
-    audioElement.addEventListener('ended', completeCurrentAudioJob);
-    audioElement.addEventListener('canplay', () => {
-        console.debug('Starting TTS playback');
-        audioElement.play();
-    });
-}
-
-window['tts_preview'] = function (id) {
-    const audio = document.getElementById(id);
-
-    if (audio && !$(audio).data('disabled')) {
-        audio.play();
-    }
-    else {
-        ttsProvider.previewTtsVoice(id);
-    }
-};
-
-async function onTtsVoicesClick() {
-    let popupText = '';
-
-    try {
-        const voiceIds = await ttsProvider.fetchTtsVoiceObjects();
-
-        for (const voice of voiceIds) {
-            popupText += `
-            <div class="voice_preview">
-                <span class="voice_lang">${voice.lang || ''}</span>
-                <b class="voice_name">${voice.name}</b>
-                <i onclick="tts_preview('${voice.voice_id}')" class="fa-solid fa-play"></i>
-            </div>`;
-            if (voice.preview_url) {
-                popupText += `<audio id="${voice.voice_id}" src="${voice.preview_url}" data-disabled="${voice.preview_url == false}"></audio>`;
-            }
-        }
-    } catch {
-        popupText = 'Could not load voices list. Check your API key.';
-    }
-
-    callPopup(popupText, 'text');
-}
-
-function updateUiAudioPlayState() {
-    if (extension_settings.tts.enabled == true) {
-        $('#ttsExtensionMenuItem').show();
-        let img;
-        // Give user feedback that TTS is active by setting the stop icon if processing or playing
-        if (!audioElement.paused || isTtsProcessing()) {
-            img = 'fa-solid fa-stop-circle extensionsMenuExtensionButton';
-        } else {
-            img = 'fa-solid fa-circle-play extensionsMenuExtensionButton';
-        }
-        $('#tts_media_control').attr('class', img);
-    } else {
-        $('#ttsExtensionMenuItem').hide();
-    }
-}
-
-function onAudioControlClicked() {
-    audioElement.src = '/sounds/silence.mp3';
-    let context = getContext();
-    // Not pausing, doing a full stop to anything TTS is doing. Better UX as pause is not as useful
-    if (!audioElement.paused || isTtsProcessing()) {
-        resetTtsPlayback();
-        talkingAnimation(false);
-    } else {
-        // Default play behavior if not processing or playing is to play the last message.
-        ttsJobQueue.push(context.chat[context.chat.length - 1]);
-    }
-    updateUiAudioPlayState();
-}
-
-function addAudioControl() {
-
-    $('#extensionsMenu').prepend(`
-        <div id="ttsExtensionMenuItem" class="list-group-item flex-container flexGap5">
-            <div id="tts_media_control" class="extensionsMenuExtensionButton "/></div>
-            TTS Playback
-        </div>`);
-    $('#ttsExtensionMenuItem').attr('title', 'TTS play/pause').on('click', onAudioControlClicked);
-    updateUiAudioPlayState();
-}
-
-function completeCurrentAudioJob() {
-    audioQueueProcessorReady = true;
-    currentAudioJob = null;
-    talkingAnimation(false); //stop lip animation
-    // updateUiPlayState();
-}
-
-/**
- * Accepts an HTTP response containing audio/mpeg data, and puts the data as a Blob() on the queue for playback
- * @param {Response} response
- */
-async function addAudioJob(response) {
-    const audioData = await response.blob();
-    if (!audioData.type.startsWith('audio/')) {
-        throw `TTS received HTTP response with invalid data format. Expecting audio/*, got ${audioData.type}`;
-    }
-    audioJobQueue.push(audioData);
-    console.debug('Pushed audio job to queue.');
-}
-
-async function processAudioJobQueue() {
-    // Nothing to do, audio not completed, or audio paused - stop processing.
-    if (audioJobQueue.length == 0 || !audioQueueProcessorReady || audioPaused) {
-        return;
-    }
-    try {
-        audioQueueProcessorReady = false;
-        currentAudioJob = audioJobQueue.pop();
-        playAudioData(currentAudioJob);
-        talkingAnimation(true);
-    } catch (error) {
-        console.error(error);
-        audioQueueProcessorReady = true;
-    }
-}
-
-//################//
-//  TTS Control   //
-//################//
-
-let ttsJobQueue = [];
-let currentTtsJob; // Null if nothing is currently being processed
-let currentMessageNumber = 0;
-
-function completeTtsJob() {
-    console.info(`Current TTS job for ${currentTtsJob?.name} completed.`);
-    currentTtsJob = null;
-}
-
-function saveLastValues() {
-    const context = getContext();
-    lastChatId = context.chatId;
-    lastMessageHash = getStringHash(
-        (context.chat.length && context.chat[context.chat.length - 1].mes) ?? '',
-    );
-}
-
-async function tts(text, voiceId, char) {
-    let response = await ttsProvider.generateTts(text, voiceId);
-
-    // RVC injection
-    if (extension_settings.rvc.enabled && typeof window['rvcVoiceConversion'] === 'function')
-        response = await window['rvcVoiceConversion'](response, char, text);
-
-    addAudioJob(response);
-    completeTtsJob();
-}
-
-async function processTtsQueue() {
-    // Called each moduleWorker iteration to pull chat messages from queue
-    if (currentTtsJob || ttsJobQueue.length <= 0 || audioPaused) {
-        return;
-    }
-
-    console.debug('New message found, running TTS');
-    currentTtsJob = ttsJobQueue.shift();
-    let text = extension_settings.tts.narrate_translated_only ? (currentTtsJob?.extra?.display_text || currentTtsJob.mes) : currentTtsJob.mes;
-
-    if (extension_settings.tts.skip_codeblocks) {
-        text = text.replace(/^\s{4}.*$/gm, '').trim();
-        text = text.replace(/```.*?```/gs, '').trim();
-    }
-
-    if (!extension_settings.tts.pass_asterisks) {
-        text = extension_settings.tts.narrate_dialogues_only
-            ? text.replace(/\*[^*]*?(\*|$)/g, '').trim() // remove asterisks content
-            : text.replaceAll('*', '').trim(); // remove just the asterisks
-    }
-
-    if (extension_settings.tts.narrate_quoted_only) {
-        const special_quotes = /[“”]/g; // Extend this regex to include other special quotes
-        text = text.replace(special_quotes, '"');
-        const matches = text.match(/".*?"/g); // Matches text inside double quotes, non-greedily
-        const partJoiner = (ttsProvider?.separator || ' ... ');
-        text = matches ? matches.join(partJoiner) : text;
-    }
-
-    if (typeof ttsProvider?.processText === 'function') {
-        text = await ttsProvider.processText(text);
-    }
-
-    // Collapse newlines and spaces into single space
-    text = text.replace(/\s+/g, ' ').trim();
-
-    console.log(`TTS: ${text}`);
-    const char = currentTtsJob.name;
-
-    // Remove character name from start of the line if power user setting is disabled
-    if (char && !power_user.allow_name2_display) {
-        const escapedChar = escapeRegex(char);
-        text = text.replace(new RegExp(`^${escapedChar}:`, 'gm'), '');
-    }
-
-    try {
-        if (!text) {
-            console.warn('Got empty text in TTS queue job.');
-            completeTtsJob();
-            return;
-        }
-
-        const voiceMapEntry = voiceMap[char] === DEFAULT_VOICE_MARKER ? voiceMap[DEFAULT_VOICE_MARKER] : voiceMap[char];
-
-        if (!voiceMapEntry || voiceMapEntry === DISABLED_VOICE_MARKER) {
-            throw `${char} not in voicemap. Configure character in extension settings voice map`;
-        }
-        const voice = await ttsProvider.getVoice(voiceMapEntry);
-        const voiceId = voice.voice_id;
-        if (voiceId == null) {
-            toastr.error(`Specified voice for ${char} was not found. Check the TTS extension settings.`);
-            throw `Unable to attain voiceId for ${char}`;
-        }
-        tts(text, voiceId, char);
-    } catch (error) {
-        console.error(error);
-        currentTtsJob = null;
-    }
-}
-
-// Secret function for now
-async function playFullConversation() {
-    const context = getContext();
-    const chat = context.chat;
-    ttsJobQueue = chat;
-}
-window.playFullConversation = playFullConversation;
-
-//#############################//
-//  Extension UI and Settings  //
-//#############################//
-
-function loadSettings() {
-    if (Object.keys(extension_settings.tts).length === 0) {
-        Object.assign(extension_settings.tts, defaultSettings);
-    }
-    for (const key in defaultSettings) {
-        if (!(key in extension_settings.tts)) {
-            extension_settings.tts[key] = defaultSettings[key];
-        }
-    }
-    $('#tts_provider').val(extension_settings.tts.currentProvider);
-    $('#tts_enabled').prop(
-        'checked',
-        extension_settings.tts.enabled,
-    );
-    $('#tts_narrate_dialogues').prop('checked', extension_settings.tts.narrate_dialogues_only);
-    $('#tts_narrate_quoted').prop('checked', extension_settings.tts.narrate_quoted_only);
-    $('#tts_auto_generation').prop('checked', extension_settings.tts.auto_generation);
-    $('#tts_narrate_translated_only').prop('checked', extension_settings.tts.narrate_translated_only);
-    $('#tts_narrate_user').prop('checked', extension_settings.tts.narrate_user);
-    $('#tts_pass_asterisks').prop('checked', extension_settings.tts.pass_asterisks);
-    $('body').toggleClass('tts', extension_settings.tts.enabled);
-}
-
-const defaultSettings = {
-    voiceMap: '',
-    ttsEnabled: false,
-    currentProvider: 'ElevenLabs',
-    auto_generation: true,
-    narrate_user: false,
-};
-
-function setTtsStatus(status, success) {
-    $('#tts_status').text(status);
-    if (success) {
-        $('#tts_status').removeAttr('style');
-    } else {
-        $('#tts_status').css('color', 'red');
-    }
-}
-
-function onRefreshClick() {
-    Promise.all([
-        ttsProvider.onRefreshClick(),
-        // updateVoiceMap()
-    ]).then(() => {
-        extension_settings.tts[ttsProviderName] = ttsProvider.settings;
-        saveSettingsDebounced();
-        setTtsStatus('Successfully applied settings', true);
-        console.info(`Saved settings ${ttsProviderName} ${JSON.stringify(ttsProvider.settings)}`);
-        initVoiceMap();
-        updateVoiceMap();
-    }).catch(error => {
-        console.error(error);
-        setTtsStatus(error, false);
-    });
-}
-
-function onEnableClick() {
-    extension_settings.tts.enabled = $('#tts_enabled').is(
-        ':checked',
-    );
-    updateUiAudioPlayState();
-    saveSettingsDebounced();
-}
-
-
-function onAutoGenerationClick() {
-    extension_settings.tts.auto_generation = !!$('#tts_auto_generation').prop('checked');
-    saveSettingsDebounced();
-}
-
-
-function onNarrateDialoguesClick() {
-    extension_settings.tts.narrate_dialogues_only = !!$('#tts_narrate_dialogues').prop('checked');
-    saveSettingsDebounced();
-}
-
-function onNarrateUserClick() {
-    extension_settings.tts.narrate_user = !!$('#tts_narrate_user').prop('checked');
-    saveSettingsDebounced();
-}
-
-function onNarrateQuotedClick() {
-    extension_settings.tts.narrate_quoted_only = !!$('#tts_narrate_quoted').prop('checked');
-    saveSettingsDebounced();
-}
-
-
-function onNarrateTranslatedOnlyClick() {
-    extension_settings.tts.narrate_translated_only = !!$('#tts_narrate_translated_only').prop('checked');
-    saveSettingsDebounced();
-}
-
-function onSkipCodeblocksClick() {
-    extension_settings.tts.skip_codeblocks = !!$('#tts_skip_codeblocks').prop('checked');
-    saveSettingsDebounced();
-}
-
-function onPassAsterisksClick() {
-    extension_settings.tts.pass_asterisks = !!$('#tts_pass_asterisks').prop('checked');
-    saveSettingsDebounced();
-}
-
-//##############//
-// TTS Provider //
-//##############//
-
-async function loadTtsProvider(provider) {
-    //Clear the current config and add new config
-    $('#tts_provider_settings').html('');
-
-    if (!provider) {
-        return;
-    }
-
-    // Init provider references
-    extension_settings.tts.currentProvider = provider;
-    ttsProviderName = provider;
-    ttsProvider = new ttsProviders[provider];
-
-    // Init provider settings
-    $('#tts_provider_settings').append(ttsProvider.settingsHtml);
-    if (!(ttsProviderName in extension_settings.tts)) {
-        console.warn(`Provider ${ttsProviderName} not in Extension Settings, initiatilizing provider in settings`);
-        extension_settings.tts[ttsProviderName] = {};
-    }
-    await ttsProvider.loadSettings(extension_settings.tts[ttsProviderName]);
-    await initVoiceMap();
-}
-
-function onTtsProviderChange() {
-    const ttsProviderSelection = $('#tts_provider').val();
-    extension_settings.tts.currentProvider = ttsProviderSelection;
-    loadTtsProvider(ttsProviderSelection);
-}
-
-// Ensure that TTS provider settings are saved to extension settings.
-export function saveTtsProviderSettings() {
-    extension_settings.tts[ttsProviderName] = ttsProvider.settings;
-    updateVoiceMap();
-    saveSettingsDebounced();
-    console.info(`Saved settings ${ttsProviderName} ${JSON.stringify(ttsProvider.settings)}`);
-}
-
-
-//###################//
-// voiceMap Handling //
-//###################//
-
-async function onChatChanged() {
-    await resetTtsPlayback();
-    const voiceMapInit = initVoiceMap();
-    await Promise.race([voiceMapInit, delay(1000)]);
-    ttsLastMessage = null;
-}
-
-async function onChatDeleted() {
-    const context = getContext();
-
-    // update internal references to new last message
-    lastChatId = context.chatId;
-    currentMessageNumber = context.chat.length ? context.chat.length : 0;
-
-    // compare against lastMessageHash. If it's the same, we did not delete the last chat item, so no need to reset tts queue
-    let messageHash = getStringHash((context.chat.length && context.chat[context.chat.length - 1].mes) ?? '');
-    if (messageHash === lastMessageHash) {
-        return;
-    }
-    lastMessageHash = messageHash;
-    ttsLastMessage = (context.chat.length && context.chat[context.chat.length - 1].mes) ?? '';
-
-    // stop any tts playback since message might not exist anymore
-    await resetTtsPlayback();
-}
-
-/**
- * Get characters in current chat
- * @param {boolean} unrestricted - If true, will include all characters in voiceMapEntries, even if they are not in the current chat.
- * @returns {string[]} - Array of character names
- */
-function getCharacters(unrestricted) {
-    const context = getContext();
-
-    if (unrestricted) {
-        const names = context.characters.map(char => char.name);
-        names.unshift(DEFAULT_VOICE_MARKER);
-        return names;
-    }
-
-    let characters = [];
-    if (context.groupId === null) {
-        // Single char chat
-        characters.push(DEFAULT_VOICE_MARKER);
-        characters.push(context.name1);
-        characters.push(context.name2);
-    } else {
-        // Group chat
-        characters.push(DEFAULT_VOICE_MARKER);
-        characters.push(context.name1);
-        const group = context.groups.find(group => context.groupId == group.id);
-        for (let member of group.members) {
-            // Remove suffix
-            if (member.endsWith('.png')) {
-                member = member.slice(0, -4);
-            }
-            characters.push(member);
-        }
-    }
-    return characters;
-}
-
-function sanitizeId(input) {
-    // Remove any non-alphanumeric characters except underscore (_) and hyphen (-)
-    let sanitized = input.replace(/[^a-zA-Z0-9-_]/g, '');
-
-    // Ensure first character is always a letter
-    if (!/^[a-zA-Z]/.test(sanitized)) {
-        sanitized = 'element_' + sanitized;
-    }
-
-    return sanitized;
-}
-
-function parseVoiceMap(voiceMapString) {
-    let parsedVoiceMap = {};
-    for (const [charName, voiceId] of voiceMapString
-        .split(',')
-        .map(s => s.split(':'))) {
-        if (charName && voiceId) {
-            parsedVoiceMap[charName.trim()] = voiceId.trim();
-        }
-    }
-    return parsedVoiceMap;
-}
-
-
-
-/**
- * Apply voiceMap based on current voiceMapEntries
- */
-function updateVoiceMap() {
-    const tempVoiceMap = {};
-    for (const voice of voiceMapEntries) {
-        if (voice.voiceId === null) {
-            continue;
-        }
-        tempVoiceMap[voice.name] = voice.voiceId;
-    }
-    if (Object.keys(tempVoiceMap).length !== 0) {
-        voiceMap = tempVoiceMap;
-        console.log(`Voicemap updated to ${JSON.stringify(voiceMap)}`);
-    }
-    if (!extension_settings.tts[ttsProviderName].voiceMap) {
-        extension_settings.tts[ttsProviderName].voiceMap = {};
-    }
-    Object.assign(extension_settings.tts[ttsProviderName].voiceMap, voiceMap);
-    saveSettingsDebounced();
-}
-
-class VoiceMapEntry {
-    name;
-    voiceId;
-    selectElement;
-    constructor(name, voiceId = DEFAULT_VOICE_MARKER) {
-        this.name = name;
-        this.voiceId = voiceId;
-        this.selectElement = null;
-    }
-
-    addUI(voiceIds) {
-        let sanitizedName = sanitizeId(this.name);
-        let defaultOption = this.name === DEFAULT_VOICE_MARKER ?
-            `<option>${DISABLED_VOICE_MARKER}</option>` :
-            `<option>${DEFAULT_VOICE_MARKER}</option><option>${DISABLED_VOICE_MARKER}</option>`;
-        let template = `
-            <div class='tts_voicemap_block_char flex-container flexGap5'>
-                <span id='tts_voicemap_char_${sanitizedName}'>${this.name}</span>
-                <select id='tts_voicemap_char_${sanitizedName}_voice'>
-                    ${defaultOption}
-                </select>
-            </div>
-        `;
-        $('#tts_voicemap_block').append(template);
-
-        // Populate voice ID select list
-        for (const voiceId of voiceIds) {
-            const option = document.createElement('option');
-            option.innerText = voiceId.name;
-            option.value = voiceId.name;
-            $(`#tts_voicemap_char_${sanitizedName}_voice`).append(option);
-        }
-
-        this.selectElement = $(`#tts_voicemap_char_${sanitizedName}_voice`);
-        this.selectElement.on('change', args => this.onSelectChange(args));
-        this.selectElement.val(this.voiceId);
-    }
-
-    onSelectChange(args) {
-        this.voiceId = this.selectElement.find(':selected').val();
-        updateVoiceMap();
-    }
-}
-
-/**
- * Init voiceMapEntries for character select list.
- * @param {boolean} unrestricted - If true, will include all characters in voiceMapEntries, even if they are not in the current chat.
- */
-export async function initVoiceMap(unrestricted = false) {
-    // Gate initialization if not enabled or TTS Provider not ready. Prevents error popups.
-    const enabled = $('#tts_enabled').is(':checked');
-    if (!enabled) {
-        return;
-    }
-
-    // Keep errors inside extension UI rather than toastr. Toastr errors for TTS are annoying.
-    try {
-        await ttsProvider.checkReady();
-    } catch (error) {
-        const message = `TTS Provider not ready. ${error}`;
-        setTtsStatus(message, false);
-        return;
-    }
-
-    setTtsStatus('TTS Provider Loaded', true);
-
-    // Clear existing voiceMap state
-    $('#tts_voicemap_block').empty();
-    voiceMapEntries = [];
-
-    // Get characters in current chat
-    const characters = getCharacters(unrestricted);
-
-    // Get saved voicemap from provider settings, handling new and old representations
-    let voiceMapFromSettings = {};
-    if ('voiceMap' in extension_settings.tts[ttsProviderName]) {
-        // Handle previous representation
-        if (typeof extension_settings.tts[ttsProviderName].voiceMap === 'string') {
-            voiceMapFromSettings = parseVoiceMap(extension_settings.tts[ttsProviderName].voiceMap);
-            // Handle new representation
-        } else if (typeof extension_settings.tts[ttsProviderName].voiceMap === 'object') {
-            voiceMapFromSettings = extension_settings.tts[ttsProviderName].voiceMap;
-        }
-    }
-
-    // Get voiceIds from provider
-    let voiceIdsFromProvider;
-    try {
-        voiceIdsFromProvider = await ttsProvider.fetchTtsVoiceObjects();
-    }
-    catch {
-        toastr.error('TTS Provider failed to return voice ids.');
-    }
-
-    // Build UI using VoiceMapEntry objects
-    for (const character of characters) {
-        if (character === 'SillyTavern System') {
-            continue;
-        }
-        // Check provider settings for voiceIds
-        let voiceId;
-        if (character in voiceMapFromSettings) {
-            voiceId = voiceMapFromSettings[character];
-        } else if (character === DEFAULT_VOICE_MARKER) {
-            voiceId = DISABLED_VOICE_MARKER;
-        } else {
-            voiceId = DEFAULT_VOICE_MARKER;
-        }
-        const voiceMapEntry = new VoiceMapEntry(character, voiceId);
-        voiceMapEntry.addUI(voiceIdsFromProvider);
-        voiceMapEntries.push(voiceMapEntry);
-    }
-    updateVoiceMap();
-}
-
-$(document).ready(function () {
-    function addExtensionControls() {
-        const settingsHtml = `
-        <div id="tts_settings">
-            <div class="inline-drawer">
-                <div class="inline-drawer-toggle inline-drawer-header">
-                    <b>TTS</b>
-                    <div class="inline-drawer-icon fa-solid fa-circle-chevron-down down"></div>
-                </div>
-                <div class="inline-drawer-content">
-                    <div id="tts_status">
-                    </div>
-                    <span>Select TTS Provider</span> </br>
-                    <div class="tts_block">
-                        <select id="tts_provider" class="flex1">
-                        </select>
-                        <input id="tts_refresh" class="menu_button" type="submit" value="Reload" />
-                    </div>
-                    <div>
-                        <label class="checkbox_label" for="tts_enabled">
-                            <input type="checkbox" id="tts_enabled" name="tts_enabled">
-                            <small>Enabled</small>
-                        </label>
-                        <label class="checkbox_label" for="tts_narrate_user">
-                            <input type="checkbox" id="tts_narrate_user">
-                            <small>Narrate user messages</small>
-                        </label>
-                        <label class="checkbox_label" for="tts_auto_generation">
-                            <input type="checkbox" id="tts_auto_generation">
-                            <small>Auto Generation</small>
-                        </label>
-                        <label class="checkbox_label" for="tts_narrate_quoted">
-                            <input type="checkbox" id="tts_narrate_quoted">
-                            <small>Only narrate "quotes"</small>
-                        </label>
-                        <label class="checkbox_label" for="tts_narrate_dialogues">
-                            <input type="checkbox" id="tts_narrate_dialogues">
-                            <small>Ignore *text, even "quotes", inside asterisks*</small>
-                        </label>
-                        <label class="checkbox_label" for="tts_narrate_translated_only">
-                            <input type="checkbox" id="tts_narrate_translated_only">
-                            <small>Narrate only the translated text</small>
-                        </label>
-                        <label class="checkbox_label" for="tts_skip_codeblocks">
-                            <input type="checkbox" id="tts_skip_codeblocks">
-                            <small>Skip codeblocks</small>
-                        </label>
-                        <label class="checkbox_label" for="tts_pass_asterisks">
-                        <input type="checkbox" id="tts_pass_asterisks">
-                        <small>Pass Asterisks to TTS Engine</small>
-                        </label>
-                    </div>
-                    <div id="tts_voicemap_block">
-                    </div>
-                    <hr>
-                    <form id="tts_provider_settings" class="inline-drawer-content">
-                    </form>
-                    <div class="tts_buttons">
-                        <input id="tts_voices" class="menu_button" type="submit" value="Available voices" />
-                    </div>
-                    </div>
-                </div>
-            </div>
-        </div>
-        `;
-        $('#extensions_settings').append(settingsHtml);
-        $('#tts_refresh').on('click', onRefreshClick);
-        $('#tts_enabled').on('click', onEnableClick);
-        $('#tts_narrate_dialogues').on('click', onNarrateDialoguesClick);
-        $('#tts_narrate_quoted').on('click', onNarrateQuotedClick);
-        $('#tts_narrate_translated_only').on('click', onNarrateTranslatedOnlyClick);
-        $('#tts_skip_codeblocks').on('click', onSkipCodeblocksClick);
-        $('#tts_pass_asterisks').on('click', onPassAsterisksClick);
-        $('#tts_auto_generation').on('click', onAutoGenerationClick);
-        $('#tts_narrate_user').on('click', onNarrateUserClick);
-        $('#tts_voices').on('click', onTtsVoicesClick);
-        for (const provider in ttsProviders) {
-            $('#tts_provider').append($('<option />').val(provider).text(provider));
-        }
-        $('#tts_provider').on('change', onTtsProviderChange);
-        $(document).on('click', '.mes_narrate', onNarrateOneMessage);
-    }
-    addExtensionControls(); // No init dependencies
-    loadSettings(); // Depends on Extension Controls and loadTtsProvider
-    loadTtsProvider(extension_settings.tts.currentProvider); // No dependencies
-    addAudioControl(); // Depends on Extension Controls
-    const wrapper = new ModuleWorkerWrapper(moduleWorker);
-    setInterval(wrapper.update.bind(wrapper), UPDATE_INTERVAL); // Init depends on all the things
-    eventSource.on(event_types.MESSAGE_SWIPED, resetTtsPlayback);
-    eventSource.on(event_types.CHAT_CHANGED, onChatChanged);
-    eventSource.on(event_types.MESSAGE_DELETED, onChatDeleted);
-    eventSource.on(event_types.GROUP_UPDATED, onChatChanged);
-    registerSlashCommand('speak', onNarrateText, ['narrate', 'tts'], '<span class="monospace">(text)</span>  – narrate any text using currently selected character\'s voice. Use voice="Character Name" argument to set other voice from the voice map, example: <tt>/speak voice="Donald Duck" Quack!</tt>', true, true);
-    document.body.appendChild(audioElement);
-});
+import { callPopup, cancelTtsPlay, eventSource, event_types, name2, saveSettingsDebounced } from '../../../script.js';
+import { ModuleWorkerWrapper, doExtrasFetch, extension_settings, getApiUrl, getContext, modules } from '../../extensions.js';
+import { delay, escapeRegex, getBase64Async, getStringHash, onlyUnique } from '../../utils.js';
+import { EdgeTtsProvider } from './edge.js';
+import { ElevenLabsTtsProvider } from './elevenlabs.js';
+import { SileroTtsProvider } from './silerotts.js';
+import { CoquiTtsProvider } from './coqui.js';
+import { SystemTtsProvider } from './system.js';
+import { NovelTtsProvider } from './novel.js';
+import { power_user } from '../../power-user.js';
+import { registerSlashCommand } from '../../slash-commands.js';
+import { OpenAITtsProvider } from './openai.js';
+import { XTTSTtsProvider } from './xtts.js';
+import { AllTalkTtsProvider } from './alltalk.js';
+export { talkingAnimation };
+
+const UPDATE_INTERVAL = 1000;
+
+let voiceMapEntries = [];
+let voiceMap = {}; // {charName:voiceid, charName2:voiceid2}
+let storedvalue = false;
+let lastChatId = null;
+let lastMessageHash = null;
+
+const DEFAULT_VOICE_MARKER = '[Default Voice]';
+const DISABLED_VOICE_MARKER = 'disabled';
+
+export function getPreviewString(lang) {
+    const previewStrings = {
+        'en-US': 'The quick brown fox jumps over the lazy dog',
+        'en-GB': 'Sphinx of black quartz, judge my vow',
+        'fr-FR': 'Portez ce vieux whisky au juge blond qui fume',
+        'de-DE': 'Victor jagt zwölf Boxkämpfer quer über den großen Sylter Deich',
+        'it-IT': 'Pranzo d\'acqua fa volti sghembi',
+        'es-ES': 'Quiere la boca exhausta vid, kiwi, piña y fugaz jamón',
+        'es-MX': 'Fabio me exige, sin tapujos, que añada cerveza al whisky',
+        'ru-RU': 'В чащах юга жил бы цитрус? Да, но фальшивый экземпляр!',
+        'pt-BR': 'Vejo xá gritando que fez show sem playback.',
+        'pt-PR': 'Todo pajé vulgar faz boquinha sexy com kiwi.',
+        'uk-UA': 'Фабрикуймо гідність, лящім їжею, ґав хапаймо, з\'єднавці чаш!',
+        'pl-PL': 'Pchnąć w tę łódź jeża lub ośm skrzyń fig',
+        'cs-CZ': 'Příliš žluťoučký kůň úpěl ďábelské ódy',
+        'sk-SK': 'Vyhŕňme si rukávy a vyprážajme čínske ryžové cestoviny',
+        'hu-HU': 'Árvíztűrő tükörfúrógép',
+        'tr-TR': 'Pijamalı hasta yağız şoföre çabucak güvendi',
+        'nl-NL': 'De waard heeft een kalfje en een pinkje opgegeten',
+        'sv-SE': 'Yxskaftbud, ge vårbygd, zinkqvarn',
+        'da-DK': 'Quizdeltagerne spiste jordbær med fløde, mens cirkusklovnen Walther spillede på xylofon',
+        'ja-JP': 'いろはにほへと　ちりぬるを　わかよたれそ　つねならむ　うゐのおくやま　けふこえて　あさきゆめみし　ゑひもせす',
+        'ko-KR': '가나다라마바사아자차카타파하',
+        'zh-CN': '我能吞下玻璃而不伤身体',
+        'ro-RO': 'Muzicologă în bej vând whisky și tequila, preț fix',
+        'bg-BG': 'Щъркелите се разпръснаха по цялото небе',
+        'el-GR': 'Ταχίστη αλώπηξ βαφής ψημένη γη, δρασκελίζει υπέρ νωθρού κυνός',
+        'fi-FI': 'Voi veljet, miksi juuri teille myin nämä vehkeet?',
+        'he-IL': 'הקצינים צעקו: "כל הכבוד לצבא הצבאות!"',
+        'id-ID': 'Jangkrik itu memang enak, apalagi kalau digoreng',
+        'ms-MY': 'Muzik penyanyi wanita itu menggambarkan kehidupan yang penuh dengan duka nestapa',
+        'th-TH': 'เป็นไงบ้างครับ ผมชอบกินข้าวผัดกระเพราหมูกรอบ',
+        'vi-VN': 'Cô bé quàng khăn đỏ đang ngồi trên bãi cỏ xanh',
+        'ar-SA': 'أَبْجَدِيَّة عَرَبِيَّة',
+        'hi-IN': 'श्वेता ने श्वेता के श्वेते हाथों में श्वेता का श्वेता चावल पकड़ा',
+    };
+    const fallbackPreview = 'Neque porro quisquam est qui dolorem ipsum quia dolor sit amet';
+
+    return previewStrings[lang] ?? fallbackPreview;
+}
+
+let ttsProviders = {
+    ElevenLabs: ElevenLabsTtsProvider,
+    Silero: SileroTtsProvider,
+    XTTSv2: XTTSTtsProvider,
+    System: SystemTtsProvider,
+    Coqui: CoquiTtsProvider,
+    Edge: EdgeTtsProvider,
+    Novel: NovelTtsProvider,
+    OpenAI: OpenAITtsProvider,
+    AllTalk: AllTalkTtsProvider,
+};
+let ttsProvider;
+let ttsProviderName;
+
+let ttsLastMessage = null;
+
+async function onNarrateOneMessage() {
+    audioElement.src = '/sounds/silence.mp3';
+    const context = getContext();
+    const id = $(this).closest('.mes').attr('mesid');
+    const message = context.chat[id];
+
+    if (!message) {
+        return;
+    }
+
+    resetTtsPlayback();
+    ttsJobQueue.push(message);
+    moduleWorker();
+}
+
+async function onNarrateText(args, text) {
+    if (!text) {
+        return;
+    }
+
+    audioElement.src = '/sounds/silence.mp3';
+
+    // To load all characters in the voice map, set unrestricted to true
+    await initVoiceMap(true);
+
+    const baseName = args?.voice || name2;
+    const name = (baseName === 'SillyTavern System' ? DEFAULT_VOICE_MARKER : baseName) || DEFAULT_VOICE_MARKER;
+
+    const voiceMapEntry = voiceMap[name] === DEFAULT_VOICE_MARKER
+        ? voiceMap[DEFAULT_VOICE_MARKER]
+        : voiceMap[name];
+
+    if (!voiceMapEntry || voiceMapEntry === DISABLED_VOICE_MARKER) {
+        toastr.info(`Specified voice for ${name} was not found. Check the TTS extension settings.`);
+        return;
+    }
+
+    resetTtsPlayback();
+    ttsJobQueue.push({ mes: text, name: name });
+    await moduleWorker();
+
+    // Return back to the chat voices
+    await initVoiceMap(false);
+}
+
+async function moduleWorker() {
+    // Primarily determining when to add new chat to the TTS queue
+    const enabled = $('#tts_enabled').is(':checked');
+    $('body').toggleClass('tts', enabled);
+    if (!enabled) {
+        return;
+    }
+
+    const context = getContext();
+    const chat = context.chat;
+
+    processTtsQueue();
+    processAudioJobQueue();
+    updateUiAudioPlayState();
+
+    // Auto generation is disabled
+    if (extension_settings.tts.auto_generation == false) {
+        return;
+    }
+
+    // no characters or group selected
+    if (!context.groupId && context.characterId === undefined) {
+        return;
+    }
+
+    // Chat changed
+    if (
+        context.chatId !== lastChatId
+    ) {
+        currentMessageNumber = context.chat.length ? context.chat.length : 0;
+        saveLastValues();
+
+        // Force to speak on the first message in the new chat
+        if (context.chat.length === 1) {
+            lastMessageHash = -1;
+        }
+
+        return;
+    }
+
+    // take the count of messages
+    let lastMessageNumber = context.chat.length ? context.chat.length : 0;
+
+    // There's no new messages
+    let diff = lastMessageNumber - currentMessageNumber;
+    let hashNew = getStringHash((chat.length && chat[chat.length - 1].mes) ?? '');
+
+    // if messages got deleted, diff will be < 0
+    if (diff < 0) {
+        // necessary actions will be taken by the onChatDeleted() handler
+        return;
+    }
+
+    // if no new messages, or same message, or same message hash, do nothing
+    if (diff == 0 && hashNew === lastMessageHash) {
+        return;
+    }
+
+    // If streaming, wait for streaming to finish before processing new messages
+    if (context.streamingProcessor && !context.streamingProcessor.isFinished) {
+        return;
+    }
+
+    // clone message object, as things go haywire if message object is altered below (it's passed by reference)
+    const message = structuredClone(chat[chat.length - 1]);
+
+    // if last message within current message, message got extended. only send diff to TTS.
+    if (ttsLastMessage !== null && message.mes.indexOf(ttsLastMessage) !== -1) {
+        let tmp = message.mes;
+        message.mes = message.mes.replace(ttsLastMessage, '');
+        ttsLastMessage = tmp;
+    } else {
+        ttsLastMessage = message.mes;
+    }
+
+    // We're currently swiping. Don't generate voice
+    if (!message || message.mes === '...' || message.mes === '') {
+        return;
+    }
+
+    // Don't generate if message doesn't have a display text
+    if (extension_settings.tts.narrate_translated_only && !(message?.extra?.display_text)) {
+        return;
+    }
+
+    // Don't generate if message is a user message and user message narration is disabled
+    if (message.is_user && !extension_settings.tts.narrate_user) {
+        return;
+    }
+
+    // New messages, add new chat to history
+    lastMessageHash = hashNew;
+    currentMessageNumber = lastMessageNumber;
+
+    console.debug(
+        `Adding message from ${message.name} for TTS processing: "${message.mes}"`,
+    );
+    ttsJobQueue.push(message);
+}
+
+function talkingAnimation(switchValue) {
+    if (!modules.includes('talkinghead')) {
+        console.debug('Talking Animation module not loaded');
+        return;
+    }
+
+    const apiUrl = getApiUrl();
+    const animationType = switchValue ? 'start' : 'stop';
+
+    if (switchValue !== storedvalue) {
+        try {
+            console.log(animationType + ' Talking Animation');
+            doExtrasFetch(`${apiUrl}/api/talkinghead/${animationType}_talking`);
+            storedvalue = switchValue; // Update the storedvalue to the current switchValue
+        } catch (error) {
+            // Handle the error here or simply ignore it to prevent logging
+        }
+    }
+    updateUiAudioPlayState();
+}
+
+function resetTtsPlayback() {
+    // Stop system TTS utterance
+    cancelTtsPlay();
+
+    // Clear currently processing jobs
+    currentTtsJob = null;
+    currentAudioJob = null;
+
+    // Reset audio element
+    audioElement.currentTime = 0;
+    audioElement.src = '';
+
+    // Clear any queue items
+    ttsJobQueue.splice(0, ttsJobQueue.length);
+    audioJobQueue.splice(0, audioJobQueue.length);
+
+    // Set audio ready to process again
+    audioQueueProcessorReady = true;
+}
+
+function isTtsProcessing() {
+    let processing = false;
+
+    // Check job queues
+    if (ttsJobQueue.length > 0 || audioJobQueue.length > 0) {
+        processing = true;
+    }
+    // Check current jobs
+    if (currentTtsJob != null || currentAudioJob != null) {
+        processing = true;
+    }
+    return processing;
+}
+
+function debugTtsPlayback() {
+    console.log(JSON.stringify(
+        {
+            'ttsProviderName': ttsProviderName,
+            'voiceMap': voiceMap,
+            'currentMessageNumber': currentMessageNumber,
+            'audioPaused': audioPaused,
+            'audioJobQueue': audioJobQueue,
+            'currentAudioJob': currentAudioJob,
+            'audioQueueProcessorReady': audioQueueProcessorReady,
+            'ttsJobQueue': ttsJobQueue,
+            'currentTtsJob': currentTtsJob,
+            'ttsConfig': extension_settings.tts,
+        },
+    ));
+}
+window.debugTtsPlayback = debugTtsPlayback;
+
+//##################//
+//   Audio Control  //
+//##################//
+
+let audioElement = new Audio();
+audioElement.id = 'tts_audio';
+audioElement.autoplay = true;
+
+let audioJobQueue = [];
+let currentAudioJob;
+let audioPaused = false;
+let audioQueueProcessorReady = true;
+
+async function playAudioData(audioBlob) {
+    // Since current audio job can be cancelled, don't playback if it is null
+    if (currentAudioJob == null) {
+        console.log('Cancelled TTS playback because currentAudioJob was null');
+    }
+    if (audioBlob instanceof Blob) {
+        const srcUrl = await getBase64Async(audioBlob);
+        audioElement.src = srcUrl;
+    } else if (typeof audioBlob === 'string') {
+        audioElement.src = audioBlob;
+    } else {
+        throw `TTS received invalid audio data type ${typeof audioBlob}`;
+    }
+    audioElement.addEventListener('ended', completeCurrentAudioJob);
+    audioElement.addEventListener('canplay', () => {
+        console.debug('Starting TTS playback');
+        audioElement.play();
+    });
+}
+
+window['tts_preview'] = function (id) {
+    const audio = document.getElementById(id);
+
+    if (audio && !$(audio).data('disabled')) {
+        audio.play();
+    }
+    else {
+        ttsProvider.previewTtsVoice(id);
+    }
+};
+
+async function onTtsVoicesClick() {
+    let popupText = '';
+
+    try {
+        const voiceIds = await ttsProvider.fetchTtsVoiceObjects();
+
+        for (const voice of voiceIds) {
+            popupText += `
+            <div class="voice_preview">
+                <span class="voice_lang">${voice.lang || ''}</span>
+                <b class="voice_name">${voice.name}</b>
+                <i onclick="tts_preview('${voice.voice_id}')" class="fa-solid fa-play"></i>
+            </div>`;
+            if (voice.preview_url) {
+                popupText += `<audio id="${voice.voice_id}" src="${voice.preview_url}" data-disabled="${voice.preview_url == false}"></audio>`;
+            }
+        }
+    } catch {
+        popupText = 'Could not load voices list. Check your API key.';
+    }
+
+    callPopup(popupText, 'text');
+}
+
+function updateUiAudioPlayState() {
+    if (extension_settings.tts.enabled == true) {
+        $('#ttsExtensionMenuItem').show();
+        let img;
+        // Give user feedback that TTS is active by setting the stop icon if processing or playing
+        if (!audioElement.paused || isTtsProcessing()) {
+            img = 'fa-solid fa-stop-circle extensionsMenuExtensionButton';
+        } else {
+            img = 'fa-solid fa-circle-play extensionsMenuExtensionButton';
+        }
+        $('#tts_media_control').attr('class', img);
+    } else {
+        $('#ttsExtensionMenuItem').hide();
+    }
+}
+
+function onAudioControlClicked() {
+    audioElement.src = '/sounds/silence.mp3';
+    let context = getContext();
+    // Not pausing, doing a full stop to anything TTS is doing. Better UX as pause is not as useful
+    if (!audioElement.paused || isTtsProcessing()) {
+        resetTtsPlayback();
+        talkingAnimation(false);
+    } else {
+        // Default play behavior if not processing or playing is to play the last message.
+        ttsJobQueue.push(context.chat[context.chat.length - 1]);
+    }
+    updateUiAudioPlayState();
+}
+
+function addAudioControl() {
+
+    $('#extensionsMenu').prepend(`
+        <div id="ttsExtensionMenuItem" class="list-group-item flex-container flexGap5">
+            <div id="tts_media_control" class="extensionsMenuExtensionButton "/></div>
+            TTS Playback
+        </div>`);
+    $('#ttsExtensionMenuItem').attr('title', 'TTS play/pause').on('click', onAudioControlClicked);
+    updateUiAudioPlayState();
+}
+
+function completeCurrentAudioJob() {
+    audioQueueProcessorReady = true;
+    currentAudioJob = null;
+    talkingAnimation(false); //stop lip animation
+    // updateUiPlayState();
+}
+
+/**
+ * Accepts an HTTP response containing audio/mpeg data, and puts the data as a Blob() on the queue for playback
+ * @param {Response} response
+ */
+async function addAudioJob(response) {
+    if (typeof response === 'string') {
+        audioJobQueue.push(response);
+    } else {
+        const audioData = await response.blob();
+        if (!audioData.type.startsWith('audio/')) {
+            throw `TTS received HTTP response with invalid data format. Expecting audio/*, got ${audioData.type}`;
+        }
+        audioJobQueue.push(audioData);
+    }
+    console.debug('Pushed audio job to queue.');
+}
+
+async function processAudioJobQueue() {
+    // Nothing to do, audio not completed, or audio paused - stop processing.
+    if (audioJobQueue.length == 0 || !audioQueueProcessorReady || audioPaused) {
+        return;
+    }
+    try {
+        audioQueueProcessorReady = false;
+        currentAudioJob = audioJobQueue.shift();
+        playAudioData(currentAudioJob);
+        talkingAnimation(true);
+    } catch (error) {
+        console.error(error);
+        audioQueueProcessorReady = true;
+    }
+}
+
+//################//
+//  TTS Control   //
+//################//
+
+let ttsJobQueue = [];
+let currentTtsJob; // Null if nothing is currently being processed
+let currentMessageNumber = 0;
+
+function completeTtsJob() {
+    console.info(`Current TTS job for ${currentTtsJob?.name} completed.`);
+    currentTtsJob = null;
+}
+
+function saveLastValues() {
+    const context = getContext();
+    lastChatId = context.chatId;
+    lastMessageHash = getStringHash(
+        (context.chat.length && context.chat[context.chat.length - 1].mes) ?? '',
+    );
+}
+
+async function tts(text, voiceId, char) {
+    async function processResponse(response) {
+        // RVC injection
+        if (extension_settings.rvc.enabled && typeof window['rvcVoiceConversion'] === 'function')
+            response = await window['rvcVoiceConversion'](response, char, text);
+
+        await addAudioJob(response);
+    }
+
+    let response = await ttsProvider.generateTts(text, voiceId);
+
+    // If async generator, process every chunk as it comes in
+    if (typeof response[Symbol.asyncIterator] === 'function') {
+        for await (const chunk of response) {
+            await processResponse(chunk);
+        }
+    } else {
+        await processResponse(response);
+    }
+
+    completeTtsJob();
+}
+
+async function processTtsQueue() {
+    // Called each moduleWorker iteration to pull chat messages from queue
+    if (currentTtsJob || ttsJobQueue.length <= 0 || audioPaused) {
+        return;
+    }
+
+    console.debug('New message found, running TTS');
+    currentTtsJob = ttsJobQueue.shift();
+    let text = extension_settings.tts.narrate_translated_only ? (currentTtsJob?.extra?.display_text || currentTtsJob.mes) : currentTtsJob.mes;
+
+    if (extension_settings.tts.skip_codeblocks) {
+        text = text.replace(/^\s{4}.*$/gm, '').trim();
+        text = text.replace(/```.*?```/gs, '').trim();
+    }
+
+    if (!extension_settings.tts.pass_asterisks) {
+        text = extension_settings.tts.narrate_dialogues_only
+            ? text.replace(/\*[^*]*?(\*|$)/g, '').trim() // remove asterisks content
+            : text.replaceAll('*', '').trim(); // remove just the asterisks
+    }
+
+    if (extension_settings.tts.narrate_quoted_only) {
+        const special_quotes = /[“”]/g; // Extend this regex to include other special quotes
+        text = text.replace(special_quotes, '"');
+        const matches = text.match(/".*?"/g); // Matches text inside double quotes, non-greedily
+        const partJoiner = (ttsProvider?.separator || ' ... ');
+        text = matches ? matches.join(partJoiner) : text;
+    }
+
+    if (typeof ttsProvider?.processText === 'function') {
+        text = await ttsProvider.processText(text);
+    }
+
+    // Collapse newlines and spaces into single space
+    text = text.replace(/\s+/g, ' ').trim();
+
+    console.log(`TTS: ${text}`);
+    const char = currentTtsJob.name;
+
+    // Remove character name from start of the line if power user setting is disabled
+    if (char && !power_user.allow_name2_display) {
+        const escapedChar = escapeRegex(char);
+        text = text.replace(new RegExp(`^${escapedChar}:`, 'gm'), '');
+    }
+
+    try {
+        if (!text) {
+            console.warn('Got empty text in TTS queue job.');
+            completeTtsJob();
+            return;
+        }
+
+        const voiceMapEntry = voiceMap[char] === DEFAULT_VOICE_MARKER ? voiceMap[DEFAULT_VOICE_MARKER] : voiceMap[char];
+
+        if (!voiceMapEntry || voiceMapEntry === DISABLED_VOICE_MARKER) {
+            throw `${char} not in voicemap. Configure character in extension settings voice map`;
+        }
+        const voice = await ttsProvider.getVoice(voiceMapEntry);
+        const voiceId = voice.voice_id;
+        if (voiceId == null) {
+            toastr.error(`Specified voice for ${char} was not found. Check the TTS extension settings.`);
+            throw `Unable to attain voiceId for ${char}`;
+        }
+        tts(text, voiceId, char);
+    } catch (error) {
+        console.error(error);
+        currentTtsJob = null;
+    }
+}
+
+// Secret function for now
+async function playFullConversation() {
+    const context = getContext();
+    const chat = context.chat;
+    ttsJobQueue = chat;
+}
+window.playFullConversation = playFullConversation;
+
+//#############################//
+//  Extension UI and Settings  //
+//#############################//
+
+function loadSettings() {
+    if (Object.keys(extension_settings.tts).length === 0) {
+        Object.assign(extension_settings.tts, defaultSettings);
+    }
+    for (const key in defaultSettings) {
+        if (!(key in extension_settings.tts)) {
+            extension_settings.tts[key] = defaultSettings[key];
+        }
+    }
+    $('#tts_provider').val(extension_settings.tts.currentProvider);
+    $('#tts_enabled').prop(
+        'checked',
+        extension_settings.tts.enabled,
+    );
+    $('#tts_narrate_dialogues').prop('checked', extension_settings.tts.narrate_dialogues_only);
+    $('#tts_narrate_quoted').prop('checked', extension_settings.tts.narrate_quoted_only);
+    $('#tts_auto_generation').prop('checked', extension_settings.tts.auto_generation);
+    $('#tts_narrate_translated_only').prop('checked', extension_settings.tts.narrate_translated_only);
+    $('#tts_narrate_user').prop('checked', extension_settings.tts.narrate_user);
+    $('#tts_pass_asterisks').prop('checked', extension_settings.tts.pass_asterisks);
+    $('body').toggleClass('tts', extension_settings.tts.enabled);
+}
+
+const defaultSettings = {
+    voiceMap: '',
+    ttsEnabled: false,
+    currentProvider: 'ElevenLabs',
+    auto_generation: true,
+    narrate_user: false,
+};
+
+function setTtsStatus(status, success) {
+    $('#tts_status').text(status);
+    if (success) {
+        $('#tts_status').removeAttr('style');
+    } else {
+        $('#tts_status').css('color', 'red');
+    }
+}
+
+function onRefreshClick() {
+    Promise.all([
+        ttsProvider.onRefreshClick(),
+        // updateVoiceMap()
+    ]).then(() => {
+        extension_settings.tts[ttsProviderName] = ttsProvider.settings;
+        saveSettingsDebounced();
+        setTtsStatus('Successfully applied settings', true);
+        console.info(`Saved settings ${ttsProviderName} ${JSON.stringify(ttsProvider.settings)}`);
+        initVoiceMap();
+        updateVoiceMap();
+    }).catch(error => {
+        console.error(error);
+        setTtsStatus(error, false);
+    });
+}
+
+function onEnableClick() {
+    extension_settings.tts.enabled = $('#tts_enabled').is(
+        ':checked',
+    );
+    updateUiAudioPlayState();
+    saveSettingsDebounced();
+}
+
+
+function onAutoGenerationClick() {
+    extension_settings.tts.auto_generation = !!$('#tts_auto_generation').prop('checked');
+    saveSettingsDebounced();
+}
+
+
+function onNarrateDialoguesClick() {
+    extension_settings.tts.narrate_dialogues_only = !!$('#tts_narrate_dialogues').prop('checked');
+    saveSettingsDebounced();
+}
+
+function onNarrateUserClick() {
+    extension_settings.tts.narrate_user = !!$('#tts_narrate_user').prop('checked');
+    saveSettingsDebounced();
+}
+
+function onNarrateQuotedClick() {
+    extension_settings.tts.narrate_quoted_only = !!$('#tts_narrate_quoted').prop('checked');
+    saveSettingsDebounced();
+}
+
+
+function onNarrateTranslatedOnlyClick() {
+    extension_settings.tts.narrate_translated_only = !!$('#tts_narrate_translated_only').prop('checked');
+    saveSettingsDebounced();
+}
+
+function onSkipCodeblocksClick() {
+    extension_settings.tts.skip_codeblocks = !!$('#tts_skip_codeblocks').prop('checked');
+    saveSettingsDebounced();
+}
+
+function onPassAsterisksClick() {
+    extension_settings.tts.pass_asterisks = !!$('#tts_pass_asterisks').prop('checked');
+    saveSettingsDebounced();
+    console.log("setting pass asterisks", extension_settings.tts.pass_asterisks)
+}
+
+//##############//
+// TTS Provider //
+//##############//
+
+async function loadTtsProvider(provider) {
+    //Clear the current config and add new config
+    $('#tts_provider_settings').html('');
+
+    if (!provider) {
+        return;
+    }
+
+    // Init provider references
+    extension_settings.tts.currentProvider = provider;
+    ttsProviderName = provider;
+    ttsProvider = new ttsProviders[provider];
+
+    // Init provider settings
+    $('#tts_provider_settings').append(ttsProvider.settingsHtml);
+    if (!(ttsProviderName in extension_settings.tts)) {
+        console.warn(`Provider ${ttsProviderName} not in Extension Settings, initiatilizing provider in settings`);
+        extension_settings.tts[ttsProviderName] = {};
+    }
+    await ttsProvider.loadSettings(extension_settings.tts[ttsProviderName]);
+    await initVoiceMap();
+}
+
+function onTtsProviderChange() {
+    const ttsProviderSelection = $('#tts_provider').val();
+    extension_settings.tts.currentProvider = ttsProviderSelection;
+    loadTtsProvider(ttsProviderSelection);
+}
+
+// Ensure that TTS provider settings are saved to extension settings.
+export function saveTtsProviderSettings() {
+    extension_settings.tts[ttsProviderName] = ttsProvider.settings;
+    updateVoiceMap();
+    saveSettingsDebounced();
+    console.info(`Saved settings ${ttsProviderName} ${JSON.stringify(ttsProvider.settings)}`);
+}
+
+
+//###################//
+// voiceMap Handling //
+//###################//
+
+async function onChatChanged() {
+    await resetTtsPlayback();
+    const voiceMapInit = initVoiceMap();
+    await Promise.race([voiceMapInit, delay(1000)]);
+    ttsLastMessage = null;
+}
+
+async function onChatDeleted() {
+    const context = getContext();
+
+    // update internal references to new last message
+    lastChatId = context.chatId;
+    currentMessageNumber = context.chat.length ? context.chat.length : 0;
+
+    // compare against lastMessageHash. If it's the same, we did not delete the last chat item, so no need to reset tts queue
+    let messageHash = getStringHash((context.chat.length && context.chat[context.chat.length - 1].mes) ?? '');
+    if (messageHash === lastMessageHash) {
+        return;
+    }
+    lastMessageHash = messageHash;
+    ttsLastMessage = (context.chat.length && context.chat[context.chat.length - 1].mes) ?? '';
+
+    // stop any tts playback since message might not exist anymore
+    await resetTtsPlayback();
+}
+
+/**
+ * Get characters in current chat
+ * @param {boolean} unrestricted - If true, will include all characters in voiceMapEntries, even if they are not in the current chat.
+ * @returns {string[]} - Array of character names
+ */
+function getCharacters(unrestricted) {
+    const context = getContext();
+
+    if (unrestricted) {
+        const names = context.characters.map(char => char.name);
+        names.unshift(DEFAULT_VOICE_MARKER);
+        return names.filter(onlyUnique);
+    }
+
+    let characters = [];
+    if (context.groupId === null) {
+        // Single char chat
+        characters.push(DEFAULT_VOICE_MARKER);
+        characters.push(context.name1);
+        characters.push(context.name2);
+    } else {
+        // Group chat
+        characters.push(DEFAULT_VOICE_MARKER);
+        characters.push(context.name1);
+        const group = context.groups.find(group => context.groupId == group.id);
+        for (let member of group.members) {
+            const character = context.characters.find(char => char.avatar == member);
+            if (character) {
+                characters.push(character.name);
+            }
+        }
+    }
+    return characters.filter(onlyUnique);
+}
+
+function sanitizeId(input) {
+    // Remove any non-alphanumeric characters except underscore (_) and hyphen (-)
+    let sanitized = input.replace(/[^a-zA-Z0-9-_]/g, '');
+
+    // Ensure first character is always a letter
+    if (!/^[a-zA-Z]/.test(sanitized)) {
+        sanitized = 'element_' + sanitized;
+    }
+
+    return sanitized;
+}
+
+function parseVoiceMap(voiceMapString) {
+    let parsedVoiceMap = {};
+    for (const [charName, voiceId] of voiceMapString
+        .split(',')
+        .map(s => s.split(':'))) {
+        if (charName && voiceId) {
+            parsedVoiceMap[charName.trim()] = voiceId.trim();
+        }
+    }
+    return parsedVoiceMap;
+}
+
+
+
+/**
+ * Apply voiceMap based on current voiceMapEntries
+ */
+function updateVoiceMap() {
+    const tempVoiceMap = {};
+    for (const voice of voiceMapEntries) {
+        if (voice.voiceId === null) {
+            continue;
+        }
+        tempVoiceMap[voice.name] = voice.voiceId;
+    }
+    if (Object.keys(tempVoiceMap).length !== 0) {
+        voiceMap = tempVoiceMap;
+        console.log(`Voicemap updated to ${JSON.stringify(voiceMap)}`);
+    }
+    if (!extension_settings.tts[ttsProviderName].voiceMap) {
+        extension_settings.tts[ttsProviderName].voiceMap = {};
+    }
+    Object.assign(extension_settings.tts[ttsProviderName].voiceMap, voiceMap);
+    saveSettingsDebounced();
+}
+
+class VoiceMapEntry {
+    name;
+    voiceId;
+    selectElement;
+    constructor(name, voiceId = DEFAULT_VOICE_MARKER) {
+        this.name = name;
+        this.voiceId = voiceId;
+        this.selectElement = null;
+    }
+
+    addUI(voiceIds) {
+        let sanitizedName = sanitizeId(this.name);
+        let defaultOption = this.name === DEFAULT_VOICE_MARKER ?
+            `<option>${DISABLED_VOICE_MARKER}</option>` :
+            `<option>${DEFAULT_VOICE_MARKER}</option><option>${DISABLED_VOICE_MARKER}</option>`;
+        let template = `
+            <div class='tts_voicemap_block_char flex-container flexGap5'>
+                <span id='tts_voicemap_char_${sanitizedName}'>${this.name}</span>
+                <select id='tts_voicemap_char_${sanitizedName}_voice'>
+                    ${defaultOption}
+                </select>
+            </div>
+        `;
+        $('#tts_voicemap_block').append(template);
+
+        // Populate voice ID select list
+        for (const voiceId of voiceIds) {
+            const option = document.createElement('option');
+            option.innerText = voiceId.name;
+            option.value = voiceId.name;
+            $(`#tts_voicemap_char_${sanitizedName}_voice`).append(option);
+        }
+
+        this.selectElement = $(`#tts_voicemap_char_${sanitizedName}_voice`);
+        this.selectElement.on('change', args => this.onSelectChange(args));
+        this.selectElement.val(this.voiceId);
+    }
+
+    onSelectChange(args) {
+        this.voiceId = this.selectElement.find(':selected').val();
+        updateVoiceMap();
+    }
+}
+
+/**
+ * Init voiceMapEntries for character select list.
+ * @param {boolean} unrestricted - If true, will include all characters in voiceMapEntries, even if they are not in the current chat.
+ */
+export async function initVoiceMap(unrestricted = false) {
+    // Gate initialization if not enabled or TTS Provider not ready. Prevents error popups.
+    const enabled = $('#tts_enabled').is(':checked');
+    if (!enabled) {
+        return;
+    }
+
+    // Keep errors inside extension UI rather than toastr. Toastr errors for TTS are annoying.
+    try {
+        await ttsProvider.checkReady();
+    } catch (error) {
+        const message = `TTS Provider not ready. ${error}`;
+        setTtsStatus(message, false);
+        return;
+    }
+
+    setTtsStatus('TTS Provider Loaded', true);
+
+    // Clear existing voiceMap state
+    $('#tts_voicemap_block').empty();
+    voiceMapEntries = [];
+
+    // Get characters in current chat
+    const characters = getCharacters(unrestricted);
+
+    // Get saved voicemap from provider settings, handling new and old representations
+    let voiceMapFromSettings = {};
+    if ('voiceMap' in extension_settings.tts[ttsProviderName]) {
+        // Handle previous representation
+        if (typeof extension_settings.tts[ttsProviderName].voiceMap === 'string') {
+            voiceMapFromSettings = parseVoiceMap(extension_settings.tts[ttsProviderName].voiceMap);
+            // Handle new representation
+        } else if (typeof extension_settings.tts[ttsProviderName].voiceMap === 'object') {
+            voiceMapFromSettings = extension_settings.tts[ttsProviderName].voiceMap;
+        }
+    }
+
+    // Get voiceIds from provider
+    let voiceIdsFromProvider;
+    try {
+        voiceIdsFromProvider = await ttsProvider.fetchTtsVoiceObjects();
+    }
+    catch {
+        toastr.error('TTS Provider failed to return voice ids.');
+    }
+
+    // Build UI using VoiceMapEntry objects
+    for (const character of characters) {
+        if (character === 'SillyTavern System') {
+            continue;
+        }
+        // Check provider settings for voiceIds
+        let voiceId;
+        if (character in voiceMapFromSettings) {
+            voiceId = voiceMapFromSettings[character];
+        } else if (character === DEFAULT_VOICE_MARKER) {
+            voiceId = DISABLED_VOICE_MARKER;
+        } else {
+            voiceId = DEFAULT_VOICE_MARKER;
+        }
+        const voiceMapEntry = new VoiceMapEntry(character, voiceId);
+        voiceMapEntry.addUI(voiceIdsFromProvider);
+        voiceMapEntries.push(voiceMapEntry);
+    }
+    updateVoiceMap();
+}
+
+$(document).ready(function () {
+    function addExtensionControls() {
+        const settingsHtml = `
+        <div id="tts_settings">
+            <div class="inline-drawer">
+                <div class="inline-drawer-toggle inline-drawer-header">
+                    <b>TTS</b>
+                    <div class="inline-drawer-icon fa-solid fa-circle-chevron-down down"></div>
+                </div>
+                <div class="inline-drawer-content">
+                    <div id="tts_status">
+                    </div>
+                    <span>Select TTS Provider</span> </br>
+                    <div class="tts_block">
+                        <select id="tts_provider" class="flex1">
+                        </select>
+                        <input id="tts_refresh" class="menu_button" type="submit" value="Reload" />
+                    </div>
+                    <div>
+                        <label class="checkbox_label" for="tts_enabled">
+                            <input type="checkbox" id="tts_enabled" name="tts_enabled">
+                            <small>Enabled</small>
+                        </label>
+                        <label class="checkbox_label" for="tts_narrate_user">
+                            <input type="checkbox" id="tts_narrate_user">
+                            <small>Narrate user messages</small>
+                        </label>
+                        <label class="checkbox_label" for="tts_auto_generation">
+                            <input type="checkbox" id="tts_auto_generation">
+                            <small>Auto Generation</small>
+                        </label>
+                        <label class="checkbox_label" for="tts_narrate_quoted">
+                            <input type="checkbox" id="tts_narrate_quoted">
+                            <small>Only narrate "quotes"</small>
+                        </label>
+                        <label class="checkbox_label" for="tts_narrate_dialogues">
+                            <input type="checkbox" id="tts_narrate_dialogues">
+                            <small>Ignore *text, even "quotes", inside asterisks*</small>
+                        </label>
+                        <label class="checkbox_label" for="tts_narrate_translated_only">
+                            <input type="checkbox" id="tts_narrate_translated_only">
+                            <small>Narrate only the translated text</small>
+                        </label>
+                        <label class="checkbox_label" for="tts_skip_codeblocks">
+                            <input type="checkbox" id="tts_skip_codeblocks">
+                            <small>Skip codeblocks</small>
+                        </label>
+                        <label class="checkbox_label" for="tts_pass_asterisks">
+                        <input type="checkbox" id="tts_pass_asterisks">
+                        <small>Pass Asterisks to TTS Engine</small>
+                        </label>
+                    </div>
+                    <div id="tts_voicemap_block">
+                    </div>
+                    <hr>
+                    <form id="tts_provider_settings" class="inline-drawer-content">
+                    </form>
+                    <div class="tts_buttons">
+                        <input id="tts_voices" class="menu_button" type="submit" value="Available voices" />
+                    </div>
+                    </div>
+                </div>
+            </div>
+        </div>
+        `;
+        $('#extensions_settings').append(settingsHtml);
+        $('#tts_refresh').on('click', onRefreshClick);
+        $('#tts_enabled').on('click', onEnableClick);
+        $('#tts_narrate_dialogues').on('click', onNarrateDialoguesClick);
+        $('#tts_narrate_quoted').on('click', onNarrateQuotedClick);
+        $('#tts_narrate_translated_only').on('click', onNarrateTranslatedOnlyClick);
+        $('#tts_skip_codeblocks').on('click', onSkipCodeblocksClick);
+        $('#tts_pass_asterisks').on('click', onPassAsterisksClick);
+        $('#tts_auto_generation').on('click', onAutoGenerationClick);
+        $('#tts_narrate_user').on('click', onNarrateUserClick);
+        $('#tts_voices').on('click', onTtsVoicesClick);
+        for (const provider in ttsProviders) {
+            $('#tts_provider').append($('<option />').val(provider).text(provider));
+        }
+        $('#tts_provider').on('change', onTtsProviderChange);
+        $(document).on('click', '.mes_narrate', onNarrateOneMessage);
+    }
+    addExtensionControls(); // No init dependencies
+    loadSettings(); // Depends on Extension Controls and loadTtsProvider
+    loadTtsProvider(extension_settings.tts.currentProvider); // No dependencies
+    addAudioControl(); // Depends on Extension Controls
+    const wrapper = new ModuleWorkerWrapper(moduleWorker);
+    setInterval(wrapper.update.bind(wrapper), UPDATE_INTERVAL); // Init depends on all the things
+    eventSource.on(event_types.MESSAGE_SWIPED, resetTtsPlayback);
+    eventSource.on(event_types.CHAT_CHANGED, onChatChanged);
+    eventSource.on(event_types.MESSAGE_DELETED, onChatDeleted);
+    eventSource.on(event_types.GROUP_UPDATED, onChatChanged);
+    registerSlashCommand('speak', onNarrateText, ['narrate', 'tts'], '<span class="monospace">(text)</span>  – narrate any text using currently selected character\'s voice. Use voice="Character Name" argument to set other voice from the voice map, example: <tt>/speak voice="Donald Duck" Quack!</tt>', true, true);
+    document.body.appendChild(audioElement);
+});
\ No newline at end of file
diff --git a/templates/STfiles/style.css b/templates/STfiles/style.css
new file mode 100644
index 0000000..f926887
--- /dev/null
+++ b/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; 
+}
\ No newline at end of file

From a9d95fc563f525447d931ec0987eff55fb4eb252 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Thu, 18 Jan 2024 14:15:34 +0000
Subject: [PATCH 21/44] Update script.py

---
 script.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/script.py b/script.py
index e569ff8..2aab5af 100644
--- a/script.py
+++ b/script.py
@@ -613,7 +613,7 @@ def output_modifier(string, state):
                     # 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)
@@ -899,4 +899,4 @@ if running_in_standalone:
         try:
             time.sleep(1)  # Add a small delay to avoid high CPU usage
         except KeyboardInterrupt:
-            break  # Allow graceful exit on Ctrl+C
\ No newline at end of file
+            break  # Allow graceful exit on Ctrl+C

From 2bd1ef843e1eb0c9b115504c760b01c42cefb3df Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sat, 20 Jan 2024 00:18:06 +0000
Subject: [PATCH 22/44] Dynamic IP support

---
 .../tts_chunk_player/tts_chunk_player.html     | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/templates/tts_chunk_player/tts_chunk_player.html b/templates/tts_chunk_player/tts_chunk_player.html
index 61c36bd..65e3063 100644
--- a/templates/tts_chunk_player/tts_chunk_player.html
+++ b/templates/tts_chunk_player/tts_chunk_player.html
@@ -709,7 +709,10 @@
     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 ////////
@@ -850,7 +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",
@@ -920,7 +923,7 @@
                 autoplay: "false",
                 autoplay_volume: "0.1"
             });
-            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",
@@ -1050,7 +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",
@@ -1080,8 +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
             });
@@ -1140,7 +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,
             });
@@ -1632,7 +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");
 

From 525a337835382b7b9acde5e56fbf73dbde26c036 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sat, 20 Jan 2024 13:47:58 +0000
Subject: [PATCH 23/44] Update README.md

---
 README.md | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index c4b1551..424be0d 100644
--- a/README.md
+++ b/README.md
@@ -161,7 +161,7 @@ Deepspeed and other such things can be installed. Please read the relevant instr
 
 
 #### 🟩 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).
 
@@ -348,6 +348,15 @@ 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>

From 7010369966fe9f9d6a64df313013d0c8699d854b Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sun, 21 Jan 2024 12:20:29 +0000
Subject: [PATCH 24/44] Added startup_wait_time to top of script

Making it simple for people to adjust the allowed start-up time
---
 script.py | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/script.py b/script.py
index 2aab5af..74f23f5 100644
--- a/script.py
+++ b/script.py
@@ -16,6 +16,14 @@ 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 ####
 #################################################################
@@ -239,7 +247,7 @@ if process.poll() is None:
     print(f"[{params['branding']}Startup] TTS Subprocess starting")
     print(f"[{params['branding']}Startup]")
     print(
-        f"[{params['branding']}Startup] \033[94mSettings & Documentation:\033[00m",
+        f"[{params['branding']}Startup] \033[94m {params['branding']}Settings & Documentation:\033[00m",
         f"\033[92mhttp://{params['ip_address']}:{params['port_number']}\033[00m",
     )
     print(f"[{params['branding']}Startup]")
@@ -266,7 +274,7 @@ else:
     # 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
+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.
@@ -279,13 +287,15 @@ while time.time() - start_time < timeout:
     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[91mWarning\033[0m TTS Subprocess has NOT started up yet, Will keep trying for {timeout} seconds maximum. Please wait."
         )
-    time.sleep(4)
+    time.sleep(5)
 else:
-    print(
-        f"[{params['branding']}Startup] Startup timed out. Check the server logs for more information."
-    )
+    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)
 

From c9a222932caea880477dbe5f907be3eb318e4cb6 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sun, 21 Jan 2024 12:22:14 +0000
Subject: [PATCH 25/44] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 424be0d..5b84610 100644
--- a/README.md
+++ b/README.md
@@ -297,7 +297,7 @@ If you are on a Windows machine or a Linux machine, you should be able to use th
 **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` at the top of the script.py file, to a larger value e.g `startup_wait_time = 240` (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.
 

From 6c28d58b4aa49ee718f13217e7995b1e23d4dd2e Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sun, 21 Jan 2024 12:23:53 +0000
Subject: [PATCH 26/44] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 5b84610..396d0c0 100644
--- a/README.md
+++ b/README.md
@@ -297,7 +297,7 @@ If you are on a Windows machine or a Linux machine, you should be able to use th
 **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 `startup_wait_time = 120` at the top of the script.py file, to a larger value e.g `startup_wait_time = 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.
 

From 535c9b652a0103ced6e267b8080db79ae07cccd0 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sun, 21 Jan 2024 12:53:04 +0000
Subject: [PATCH 27/44] Update README.md

---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index 396d0c0..3864a1f 100644
--- a/README.md
+++ b/README.md
@@ -32,6 +32,8 @@ Please check the below link to find a list of all recent updates and changes.
 #### &nbsp;&nbsp;&nbsp;&nbsp;🔄 **Updates list & bug fixes list** can be found [here](https://github.com/erew123/alltalk_tts/issues/25)
 #### &nbsp;&nbsp;&nbsp;&nbsp;🔄 **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.
+
 ## 🟩 Quick Setup (Text-generation-webui & Standalone Installation)
 For Windows 10/11 and Linux machines there is a quick setup script. Click to expand the correct section below:
 <details>

From dbc2582fa69f6db125f5fe9b2c5305757a9a1a59 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Sun, 21 Jan 2024 13:05:35 +0000
Subject: [PATCH 28/44] Update README.md

---
 README.md | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/README.md b/README.md
index 3864a1f..cb92492 100644
--- a/README.md
+++ b/README.md
@@ -15,7 +15,7 @@ AllTalk is an updated version of the Coqui_tts extension for Text Generation web
 - **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/#-quick-setup-text-generation-webui--standalone-installation)
 - 🟪 [Updating & problems with updating](https://github.com/erew123/alltalk_tts?#-updating)
@@ -27,14 +27,14 @@ AllTalk is an updated version of the Coqui_tts extension for Text Generation web
 - 🟠 [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)
 
-## 🔄 Feature requests, Updates & Bug fixes
+### 🔄 Feature requests, Updates & Bug fixes
 Please check the below link to find a list of all recent updates and changes.
 #### &nbsp;&nbsp;&nbsp;&nbsp;🔄 **Updates list & bug fixes list** can be found [here](https://github.com/erew123/alltalk_tts/issues/25)
 #### &nbsp;&nbsp;&nbsp;&nbsp;🔄 **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.
 
-## 🟩 Quick Setup (Text-generation-webui & Standalone Installation)
+### 🟩 Quick Setup (Text-generation-webui & Standalone Installation)
 For Windows 10/11 and Linux machines there is a quick setup script. Click to expand the correct section below:
 <details>
 	<summary>QUICK SETUP - Text-Generation-webui</summary><br>
@@ -72,7 +72,7 @@ For Windows 10/11 and Linux machines there is a quick setup script. Click to exp
    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
+### 🟩 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>
@@ -112,7 +112,7 @@ This has been tested on the current Dec 2023 release of Text generation webUI. I
 
 </details>
 
-## 🟩 Manual Installation - As a Standalone Application
+### 🟩 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>
@@ -182,7 +182,7 @@ 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. 
@@ -261,12 +261,12 @@ 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/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/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)|
 
-## 🟨 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)
 
@@ -403,7 +403,7 @@ 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).
@@ -500,7 +500,7 @@ 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
@@ -678,7 +678,7 @@ def get_shm_size():
 </details>
 </details>
 
-## ⬜ AllTalk TTS Generator
+### ⬜ 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. 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). 
 
 #### ⬜ Estimated Throughput
@@ -715,7 +715,7 @@ For generating **large amounts of TTS**, it's recommended to select the **No Pla
 - 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.
 

From e50817a234e2ff4bc2a40d29c3295db72c50d366 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 18:55:45 +0000
Subject: [PATCH 29/44] Update atsetup.bat

force install of transformers pip install transformers==4.36.2
---
 atsetup.bat | 1 +
 1 file changed, 1 insertion(+)

diff --git a/atsetup.bat b/atsetup.bat
index 21e4ce9..3d53413 100644
--- a/atsetup.bat
+++ b/atsetup.bat
@@ -353,6 +353,7 @@ if "%UserChoice%" == "1" (
     pip install python-multipart==0.0.6
     pip install cutlet>=0.3.0
     pip install unidic-lite>=1.0.8
+    pip install transformers==4.36.2
     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...

From 4d837a0219d1b7529ea9423a2a62362c9641b6cb Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 18:56:11 +0000
Subject: [PATCH 30/44] Update atsetup.sh

force     pip install transformers==4.36.2
---
 atsetup.sh | 1 +
 1 file changed, 1 insertion(+)

diff --git a/atsetup.sh b/atsetup.sh
index 2fded23..af1baa1 100644
--- a/atsetup.sh
+++ b/atsetup.sh
@@ -313,6 +313,7 @@ install_custom_standalone() {
     	pip install python-multipart==0.0.6
         pip install cutlet>=0.3.0
     	pip install unidic-lite>=1.0.8
+        pip install transformers==4.36.2
     else
         pip install -r requirements_other.txt
     fi

From 7928af1bb79da45bb45185d9e3d54e5c12e644c1 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 18:56:39 +0000
Subject: [PATCH 31/44] Update requirements_nvidia.txt

---
 requirements_nvidia.txt | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/requirements_nvidia.txt b/requirements_nvidia.txt
index 51d6d2a..010d471 100644
--- a/requirements_nvidia.txt
+++ b/requirements_nvidia.txt
@@ -14,4 +14,5 @@ pydantic>=1.10.13
 sounddevice>=0.4.6
 python-multipart>=0.0.6
 cutlet>=0.3.0
-unidic-lite>=1.0.8
\ No newline at end of file
+unidic-lite>=1.0.8
+transformers==4.36.2

From af907a299d856fbe07211688125fd9bb0a5445e2 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 18:56:50 +0000
Subject: [PATCH 32/44] Update requirements_other.txt

---
 requirements_other.txt | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/requirements_other.txt b/requirements_other.txt
index e0363f2..c458bfe 100644
--- a/requirements_other.txt
+++ b/requirements_other.txt
@@ -14,4 +14,5 @@ pydantic>=1.10.13
 sounddevice>=0.4.6
 python-multipart>=0.0.6
 cutlet>=0.3.0
-unidic-lite>=1.0.8
\ No newline at end of file
+unidic-lite>=1.0.8
+transformers==4.36.2

From d0866e3c6c9ef54d73fcd2dd210c8aadf8750428 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 19:16:54 +0000
Subject: [PATCH 33/44] Update README.md

---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index cb92492..229adb9 100644
--- a/README.md
+++ b/README.md
@@ -34,6 +34,8 @@ Please check the below link to find a list of all recent updates and changes.
 
 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. Click to expand the correct section below:
 <details>

From ad57deed203a540344ecfaff854bb75cca733e92 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 20:00:21 +0000
Subject: [PATCH 34/44] Update atsetup.bat

---
 atsetup.bat | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/atsetup.bat b/atsetup.bat
index 3d53413..a0fba2a 100644
--- a/atsetup.bat
+++ b/atsetup.bat
@@ -341,6 +341,7 @@ if "%UserChoice%" == "1" (
     pip install fsspec>=2023.6.0
     pip install soundfile==0.12.1
     pip install uvicorn==0.24.0.post1
+    pip install transformers==4.36.2
     pip install TTS==0.21.3
     pip install fastapi==0.104.1
     pip install Jinja2==3.1.2
@@ -353,7 +354,6 @@ if "%UserChoice%" == "1" (
     pip install python-multipart==0.0.6
     pip install cutlet>=0.3.0
     pip install unidic-lite>=1.0.8
-    pip install transformers==4.36.2
     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...

From d93906a75fd1fed046e0ea3e57c4b4193d8ee009 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 20:00:47 +0000
Subject: [PATCH 35/44] Update atsetup.sh

---
 atsetup.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/atsetup.sh b/atsetup.sh
index af1baa1..7969a62 100644
--- a/atsetup.sh
+++ b/atsetup.sh
@@ -301,6 +301,7 @@ install_custom_standalone() {
     	pip install fsspec>=2023.6.0
 	pip install soundfile==0.12.1
     	pip install uvicorn==0.24.0.post1
+        pip install transformers==4.36.2
     	pip install TTS==0.21.3
     	pip install fastapi==0.104.1
     	pip install Jinja2==3.1.2
@@ -313,7 +314,6 @@ install_custom_standalone() {
     	pip install python-multipart==0.0.6
         pip install cutlet>=0.3.0
     	pip install unidic-lite>=1.0.8
-        pip install transformers==4.36.2
     else
         pip install -r requirements_other.txt
     fi

From e524063ec2c8c3026a2e84e8df5bf9c1e43f7adf Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 20:01:04 +0000
Subject: [PATCH 36/44] Update requirements_nvidia.txt

---
 requirements_nvidia.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/requirements_nvidia.txt b/requirements_nvidia.txt
index 010d471..31903f5 100644
--- a/requirements_nvidia.txt
+++ b/requirements_nvidia.txt
@@ -1,6 +1,7 @@
 numpy>=1.22.0
 soundfile>=0.12.1
 uvicorn>=0.24.0.post1
+transformers==4.36.2
 TTS>=0.21.3
 torch>=2.1.0+cu118
 torchaudio>=2.1.0+cu118
@@ -15,4 +16,3 @@ sounddevice>=0.4.6
 python-multipart>=0.0.6
 cutlet>=0.3.0
 unidic-lite>=1.0.8
-transformers==4.36.2

From 2b60f5b0da988e5a14e20c93ab3f69624df74af8 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 20:01:16 +0000
Subject: [PATCH 37/44] Update requirements_other.txt

---
 requirements_other.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/requirements_other.txt b/requirements_other.txt
index c458bfe..1f00475 100644
--- a/requirements_other.txt
+++ b/requirements_other.txt
@@ -1,6 +1,7 @@
 numpy>=1.22.0
 soundfile>=0.12.1
 uvicorn>=0.24.0.post1
+transformers==4.36.2
 TTS>=0.21.3
 torch>=2.1.0
 torchaudio>=2.1.0
@@ -15,4 +16,3 @@ sounddevice>=0.4.6
 python-multipart>=0.0.6
 cutlet>=0.3.0
 unidic-lite>=1.0.8
-transformers==4.36.2

From abc9cf1fb721759306eaed2d312234819d4a42c6 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 20:45:11 +0000
Subject: [PATCH 38/44] Update README.md

---
 README.md | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 229adb9..7e9330b 100644
--- a/README.md
+++ b/README.md
@@ -37,7 +37,9 @@ I welcome your input and ideas for new features, suggestions, and improvements.
 **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. Click to expand the correct section below:
+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>
 
@@ -330,6 +332,15 @@ 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
+<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`. 
+</details>
+
 #### 🟨 I think AllTalks requirements file has installed something another extension doesn't like
 <details>
 	<summary>Click to expand</summary><br>

From 82ecf3eecc442905bdbc029e583cbeec02fd23e3 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 22:18:16 +0000
Subject: [PATCH 39/44] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 7e9330b..97e9c93 100644
--- a/README.md
+++ b/README.md
@@ -332,7 +332,7 @@ 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
+#### 🟨 Windows & Python requirements for compiling packages `error: Microsoft Visual C++ 14.0 or greater is required`
 <details>
 	<summary>Click to expand</summary><br>
 

From 6c4a9b19c72ab5446d3d20ce4208eb05cc79c7e9 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 22:21:21 +0000
Subject: [PATCH 40/44] Update README.md

---
 README.md | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 97e9c93..484dd09 100644
--- a/README.md
+++ b/README.md
@@ -332,7 +332,10 @@ 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`
+#### 🟨 Windows & Python requirements for compiling packages
+
+`ERROR: Microsoft Visual C++ 14.0 or greater is required` or `ERROR: Could not build wheels for TTS.`
+
 <details>
 	<summary>Click to expand</summary><br>
 

From 6d4b6d336b02868448197a3659a925ddb2f8d6d5 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 22:30:47 +0000
Subject: [PATCH 41/44] Update README.md

---
 README.md | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/README.md b/README.md
index 484dd09..649c2f5 100644
--- a/README.md
+++ b/README.md
@@ -342,6 +342,9 @@ Other possibilities for this issue are:
  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

From ecdc10ece5a943f19e71663fa8d4f2cbeef35027 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Mon, 22 Jan 2024 23:27:55 +0000
Subject: [PATCH 42/44] Update atsetup.bat

---
 atsetup.bat | 2 --
 1 file changed, 2 deletions(-)

diff --git a/atsetup.bat b/atsetup.bat
index a0fba2a..2bc07f0 100644
--- a/atsetup.bat
+++ b/atsetup.bat
@@ -370,7 +370,6 @@ 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
-echo exit >> start_environment.bat
 @rem Create start_alltalk.bat to run AllTalk
 echo @echo off > start_alltalk.bat
 echo cd /D "%~dp0" >> start_alltalk.bat
@@ -378,7 +377,6 @@ 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 exit >> start_alltalk.bat
 Echo.
 Echo    start_alltalk.bat has been created.
 Echo    You can now start AllTalk with %L_YELLOW%start_alltalk.bat%RESET%

From 03b02e0e4c04ba7f86cbd0a9c97c16a9ba7c8724 Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Tue, 23 Jan 2024 11:18:42 +0000
Subject: [PATCH 43/44] Update README.md

---
 README.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 649c2f5..0990068 100644
--- a/README.md
+++ b/README.md
@@ -45,7 +45,7 @@ Click to expand the correct section below:
 
  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) On this page select **CODE** > **Download ZIP** then extract it to the text-generation-webui extensions folder<br>e.g. `\text-generation-webui\extensions\alltalk_tts\`<br><br>
+   - A) On this page select **CODE** > **Download ZIP** then extract it to the text-generation-webui extensions folder<br>e.g. `\text-generation-webui\extensions\alltalk_tts\` remove `-main` from the folder name.<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`
@@ -63,7 +63,7 @@ Click to expand the correct section below:
 
  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) On this page select **CODE** > **Download ZIP** then extract it to the folder of your choice<br>e.g. `C:\myfiles\alltalk_tts\`<br><br>
+   - A) On this page select **CODE** > **Download ZIP** then extract it to the folder of your choice<br>e.g. `C:\myfiles\alltalk_tts\` remove `-main` from the folder name.<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`

From ab37dd88495df5af3556b79415d382b31a6c284c Mon Sep 17 00:00:00 2001
From: erew123 <35898566+erew123@users.noreply.github.com>
Date: Tue, 23 Jan 2024 11:45:29 +0000
Subject: [PATCH 44/44] Update README.md

---
 README.md | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 0990068..8683d12 100644
--- a/README.md
+++ b/README.md
@@ -37,7 +37,7 @@ I welcome your input and ideas for new features, suggestions, and improvements.
 **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. 
+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>
@@ -45,7 +45,7 @@ Click to expand the correct section below:
 
  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) On this page select **CODE** > **Download ZIP** then extract it to the text-generation-webui extensions folder<br>e.g. `\text-generation-webui\extensions\alltalk_tts\` remove `-main` from the folder name.<br><br>
+   - 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`
@@ -63,7 +63,7 @@ Click to expand the correct section below:
 
  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) On this page select **CODE** > **Download ZIP** then extract it to the folder of your choice<br>e.g. `C:\myfiles\alltalk_tts\` remove `-main` from the folder name.<br><br>
+   - 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`
@@ -73,6 +73,8 @@ Click to expand the correct section below:
 
    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>
 
@@ -387,6 +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>