initial upload attempt
initial upload attempt
This commit is contained in:
erew123 committed
1 parent
84c19ed5a9
commit
9fd928f6e7
527 files changed
+37359
No files matched your search
@@ -0,0 +1,16 @@
|
||||
import gradio as gr
|
||||
|
||||
def alltalk_about():
|
||||
about = """
|
||||
### 🛠️ About this project
|
||||
> AllTalk is a labour of love that has been developed, supported and sustained in my personal free time. As a solo enthusiast (not a business or team) my resources are inherently limited. This project has been one of my passions, but I must balance it with other commitments.<br><br>
|
||||
To manage AllTalk sustainably, I prioritize support requests based on their overall impact and the number of users affected. I encourage you to utilize the comprehensive documentation and engage with the AllTalk community discussion area. These resources often provide immediate answers and foster a supportive user network.<br><br>
|
||||
Should your inquiry extend beyond the documentation, especially if it concerns a bug or feature request, I assure you I’ll offer my best support as my schedule permits. However, please be prepared for varying response times, reflective of the personal dedication I bring to AllTalk. Your understanding and patience in this regard are greatly appreciated.<br><br>
|
||||
It's important to note that **I am not** the developer of any TTS models utilized by AllTalk, nor do I claim to be an expert on them, including understanding all their nuances, issues, and quirks. For specific TTS model concerns, I’ve provided links to the original developers in each TTS engines "Engine Information" section for direct assistance/research.<br><br>
|
||||
Thank you for your continued support and understanding.
|
||||
|
||||
### 💖 Showing Your Support
|
||||
> If AllTalk has been helpful to you, consider showing your support through a donation on my **[Ko-fi page](https://ko-fi.com/erew123)**. <br><br>
|
||||
Your support is greatly appreciated and helps ensure the continued development and improvement of AllTalk.
|
||||
"""
|
||||
gr.Markdown(about)
|
||||
@@ -0,0 +1,76 @@
|
||||
import os
|
||||
from pathlib import Path
|
||||
import gradio as gr
|
||||
|
||||
# Define directories
|
||||
this_dir = Path(__file__).parent.resolve()
|
||||
main_dir = this_dir.parent.parent.resolve()
|
||||
|
||||
# Folder paths
|
||||
folders = {
|
||||
"models": main_dir / "models",
|
||||
"finetune": main_dir / "finetune",
|
||||
"voices": main_dir / "voices",
|
||||
"outputs": main_dir / "outputs",
|
||||
"alltalk_environment": main_dir / "alltalk_environment"
|
||||
}
|
||||
|
||||
def get_folder_size_scandir(folder_path):
|
||||
total_size = 0
|
||||
for entry in os.scandir(folder_path):
|
||||
if entry.is_file(follow_symlinks=False):
|
||||
try:
|
||||
total_size += entry.stat(follow_symlinks=False).st_size
|
||||
except OSError as e:
|
||||
print(f"Error getting size for file {entry.path}: {e}")
|
||||
elif entry.is_dir(follow_symlinks=False):
|
||||
try:
|
||||
total_size += get_folder_size_scandir(entry.path)
|
||||
except OSError as e:
|
||||
print(f"Error accessing directory {entry.path}: {e}")
|
||||
return total_size
|
||||
|
||||
def format_size(size):
|
||||
# Convert size to a readable format
|
||||
for unit in ['B', 'KB', 'MB', 'GB', 'TB']:
|
||||
if size < 1024:
|
||||
return f"{size:.2f} {unit}"
|
||||
size /= 1024
|
||||
|
||||
def calculate_disk_space():
|
||||
sizes = {}
|
||||
for name, path in folders.items():
|
||||
if path.exists():
|
||||
folder_size = get_folder_size_scandir(path)
|
||||
# print(f"Folder: {name}, Total Size: {folder_size} bytes")
|
||||
sizes[name] = format_size(folder_size)
|
||||
else:
|
||||
sizes[name] = "Not present"
|
||||
|
||||
return sizes['models'], sizes['finetune'], sizes['voices'], sizes['outputs'], sizes['alltalk_environment']
|
||||
|
||||
def disk_space_page():
|
||||
# Define the layout
|
||||
with gr.Tab("Disk Space Usage"):
|
||||
with gr.Row():
|
||||
models_space = gr.Textbox(label="Models Folder", interactive=False)
|
||||
finetune_space = gr.Textbox(label="Finetune Folder", interactive=False)
|
||||
voices_space = gr.Textbox(label="Voices Folder", interactive=False)
|
||||
outputs_space = gr.Textbox(label="Outputs Folder", interactive=False)
|
||||
alltalk_env_space = gr.Textbox(label="Alltalk Python Environment", interactive=False)
|
||||
|
||||
calculate_button = gr.Button("Calculate Disk Space Usage")
|
||||
|
||||
# Define actions for buttons
|
||||
calculate_button.click(calculate_disk_space, outputs=[models_space, finetune_space, voices_space, outputs_space, alltalk_env_space])
|
||||
|
||||
def get_disk_interface():
|
||||
return disk_space_page
|
||||
|
||||
# Example usage in the main script
|
||||
if __name__ == "__main__":
|
||||
app = gr.Blocks()
|
||||
with app:
|
||||
disk_space_page()
|
||||
|
||||
app.launch()
|
||||
File diff suppressed because it is too large.
Load diff
@@ -0,0 +1,99 @@
|
||||
import gradio as gr
|
||||
|
||||
def alltalk_generation_help():
|
||||
generation_blurb = """
|
||||
The Generation Screen is the main interface where you can input text to generate speech, as well as swap **and set the default** Text-to-Speech (TTS) engine and model. Below is a detailed description of each setting and its functionality.
|
||||
"""
|
||||
generation_help = """
|
||||
### 🟨 TTS Engine and Model<br>
|
||||
**Swap TTS Engine**<br>
|
||||
> This button allows you to change and set the current TTS engine. Swapping the engine will also set the new engine as the default for future sessions. When you swap the engine, the settings on the page will refresh to match the capabilities of the selected engine. Some settings may become unavailable or newly available depending on the chosen engine.<br>
|
||||
|
||||
**Load Different Model**<br>
|
||||
> This dropdown lists the available models for the selected TTS engine. These models are located in the models folder and are specific to each TTS engine. Changing the model will also set it as the default for future sessions and refresh the settings on the page.<br>
|
||||
|
||||
### 🟨 RVC Pipeline<br>
|
||||
**RVC Character Voice**<br>
|
||||
> This setting is part of the RVC pipeline. If RVC is not enabled (which can be done in the RVC tab), "Disabled" will be the only option. Once RVC is enabled and the required models (approximately 700MB) are downloaded, any voices stored in the `/models/rvc_voices/{yourmodelhere}` folder will be available for selection. Selecting a voice will apply it during the TTS generation process. You can select "Disabled" at any time to bypass the RVC pipeline even when it is globally enabled.<br>
|
||||
|
||||
**RVC Narrator Voice**<br>
|
||||
> Similar to the RVC Character Voice, this setting applies to the narrator voice in the RVC pipeline.<br>
|
||||
|
||||
### 🟨 Generation Settings<br>
|
||||
**Generation Mode**<br>
|
||||
> Choose the mode of TTS generation, such as Standard or Streaming. Note that Gradio may have difficulty with streaming, so you might receive standard audio as a file even when streaming is selected. If the engine doesn't support Streaming, only Standard mode will be shown.<br>
|
||||
|
||||
**Language/Model not multi-language**<br>
|
||||
> Select the language for TTS generation here. Some models are **not** multi-language capable and the language it generates in is built into the model itself. In such cases, this option will change to `Model not multi-language` and it will no longer be selectable when the model doesn't support multiple languages.<br>
|
||||
|
||||
**Narrator Enabled/Disabled**<br>
|
||||
> Enable or disable the narrator feature. When enabled, the TTS engine processes three types of text (Refer to the "Narrator Function" help tab for more details):<br>
|
||||
> **Narrated Text** : Text enclosed in asterisks *Narrated text*.<br>
|
||||
> **Character Text** : Text enclosed in double quotes "Character text".<br>
|
||||
> **Text-Not-Inside**: Any text not enclosed in asterisks or double quotes. The handling of this text is customizable.<br>
|
||||
|
||||
**Narrator Text-not-inside**<br>
|
||||
> Configures how text that is not enclosed in asterisks or double quotes is handled. Detailed explanations are available in the "Narrator Function" help tab.<br>
|
||||
|
||||
**Auto-Stop Current Generation**<br>
|
||||
> If the loaded model or generation method supports stopping the current TTS generation when sending a new request, this setting will attempt to stop the current process before starting a new one.
|
||||
|
||||
### 🟨 Voice Selection<br>
|
||||
**Character (Main TTS) Voice**<br>
|
||||
> Select the character voice from the available voices within the currently loaded TTS engine and model.<br>
|
||||
|
||||
**Narrator Voice**<br>
|
||||
> Choose the narrator voice from the available voices within the currently loaded TTS engine and model.<br>
|
||||
|
||||
"""
|
||||
generation_help2 = """
|
||||
### 🟨 Additional Settings
|
||||
**Text Filtering**<br>
|
||||
> **None**: No filtering. Raw text is sent to the TTS engine, which may result in odd sounds with some special characters.<br>
|
||||
> **HTML**: For HTML content, using HTML entities like emojis or text characters.<br>
|
||||
> **Standard**: Human-readable text with basic filtering to clean up special characters.<br>
|
||||
|
||||
**Play Locally or Remotely**<br>
|
||||
> Choose to play the generated speech locally or on the terminal/console where the server is running.<br>
|
||||
|
||||
**Remote Play Volume**<br>
|
||||
> Adjust the volume for remote playback.<br>
|
||||
|
||||
**Output File Name**<br>
|
||||
> Specify the name for the output file.<br>
|
||||
|
||||
**Include Timestamp**<br>
|
||||
> If enabled, each generated file will include a timestamp to ensure uniqueness. If disabled, the output filename will be used, and the file will be overwritten with each generation.<br>
|
||||
|
||||
**Speed**<br>
|
||||
> Adjust the speed of the generated speech. This option is not available if the selected TTS engine doesn't support it.<br>
|
||||
|
||||
**Pitch**<br>
|
||||
>Adjust the pitch of the generated speech. This option is not available if the selected TTS engine doesn't support it.<br>
|
||||
|
||||
**Temperature**<br>
|
||||
> Control the randomness of the generation process. Higher values result in more varied output. This option is not available if the selected TTS engine doesn't support it.<br>
|
||||
|
||||
**Repetition Penalty**<br>
|
||||
> Set the penalty for repetitive sequences in the generated speech. This option is not available if the selected TTS engine doesn't support it.<br>
|
||||
|
||||
### 🟨 Output and Controls
|
||||
**TTS Result**<br>
|
||||
> View the result of the TTS generation process here.<br>
|
||||
|
||||
**Playback Controls**<br>
|
||||
> Use these controls to play, pause, and navigate through the generated speech.<br>
|
||||
|
||||
**Light/Dark Mode**<br>
|
||||
> Toggle between light and dark mode for the interface.<br>
|
||||
|
||||
**Refresh Server Settings**<br>
|
||||
>Refresh the server settings to apply any changes made. This is useful if you have reloaded the engine elsewhere or added new models/voices to your folders. If refreshing doesn't update your voices, you can use the "Swap TTS Engine" button to force a full refresh.<br>
|
||||
|
||||
**Interrupt TTS Generation**<br>
|
||||
> Manually stop the current TTS generation process, similar to the "Auto-Stop Current Generation" setting but applied manually.<br>
|
||||
"""
|
||||
gr.Markdown(generation_blurb)
|
||||
with gr.Row():
|
||||
gr.Markdown(generation_help)
|
||||
gr.Markdown(generation_help2)
|
||||
@@ -0,0 +1,59 @@
|
||||
import os
|
||||
import json
|
||||
import pathlib as Path
|
||||
import gradio as gr
|
||||
|
||||
def modify_config():
|
||||
config_file = os.path.join("confignew.json")
|
||||
with open(config_file, "r") as f:
|
||||
config = json.load(f)
|
||||
config["firstrun_splash"] = False
|
||||
with open(config_file, "w") as f:
|
||||
json.dump(config, f, indent=4)
|
||||
return f"Welcome screen is disabled."
|
||||
|
||||
def alltalk_welcome():
|
||||
welcome = """
|
||||
## 🟧 Welcome the the AllTalk v2 BETA
|
||||
Thanks for trying out the BETA. Ive no doubt there will be bugs and quirks here and there. Most errors/issues should have outputs at the command prompt/console.
|
||||
|
||||
I have validated this BETA to run on Windows/Linux, because I dont have a Mac. With Python 3.11.9, Pytorch 2.2.1 with CUDA 12.1 extensions installed. Thats not to say it wont work on Mac or other versions of Python and Pytorch, its just there would be some extra testing/figuring things out to make it work. Obviously, I am kind of a bit limited to do that on Mac's. Certainly Mac's dont need the Nvidia lines in the requirements file and I cannot say how certain engines will/wont work/perform on Mac's.
|
||||
|
||||
### 🟧 Important Requirements
|
||||
> - Please ensure that you have installed Espeak-ng for your platform (you should get and error message at the command prompt/terminal if you havnt).<br>
|
||||
> - It is possible I have forgotten some requirements, but hopefully not!
|
||||
> - Linux users, you should have installed `libaio-dev` or `libaio-devl` (depending on your Linux flavour), otherwise DeepSpeed will fail e.g.<br>
|
||||
> **Debian-based systems** `sudo apt install libaio-dev`<br>
|
||||
> **RPM-based systems** `sudo yum install libaio-devel`
|
||||
|
||||
### 🟧 TLDR what you need to do
|
||||
> - To download models, you can go to the `TTS Engines Settings`, choose the engine you want and there are downloads there, along with additional instructions/information about each engine, its specific settings, how to work with it etc.
|
||||
> - RVC when enabled will download about 800MB of models that it needs to work. If you want more information on RVC, please read the Documentation.
|
||||
> - Talking of which, Gradio isnt great at documentation. Ive found that the `Light/Dark Mode` button is handy, along with sometime using your browsers zoom function.
|
||||
> - **Check the console** for errors/warnings if you have problems. I have **tried** to cover most issues/possible errors.
|
||||
> - The documentation may be a bit rough and ready. I havnt had time to go through it all step by step.
|
||||
|
||||
### 🟧 DeepSpeed on Linux
|
||||
> I've not managed to update the documentation, but if you are **NOT** using AllTalk as a standalone on Linux, take a look here and this should ease the setup of DeepSpeed https://github.com/erew123/alltalk_tts/releases/tag/DeepSpeed-14.2-Linux
|
||||
|
||||
### 🟧 SillyTavern users
|
||||
> There is an updated ST extension in the system folder. Instructions are inside the folder.
|
||||
|
||||
### 🟧 Text-generation-webui users
|
||||
> There is a TGWUI remote extension, if you want to run AllTalk on a computer that is NOT your AllTalk system. Please look in the system folder. Instructions are inside the folder.
|
||||
|
||||
### 🟧 Why is X feature no in the BETA yet? Or I have a great idea!
|
||||
Mostly because of time restrains. V2 has been a massive re-write of code in the 100's of hours range to get it where it is. Please do check the Feature Requests list here https://github.com/erew123/alltalk_tts/discussions/74. I will get to them when I can. People are welcome to work on code/test things out with this version if they wish. I will set up a page for feeback on the **Github Discussions Board** https://github.com/erew123/alltalk_tts/discussions
|
||||
|
||||
### 🟧 Can I add other TTS engines?
|
||||
Yes if you have a bit of coding experience. All the Coqui supported engines should be pretty easy to set up now, I just havnt gotten around it yet. Other engines like Piper and Parler have been done of course, showing other engines can be imported. Rough instructions are in the `system/tts_engines/template` folder.
|
||||
|
||||
### 🟧 Showing Your Support
|
||||
> If AllTalk has been helpful to you, consider showing your support through a donation on my **[Ko-fi page](https://ko-fi.com/erew123)**. Your support is greatly appreciated and helps ensure the continued development and improvement of AllTalk.
|
||||
"""
|
||||
with gr.Tab("AllTalk v2 BETA"):
|
||||
gr.Markdown(welcome)
|
||||
with gr.Row():
|
||||
output = gr.Textbox(label="Output")
|
||||
update_btn = gr.Button("Dont show me this screen again!")
|
||||
update_btn.click(fn=modify_config, inputs=None, outputs=output)
|
||||
@@ -0,0 +1,580 @@
|
||||
import gradio as gr
|
||||
|
||||
def api_documentation():
|
||||
best_practices = """
|
||||
### 🟠 Best Practices for writing an extension
|
||||
|
||||
You will need to store the IP address and Port (minimum) that your extension will be connecting to. Potentially also http/https if you wish to use AllTalk over tunnels. Additionally, you may also wish to store a connection timeout value.<br>
|
||||
|
||||
```
|
||||
{
|
||||
"api_alltalk_protocol": "http://",
|
||||
"api_alltalk_ip_port": "127.0.0.1:7851",
|
||||
"api_connection_timeout": 5
|
||||
}
|
||||
```
|
||||
When your extension starts up you will need to connect to the IP/Port and check the **/api/ready** end point for a 'Ready' status. You may wish to do this on a loop for the period of the connection timeout.<br>
|
||||
|
||||
If the timeout is reached without a response, you can set voices, models available, models loaded, basically whatever values you are going to store/present to the user as "Server Offline" or whatever terminology you wish.<br>
|
||||
|
||||
If the connection is available, then you would:<br>
|
||||
|
||||
> 1) Pull the current settings and populate those into a paramaters variabele. **/api/currentsettings**<br>
|
||||
2) Pull the current voices and populate those into a paramaters variabele. **/api/voices**<br>
|
||||
3) Pull the current rvcvoices and populate those into a paramaters variabele. **/api/rvcvoices**<br>
|
||||
|
||||
You can now present those to the user interface, choosing if you are just going to present the voices (narrator or not), RVC voices, model loaded, models available etc.<br>
|
||||
|
||||
If you are going to present a multitude of options, please abide by the **xxxxxx_capable** settings provided by **/api/currentsettings**, disabling or enabling options in your user interface as the loaded in TTS engine does or doesnt allow for e.g. if the current TTS engine doesnt support changing your generation audio speed, it will send **"generationspeed_capable": false** over when you use **/api/currentsettings**. As such, you should disable the option to change the generation speed within your interface, however, ultimately, even if not disabled, if the current TTS engine loaded isnt capable of speed generation, changing the generation speed will have no effect on the resulting TTS generation, but you may end up with users asking why!<br>
|
||||
|
||||
It is also advisable to have a refresh button to pull make AllTalk update its settings **/api/reload_config** and then you can pull current settings & voices again. This ensures the use always has a way to reconnect to the AllTalk server if its unavailable when your extension starts, or in the scenario that something else was changed in the Gradio interface and now the TTS Engine loaded in is different from when your extension started up.<br>
|
||||
|
||||
You can obviously choose if you will give the user access to change the model loaded, TTS engine etc. Please read the documentation on the API endpoints for more information.<br>
|
||||
|
||||
If you are presenting all the variables/options to the user, then when you send off a generation request to **/api/tts-generate** send all of the variable/options that are stored within your interface.<br>
|
||||
|
||||
If you are NOT presenting all the variables/options to the user, then you have 2x options when sending to **/api/tts-generate**:<br>
|
||||
|
||||
> 1) Send all the values/options but hard code some settings in your outbound generation request. This will ensure you always get the TTS generation result you want. Please read the **/api/tts-generate** section for details.<br>
|
||||
|
||||
OR<br>
|
||||
|
||||
>2) Dont send all the values/options in the generation request. In this scenario, the AllTalk server will populate missing settings from the global API Default Settings and the current TTS Engine's settings that are loaded in. e.g. if you dont provide a character voice, the default set character voice of whatever TTS engine is loaded in will be used. The same goes for all the other settings, except the actual text of the generation request.<br>
|
||||
|
||||
Finally, depending on how you are storing your settings, for your extension, you may wish to save the settings each time there is a successful generation request. This ensures that the settings are valid and the connected IP address/port are correct.
|
||||
"""
|
||||
|
||||
settings_endpoints = """
|
||||
### 🟠 Ready Endpoint<br>
|
||||
Check if the Text-to-Speech (TTS) engine has started and is ready to accept requests. This endpoint is useful when performing reload model/engine requests as it will return "Unloaded" while the engine is restarting. You can poll this endpoint every second or so to confirm a "Ready" status, indicating AllTalk is ready to process requests. Note that if there is an issue loading the selected model (e.g., missing from the file system), the endpoint will still return "Ready". This status only indicates that the engine has loaded.<br>
|
||||
|
||||
**URL**: `http://{ipaddress}:{port}/api/ready`<br>
|
||||
**Method**: `GET`<br>
|
||||
|
||||
> `curl -X GET "http://127.0.0.1:7851/api/ready"`
|
||||
|
||||
Response: `Ready` or `Unloaded`
|
||||
|
||||
### 🟠 Standard Voices List Endpoint<br>
|
||||
Retrieve a list of available voices for generating speech that the currently loaded TTS engine and model supports. If the currently loaded TTS engine does not load a model directly (e.g., Piper), the models themselves will be displayed as voices.
|
||||
|
||||
**URL**: `http://{ipaddress}:{port}/api/voices`<br>
|
||||
**Method**: `GET`<br>
|
||||
|
||||
> `curl -X GET "http://127.0.0.1:7851/api/voices"`
|
||||
|
||||
```
|
||||
{
|
||||
"status": "success",
|
||||
"voices": ["voice1", "voice2", "voice3"]
|
||||
}
|
||||
|
||||
```
|
||||
|
||||
### 🟠 RVC Voices List Endpoint<br>
|
||||
Retrieve a list of available RVC voices for further processing your TTS with the RVC pipeline. `Disabled` will always be included in the list. When `Disabled` is used, the RVC pipeline will not be utilized. If the RVC pipeline is globally disabled in AllTalk, `Disabled` will be the only item in the list. Index files matching their RVC voices will not be displayed; if an index file exists for an RVC voice, it will be automatically selected during generation. If multiple index files exist and it is impossible to automatically select one, a message will be output in the console.
|
||||
|
||||
**URL**: `http://{ipaddress}:{port}/api/rvcvoices`<br>
|
||||
**Method**: `GET`<br>
|
||||
|
||||
> `curl -X GET "http://127.0.0.1:7851/api/rvcvoices"`
|
||||
|
||||
```
|
||||
{
|
||||
"status": "success",
|
||||
"voices": ["Disabled", "folder1\\voice1.pth", "folder2\\voice2.pth", "folder3\\voice3.pth"]
|
||||
}
|
||||
```
|
||||
|
||||
### 🟠 Current Settings Endpoint<br>
|
||||
Retrieve the current settings of the TTS engine.
|
||||
|
||||
**URL**: `http://{ipaddress}:{port}/api/currentsettings`<br>
|
||||
**Method**: `GET`<br>
|
||||
|
||||
> `curl -X GET "http://127.0.0.1:7851/api/currentsettings"`
|
||||
|
||||
|
||||
```
|
||||
{
|
||||
"engines_available": ["parler", "piper", "vits", "xtts"],
|
||||
"current_engine_loaded": "xtts",
|
||||
"models_available": [
|
||||
{"name": "xtts - xttsv2_2.0.2"},
|
||||
{"name": "apitts - xttsv2_2.0.2"},
|
||||
{"name": "xtts - xttsv2_2.0.3"},
|
||||
{"name": "apitts - xttsv2_2.0.3"}
|
||||
],
|
||||
"current_model_loaded": "xtts - xttsv2_2.0.3",
|
||||
"manufacturer_name": "Coqui",
|
||||
"audio_format": "wav",
|
||||
"deepspeed_capable": true,
|
||||
"deepspeed_available": true,
|
||||
"deepspeed_enabled": true,
|
||||
"generationspeed_capable": true,
|
||||
"generationspeed_set": 1,
|
||||
"lowvram_capable": true,
|
||||
"lowvram_enabled": false,
|
||||
"pitch_capable": false,
|
||||
"pitch_set": 0,
|
||||
"repetitionpenalty_capable": true,
|
||||
"repetitionpenalty_set": 10,
|
||||
"streaming_capable": true,
|
||||
"temperature_capable": true,
|
||||
"temperature_set": 0.75,
|
||||
"ttsengines_installed": true,
|
||||
"languages_capable": true,
|
||||
"multivoice_capable": true,
|
||||
"multimodel_capable": true
|
||||
}
|
||||
```
|
||||
|
||||
#### **engines_available**
|
||||
> Lists the currently available TTS engines that can be loaded.
|
||||
|
||||
#### **current_engine_loaded**
|
||||
> Shows the currently loaded TTS engine.
|
||||
These can be used together with the **/api/enginereload** endpoint to determine and change the currently loaded engine. Note that swapping the engine using this method can cause the main script process of AllTalk to lose sync with the subprocess. This results in a message indicating that script.py lost control of the subprocess when exiting AllTalk.
|
||||
|
||||
#### **models_available**
|
||||
> Lists all the models available for the currently loaded TTS engine. Displayed as {engine-name - model-name} from models_available.
|
||||
|
||||
#### **current_model_loaded**
|
||||
> Shows the currently loaded model.
|
||||
You can swap models using the **/api/reload** endpoint by specifying the full {enginename - modelname}.
|
||||
|
||||
#### **audio_format**
|
||||
> The primary format in which the currently loaded engine produces audio output. This does not account for any global transcoding settings in the AllTalk Settings page but is used by the transcoding process to determine if transcoding is necessary.
|
||||
|
||||
#### **deepspeed_capable**
|
||||
> Indicates if the current TTS engine supports DeepSpeed and can handle DeepSpeed enable/disable requests.
|
||||
|
||||
#### **deepspeed_available**
|
||||
> If the current TTS engine is DeepSpeed capable, shows whether DeepSpeed was detected and loaded for use.
|
||||
|
||||
#### **deepspeed_enabled**
|
||||
> Indicates whether DeepSpeed is currently enabled or disabled for the current TTS engine, assuming the above two are true.
|
||||
|
||||
#### **generationspeed_capable**
|
||||
> Indicates if the current TTS engine supports generating TTS at different speeds.
|
||||
|
||||
#### **generationspeed_set**
|
||||
> Shows the current default speed set in the TTS engine's configuration settings.
|
||||
|
||||
#### **lowvram_capable**
|
||||
> Indicates if the current TTS engine allows moving the TTS model between VRAM and System RAM, which is useful in low VRAM situations, such as when using AllTalk with an LLM that fills up VRAM. This helps keep models contiguous within VRAM and speeds up processing.
|
||||
|
||||
#### **lowvram_enabled**
|
||||
> If the model is lowvram_capable, setting this to true allows the model to move between VRAM and System RAM as necessary.
|
||||
|
||||
#### **pitch_capable**
|
||||
> Indicates if the current TTS engine supports generating TTS at different pitches.
|
||||
|
||||
#### **pitch_set**
|
||||
> Shows the current default audio pitch set in the TTS engine's configuration settings.
|
||||
|
||||
#### **repetitionpenalty_capable**
|
||||
> Indicates if the current TTS engine supports different repetition penalties for its TTS models.
|
||||
|
||||
#### **repetitionpenalty_set**
|
||||
> Shows the current default repetition penalty set in the TTS engine's configuration settings.
|
||||
|
||||
#### **temperature_capable**
|
||||
> Indicates if the current TTS engine supports different temperature settings for its TTS models.
|
||||
|
||||
#### **temperature_set**
|
||||
> Shows the current default temperature set in the TTS engine's configuration settings.
|
||||
|
||||
#### **languages_capable**
|
||||
> Indicates if the models within the current TTS engine support multiple languages. This can be used to disable language selection in your interface if necessary.
|
||||
|
||||
#### **multivoice_capable**
|
||||
> Indicates if the current model loaded into the TTS engine supports multiple voices or just one voice. If a model is not multi-voice capable, you can display 'Default' as the only available voice.
|
||||
|
||||
#### **multimodel_capable**
|
||||
> Some TTS engines, such as Piper, use models as voices. In such cases, you don't need to load different models but present the models as voices. If a model is not multimodel_capable, it indicates this status in your interface.
|
||||
|
||||
"""
|
||||
|
||||
openapi_endpoint = """
|
||||
### 🟠 OpenAI Speech API Compatible Endpoint<br>
|
||||
Validate and generate audio based on text input using an OpenAI Speech v1 API compatible endpoint, as per the documentation at [OpenAI Text-to-Speech Guide](https://platform.openai.com/docs/guides/text-to-speech) and [OpenAI API Reference](https://platform.openai.com/docs/api-reference/audio).
|
||||
|
||||
Voices are mapped on a one-to-one basis within the AllTalk Gradio interface on a TTS engine by TTS engine basis. If RVC is globally enabled in AllTalk settings and a voice other than "Disabled" is selected for the character voice, the chosen RVC voice will be applied after the TTS is generated and before the audio is transcoded and sent back out.
|
||||
|
||||
Note that there is no capability within the OpenAI API to specify a language, so the response will be in whatever language the currently loaded TTS engine and model support.
|
||||
|
||||
**URL**: `http://{ipaddress}:{port}/v1/audio/speech`<br>
|
||||
**Method**: `POST`<br>
|
||||
|
||||
`curl -X POST "http://127.0.0.1:7851/v1/audio/speech" -H "Content-Type: application/json" -d "{\"model\":\"any_model_name\",\"input\":\"Hello, this is a test.\",\"voice\":\"nova\",\"response_format\":\"wav\",\"speed\":1.0}"`
|
||||
|
||||
The request body must be a JSON object with the following fields:
|
||||
|
||||
**model** (string): The TTS model to use. Currently ignored, but is required in the request.<br>
|
||||
**input** (string): The text to generate audio for. Maximum length is 4096 characters.<br>
|
||||
**voice** (string): The voice to use when generating the audio. Supported voices are ["alloy", "echo", "fable", "nova", "onyx", "shimmer"].<br>
|
||||
**response_format** (string, optional): The format of the audio. Audio will be transcoded to the requested format.<br>
|
||||
**speed** (float, optional): The speed of the generated audio. Must be between 0.25 and 4.0. Default is 1.0. Id the TTS engine loaded doesnt support different speeds, then the audio generated will not abide by this speed request.<br><br>
|
||||
|
||||
```
|
||||
{
|
||||
"model": "any_model_name",
|
||||
"input": "Hello, this is a test.",
|
||||
"voice": "nova",
|
||||
"response_format": "wav",
|
||||
"speed": 1.0
|
||||
}
|
||||
```
|
||||
|
||||
#### Python Example
|
||||
```
|
||||
import requests
|
||||
import json
|
||||
|
||||
# Define the endpoint URL
|
||||
url = "http://127.0.0.1:7851/v1/audio/speech"
|
||||
|
||||
# Define the request payload
|
||||
payload = {
|
||||
"model": "any_model_name",
|
||||
"input": "Hello, this is a test.",
|
||||
"voice": "nova",
|
||||
"response_format": "wav",
|
||||
"speed": 1.0
|
||||
}
|
||||
|
||||
# Set the headers
|
||||
headers = {
|
||||
"Content-Type": "application/json"
|
||||
}
|
||||
|
||||
# Send the POST request
|
||||
response = requests.post(url, data=json.dumps(payload), headers=headers)
|
||||
|
||||
# Check the response
|
||||
if response.status_code == 200:
|
||||
with open("output.wav", "wb") as f:
|
||||
f.write(response.content)
|
||||
print("Audio file saved as output.wav")
|
||||
else:
|
||||
print(f"Error: {response.status_code} - {response.text}")
|
||||
```
|
||||
#### Javascript Example
|
||||
```
|
||||
// Define the endpoint URL
|
||||
const url = "http://127.0.0.1:7851/v1/audio/speech";
|
||||
|
||||
// Define the request payload
|
||||
const payload = {
|
||||
model: "any_model_name",
|
||||
input: "Hello, this is a test.",
|
||||
voice: "nova",
|
||||
response_format: "wav",
|
||||
speed: 1.0
|
||||
};
|
||||
|
||||
// Set the headers
|
||||
const headers = {
|
||||
"Content-Type": "application/json"
|
||||
};
|
||||
|
||||
// Send the POST request
|
||||
fetch(url, {
|
||||
method: "POST",
|
||||
headers: headers,
|
||||
body: JSON.stringify(payload)
|
||||
})
|
||||
.then(response => {
|
||||
if (response.ok) {
|
||||
return response.blob();
|
||||
} else {
|
||||
return response.text().then(text => { throw new Error(text); });
|
||||
}
|
||||
})
|
||||
.then(blob => {
|
||||
// Create a link element
|
||||
const url = window.URL.createObjectURL(blob);
|
||||
const a = document.createElement('a');
|
||||
a.style.display = 'none';
|
||||
a.href = url;
|
||||
a.download = 'output.wav';
|
||||
|
||||
// Append the link to the body
|
||||
document.body.appendChild(a);
|
||||
|
||||
// Programmatically click the link to trigger the download
|
||||
a.click();
|
||||
|
||||
// Remove the link from the document
|
||||
window.URL.revokeObjectURL(url);
|
||||
document.body.removeChild(a);
|
||||
|
||||
console.log("Audio file saved as output.wav");
|
||||
})
|
||||
.catch(error => {
|
||||
console.error("Error:", error);
|
||||
});
|
||||
```
|
||||
|
||||
"""
|
||||
|
||||
interaction_endpoints = """
|
||||
### 🟠 Stop Generation Endpoint<br>
|
||||
Interrupt the current TTS generation process. When this endpoint is called, it sets tts_stop_generation in the model_engine to True, which can be used to interrupt the current TTS generation. Stop requests will only be honored if the current TTS engine is capable of handling and can honor a stop request partway through generation.
|
||||
|
||||
**URL**: `http://{ipaddress}:{port}/api/stop-generation`<br>
|
||||
**Method**: `PUT`<br>
|
||||
|
||||
> `curl -X PUT "http://127.0.0.1:7851/api/stop-generation"`
|
||||
|
||||
```
|
||||
{
|
||||
"message": "Cancelling current TTS generation"
|
||||
}
|
||||
```
|
||||
|
||||
### 🟠 Reload Configuration Endpoint<br>
|
||||
Reload the TTS engine's configuration and scan for new voices and models. When this endpoint is called, it reloads all current settings from the configuration files and scans for new voices and models that are available. This ensures that subsequent calls to /api/currentsettings, /api/voices, and /api/rvcvoices return an up-to-date set of settings and information about the current state of the TTS engine.
|
||||
|
||||
**URL**: `http://{ipaddress}:{port}/api/reload_config`<br>
|
||||
**Method**: `GET`<br>
|
||||
|
||||
> `curl -X GET "http://127.0.0.1:7851/api/reload_config"`
|
||||
|
||||
`Config file reloaded successfully`
|
||||
|
||||
### 🟠 Reload/Swap model<br>
|
||||
Can be used to load in/swap to one of the models presented by /api/currentsettings in the `models_available` list.
|
||||
|
||||
**URL**: `http://{ipaddress}:{port}/api/reload?tts_method=x`<br>
|
||||
**Method**: `POST`<br>
|
||||
|
||||
> `curl -X POST "http://127.0.0.1:7851/api/reload?tts_method=xtts%20-%20xttsv2_2.0.2"`
|
||||
|
||||
{"status": "model-success"} or {"status": "model-failure"}
|
||||
|
||||
### 🟠 Switch DeepSpeed Endpoint<br>
|
||||
|
||||
**URL**: `http://{ipaddress}:{port}/api/deepspeed`<br>
|
||||
**Method**: `POST`<br>
|
||||
|
||||
> `curl -X POST "http://127.0.0.1:7851/api/deepspeed?new_deepspeed_value=True"`
|
||||
|
||||
Replace True with False to disable DeepSpeed mode.
|
||||
|
||||
```
|
||||
{
|
||||
"status": "deepspeed-success"
|
||||
}
|
||||
```
|
||||
|
||||
### 🟠 Switching Low VRAM Endpoint<br>
|
||||
|
||||
**URL**: `http://{ipaddress}:{port}/api/lowvramsetting`<br>
|
||||
**Method: `POST`<br>
|
||||
|
||||
> `curl -X POST "http://127.0.0.1:7851/api/lowvramsetting?new_low_vram_value=True"`
|
||||
|
||||
Replace True with False to disable Low VRAM mode.
|
||||
|
||||
```
|
||||
{
|
||||
"status": "lowvram-success"
|
||||
}
|
||||
```
|
||||
"""
|
||||
|
||||
standardtts_endpoint = """
|
||||
### 🟠 TTS Generation Endpoint (Standard Generation)<br>
|
||||
Generate TTS audio based on text input. This endpoint supports both character and narrator speech generation. All global settings for the API endpoint can be configured within the AllTalk interface under Global Settings > AllTalk API Defaults. TTS engine-specific settings, such as voices to use or engine parameters, can be set on an engine-by-engine basis in TTS Engine Settings > TTS Engine of your choice.<br>
|
||||
|
||||
It's important to note that although you can send all these variables/settings, the loaded TTS engine will only support them if it is capable e.g. you can request a TTS generation in Russian, but if the TTS model that is loaded in only support English, it's only going to generate english sounding text to speech.<br>
|
||||
|
||||
**URL**: `http://{ipaddress}:{port}/api/tts-generate`<br>
|
||||
**Method**: `POST`<br>
|
||||
**Content-Type**: application/x-www-form-urlencoded<br>
|
||||
|
||||
### 🟠 Example Command Lines (Standard Generation)
|
||||
Standard TTS generation supports narration and generates a WAV file/blob.
|
||||
|
||||
> **Standard TTS Speech Example** - Generate a time-stamped file for standard text:<br><br>
|
||||
`curl -X POST "http://127.0.0.1:7851/api/tts-generate" -d "text_input=All of this is text spoken by the character. This is text not inside quotes, though that doesnt matter in the slightest" -d "text_filtering=standard" -d "character_voice_gen=female_01.wav" -d "narrator_enabled=false" -d "narrator_voice_gen=male_01.wav" -d "text_not_inside=character" -d "language=en" -d "output_file_name=myoutputfile" -d "output_file_timestamp=true" -d "autoplay=true" -d "autoplay_volume=0.8"`
|
||||
|
||||
> **Narrator Example** - Generate a time-stamped file for text with narrator and character speech:<br><br>
|
||||
`curl -X POST "http://127.0.0.1:7851/api/tts-generate" -d "text_input=*This is text spoken by the narrator* \\\"This is text spoken by the character\\\;". This is text not inside quotes." -d "text_filtering=standard" -d "character_voice_gen=female_01.wav" -d "narrator_enabled=true" -d "narrator_voice_gen=male_01.wav" -d "text_not_inside=character" -d "language=en" -d "output_file_name=myoutputfile" -d "output_file_timestamp=true" -d "autoplay=true" -d "autoplay_volume=0.8"`<br>
|
||||
|
||||
> If your text contains double quotes, escape them with \" (see the narrator example).<br>
|
||||
Voices sent in the request have to match the voices available within the TTS engine loaded. Generation requests where the voices dont match, will result nothing being generated and possibly an error message.
|
||||
|
||||
Because of the way AllTalk works you can send a request with any mix of settings you wish e.g.
|
||||
|
||||
> `curl -X POST "http://127.0.0.1:7851/api/tts-generate" -d "text_input=All of this is text spoken by the character. This is text not inside quotes, though that doesnt matter in the slightest"`
|
||||
|
||||
Would generate the TTS for whatver engine is curretly loaded in. It will use the default API settings and default TTS engine settings to populate any missing fields, which gives you flexibility on how you want to send API requests to AllTalk.
|
||||
|
||||
### 🟠 Request Parameters
|
||||
#### **text_input**
|
||||
> The text you want the TTS engine to produce. Use escaped double quotes for character speech and asterisks for narrator speech if using the narrator function. Example:<br><br>
|
||||
-d "text_input=*This is text spoken by the narrator* \"This is text spoken by the character\". This is text not inside quotes."
|
||||
|
||||
#### **text_filtering**
|
||||
> Filter for text. Options:<br><br>
|
||||
**none**: No filtering. Raw text is sent to the TTS engine.<br>
|
||||
**standard**: Basic level of filtering to clean up special characters.<br>
|
||||
**html**: For HTML content with entities like ".<br><br>
|
||||
-d "text_filtering=none"<br>
|
||||
-d "text_filtering=standard"<br>
|
||||
-d "text_filtering=html"<br>
|
||||
|
||||
#### **character_voice_gen**
|
||||
> The name of the character's voice file (WAV format).<br><br>
|
||||
-d "character_voice_gen=female_01.wav"
|
||||
|
||||
#### **rvccharacter_voice_gen**
|
||||
> The name of the RVC voice file for the character. Should be in the format `folder\\file.pth` or the word `Disabled`. When Disabled is sent and RVC is globally enabled, the RVC pipeline will not be used for the character/main voice.<br><br>
|
||||
-d "rvccharacter_voice_gen=folder\\voice1.pth"
|
||||
|
||||
#### **narrator_enabled**
|
||||
> Enable or disable the narrator function. If true, minimum text filtering is set to standard.<br><br>
|
||||
-d "narrator_enabled=true"<br>
|
||||
-d "narrator_enabled=false"
|
||||
|
||||
#### **narrator_voice_gen**
|
||||
> The name of the narrator's voice file (WAV format).<br><br>
|
||||
-d "narrator_voice_gen=male_01.wav"
|
||||
|
||||
#### **rvcnarrator_voice_gen**
|
||||
> The name of the RVC voice file for the narrator. Should be in the format folder\\file.pth or the word Disabled. When Disabled is sent and RVC is globally enabled, the RVC pipeline will not be used for the character/main voice.<br><br>
|
||||
-d "rvcnarrator_voice_gen=folder\\voice2.pth"
|
||||
|
||||
#### **text_not_inside**
|
||||
> Specify the handling of lines not inside double quotes or asterisks for the narrator feature. Options:<br><br>
|
||||
**character**: Treat as character speech.<br>
|
||||
**narrator**: Treat as narrator speech.<br>
|
||||
**silent**: Ignore text not inside quotes or asterisks.<br><br>
|
||||
-d "text_not_inside=character"<br>
|
||||
-d "text_not_inside=narrator"<br>
|
||||
-d "text_not_inside=silent"<br>
|
||||
|
||||
#### **language**
|
||||
> Choose the language for TTS. Options:<br><br>
|
||||
**ar**: Arabic<br>
|
||||
**zh-cn**: Chinese (Simplified)<br>
|
||||
**cs**: Czech<br>
|
||||
**nl**: Dutch<br>
|
||||
**en**: English<br>
|
||||
**fr**: French<br>
|
||||
**de**: German<br>
|
||||
**hi**: Hindi (limited support)<br>
|
||||
**hu**: Hungarian<br>
|
||||
**it**: Italian<br>
|
||||
**ja**: Japanese<br>
|
||||
**ko**: Korean<br>
|
||||
**pl**: Polish<br>
|
||||
**pt**: Portuguese<br>
|
||||
**ru**: Russian<br>
|
||||
**es**: Spanish<br>
|
||||
**tr**: Turkish<br><br>
|
||||
-d "language=en"
|
||||
|
||||
#### **output_file_name***
|
||||
> The name of the output file (excluding the .wav extension).<br><br>
|
||||
--d "output_file_name=myoutputfile"
|
||||
|
||||
#### **output_file_timestamp**
|
||||
> Add a timestamp to the output file name. If true, each file will have a unique timestamp; otherwise, the same file name will be overwritten each time you generate TTS.<br><br>
|
||||
--d "output_file_timestamp=true"<br>
|
||||
--d "output_file_timestamp=false"
|
||||
|
||||
#### **autoplay**
|
||||
> Enable or disable playing the generated TTS to your standard sound output device at the time of TTS generation.<br><br>
|
||||
--d "autoplay=true"<br>
|
||||
--d "autoplay=false"
|
||||
|
||||
#### **autoplay_volume**
|
||||
> Set the autoplay volume. Should be between 0.1 and 1.0.<br><br>
|
||||
--d "autoplay_volume=0.8"
|
||||
|
||||
#### **speed**
|
||||
> Set the speed of the generated audio. Should be between 0.25 and 2.0.<br><br>
|
||||
--d "speed=1.0"
|
||||
|
||||
#### **pitch**
|
||||
> Set the pitch of the generated audio. Should be between -10 and 10.<br><br>
|
||||
--d "pitch=0"
|
||||
|
||||
#### **temperature**
|
||||
> Set the temperature for the TTS engine. Should be between 0.1 and 1.0.<br><br>
|
||||
--d "temperature=0.75"
|
||||
|
||||
#### **repetition_penalty**
|
||||
> Set the repetition penalty for the TTS engine. Should be between 1.0 and 20.0.<br><br>
|
||||
--d "repetition_penalty=10"
|
||||
|
||||
### 🟠 TTS Generation Response
|
||||
> The API returns a JSON object with the following properties:<br><br>
|
||||
**status**: Indicates whether the generation was successful (generate-success) or failed (generate-failure).<br>
|
||||
**output_file_path**: The on-disk location of the generated WAV file.<br>
|
||||
**output_file_url**: The HTTP location for accessing the generated WAV file for browser playback.<br>
|
||||
**output_cache_url**: The HTTP location for accessing the generated WAV file as a pushed download.<br>
|
||||
|
||||
```
|
||||
{
|
||||
"status": "generate-success",
|
||||
"output_file_path": "C:\\text-generation-webui\\extensions\\alltalk_tts\\outputs\\myoutputfile_1704141936.wav",
|
||||
"output_file_url": "/audio/myoutputfile_1704141936.wav",
|
||||
"output_cache_url": "/audiocache/myoutputfile_1704141936.wav"
|
||||
}
|
||||
```
|
||||
<br>
|
||||
Note: The response no longer includes the IP address and port number. You will need to add these in your own software/extension.
|
||||
"""
|
||||
|
||||
streamingtts_endpoint = """
|
||||
### 🟠 TTS Generation Endpoint (Streaming Generation)
|
||||
Generate TTS audio as a stream. This endpoint does not support narration and will generate an audio stream, not a file. It also does not support the RVC pipeline. Generate and stream TTS audio directly for real-time playback.
|
||||
|
||||
**URL**: `http://{ipaddress}:{port}/api/tts-generate-streaming`<br>
|
||||
**Method**: POST<br>
|
||||
**Content-Type**: application/x-www-form-urlencoded<br>
|
||||
|
||||
> `http://127.0.0.1:7851/api/tts-generate-streaming?text=Here%20is%20some%20text&voice=female_01.wav&language=en&output_file=stream_output.wav`
|
||||
|
||||
Example JavaScript for Streaming Playback:
|
||||
|
||||
```
|
||||
const text = "Here is some text";
|
||||
const voice = "female_01.wav";
|
||||
const language = "en";
|
||||
const outputFile = "stream_output.wav";
|
||||
const encodedText = encodeURIComponent(text);
|
||||
const streamingUrl = `http://localhost:7851/api/tts-generate-streaming?text=${encodedText}&voice=${voice}&language=${language}&output_file=${outputFile}`;
|
||||
const audioElement = new Audio(streamingUrl);
|
||||
audioElement.play();
|
||||
```
|
||||
|
||||
Response: A StreamingResponse for the audio stream.
|
||||
|
||||
Request Parameters:
|
||||
|
||||
**text**: The text to convert to speech.<br>
|
||||
**voice**: The voice type to use.<br>
|
||||
**language**: The language for the TTS.<br>
|
||||
**output_file**: The name of the output file.<br>
|
||||
**Response**: A JSON object indicating the status of the request.
|
||||
|
||||
```
|
||||
{
|
||||
"output_file_path": "stream_output.wav"
|
||||
}
|
||||
```
|
||||
"""
|
||||
|
||||
with gr.Tab("API Endpoints & Dev"):
|
||||
with gr.Tab("Best Development Practices"): gr.Markdown(best_practices)
|
||||
with gr.Tab("Standard TTS Generation"): gr.Markdown(standardtts_endpoint)
|
||||
with gr.Tab("Streaming TTS Generation"): gr.Markdown(streamingtts_endpoint)
|
||||
with gr.Tab("Settings API's"): gr.Markdown(settings_endpoints)
|
||||
with gr.Tab("Interaction API's"): gr.Markdown(interaction_endpoints)
|
||||
with gr.Tab("OpenAPI Compatible Endpoint"): gr.Markdown(openapi_endpoint)
|
||||
@@ -0,0 +1,114 @@
|
||||
import os
|
||||
import json
|
||||
import sys
|
||||
import importlib
|
||||
|
||||
# Hard-coded paths
|
||||
this_folder = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..", ".."))
|
||||
config_file = os.path.join(this_folder, "confignew.json")
|
||||
gradio_pages_folder = os.path.join(this_folder, "system", "gradio_pages", "themes")
|
||||
theme_list_file = os.path.join(gradio_pages_folder, "theme_list.json")
|
||||
themes_file_path = os.path.join(gradio_pages_folder, "themes.py")
|
||||
|
||||
# Add gradio_pages folder to the system path
|
||||
sys.path.append(gradio_pages_folder)
|
||||
|
||||
def get_class(filename):
|
||||
with open(filename, "r", encoding="utf8") as file:
|
||||
for line in file:
|
||||
if "class " in line:
|
||||
return line.split("class ")[1].split(":")[0].split("(")[0].strip()
|
||||
return None
|
||||
|
||||
|
||||
def get_list():
|
||||
themes_from_files = [
|
||||
os.path.splitext(name)[0]
|
||||
for name in os.listdir(gradio_pages_folder)
|
||||
if name.endswith(".py")
|
||||
]
|
||||
try:
|
||||
with open(theme_list_file, "r", encoding="utf8") as json_file:
|
||||
themes_from_url = [item["id"] for item in json.load(json_file)]
|
||||
except FileNotFoundError:
|
||||
themes_from_url = []
|
||||
|
||||
combined_themes = sorted(set(themes_from_files + themes_from_url))
|
||||
return list(combined_themes)
|
||||
|
||||
|
||||
def select_theme(name):
|
||||
selected_file = name + ".py"
|
||||
full_path = os.path.join(gradio_pages_folder, selected_file)
|
||||
|
||||
try:
|
||||
with open(config_file, "r", encoding="utf8") as json_file:
|
||||
config_data = json.load(json_file)
|
||||
|
||||
if not os.path.exists(full_path):
|
||||
# If the theme is from theme_list.json, update only the class field
|
||||
config_data["theme"]["file"] = None
|
||||
config_data["theme"]["class"] = name
|
||||
message = f"Theme {name} successfully selected, restart AllTalk."
|
||||
else:
|
||||
# If the theme file exists locally, update both file and class fields
|
||||
class_found = get_class(full_path)
|
||||
if class_found:
|
||||
config_data["theme"]["file"] = selected_file
|
||||
config_data["theme"]["class"] = class_found
|
||||
message = f"Theme {name} successfully selected, restart AllTalk."
|
||||
else:
|
||||
message = f"Theme {name} was not found."
|
||||
|
||||
with open(config_file, "w", encoding="utf8") as json_file:
|
||||
json.dump(config_data, json_file, indent=2)
|
||||
|
||||
print(message)
|
||||
return message
|
||||
|
||||
except Exception as e:
|
||||
print(f"[AllTalk TTS] Error selecting theme {name}: {str(e)}")
|
||||
return message
|
||||
|
||||
def read_json():
|
||||
try:
|
||||
with open(config_file, "r", encoding="utf8") as json_file:
|
||||
data = json.load(json_file)
|
||||
selected_file = data["theme"]["file"]
|
||||
class_name = data["theme"]["class"]
|
||||
|
||||
if selected_file and class_name:
|
||||
return class_name
|
||||
elif not selected_file and class_name:
|
||||
return class_name
|
||||
else:
|
||||
return "gradio/base"
|
||||
except Exception as e:
|
||||
print(f"[AllTalk TTS] Error reading config.json: {e}")
|
||||
return "gradio/base"
|
||||
|
||||
|
||||
def load_json():
|
||||
try:
|
||||
with open(config_file, "r", encoding="utf8") as json_file:
|
||||
data = json.load(json_file)
|
||||
selected_file = data["theme"]["file"]
|
||||
class_name = data["theme"]["class"]
|
||||
|
||||
if selected_file and class_name:
|
||||
module_name = os.path.splitext(selected_file)[0]
|
||||
module_spec = importlib.util.spec_from_file_location(module_name, themes_file_path)
|
||||
module = importlib.util.module_from_spec(module_spec)
|
||||
module_spec.loader.exec_module(module)
|
||||
obtained_class = getattr(module, class_name)
|
||||
instance = obtained_class()
|
||||
print(f"Theme Loaded: {class_name}")
|
||||
return instance
|
||||
elif not selected_file and class_name:
|
||||
return class_name
|
||||
else:
|
||||
print("The theme is incorrect.")
|
||||
return None
|
||||
except Exception as e:
|
||||
print(f"Error Loading: {str(e)}")
|
||||
return None
|
||||
@@ -0,0 +1,81 @@
|
||||
[
|
||||
{"id": "freddyaboulton/dracula_revamped"},
|
||||
{"id": "freddyaboulton/bad-theme-space"},
|
||||
{"id": "gradio/dracula_revamped"},
|
||||
{"id": "abidlabs/dracula_revamped"},
|
||||
{"id": "gradio/dracula_test"},
|
||||
{"id": "abidlabs/dracula_test"},
|
||||
{"id": "gradio/seafoam"},
|
||||
{"id": "gradio/glass"},
|
||||
{"id": "gradio/monochrome"},
|
||||
{"id": "gradio/soft"},
|
||||
{"id": "gradio/default"},
|
||||
{"id": "gradio/base"},
|
||||
{"id": "abidlabs/pakistan"},
|
||||
{"id": "dawood/microsoft_windows"},
|
||||
{"id": "ysharma/steampunk"},
|
||||
{"id": "ysharma/huggingface"},
|
||||
{"id": "gstaff/xkcd"},
|
||||
{"id": "JohnSmith9982/small_and_pretty"},
|
||||
{"id": "abidlabs/Lime"},
|
||||
{"id": "freddyaboulton/this-theme-does-not-exist-2"},
|
||||
{"id": "aliabid94/new-theme"},
|
||||
{"id": "aliabid94/test2"},
|
||||
{"id": "aliabid94/test3"},
|
||||
{"id": "aliabid94/test4"},
|
||||
{"id": "abidlabs/banana"},
|
||||
{"id": "freddyaboulton/test-blue"},
|
||||
{"id": "gstaff/sketch"},
|
||||
{"id": "gstaff/whiteboard"},
|
||||
{"id": "ysharma/llamas"},
|
||||
{"id": "abidlabs/font-test"},
|
||||
{"id": "YenLai/Superhuman"},
|
||||
{"id": "bethecloud/storj_theme"},
|
||||
{"id": "sudeepshouche/minimalist"},
|
||||
{"id": "knotdgaf/gradiotest"},
|
||||
{"id": "ParityError/Interstellar"},
|
||||
{"id": "ParityError/Anime"},
|
||||
{"id": "Ajaxon6255/Emerald_Isle"},
|
||||
{"id": "ParityError/LimeFace"},
|
||||
{"id": "finlaymacklon/smooth_slate"},
|
||||
{"id": "finlaymacklon/boxy_violet"},
|
||||
{"id": "derekzen/stardust"},
|
||||
{"id": "EveryPizza/Cartoony-Gradio-Theme"},
|
||||
{"id": "Ifeanyi/Cyanister"},
|
||||
{"id": "Tshackelton/IBMPlex-DenseReadable"},
|
||||
{"id": "snehilsanyal/scikit-learn"},
|
||||
{"id": "Himhimhim/xkcd"},
|
||||
{"id": "shivi/calm_seafoam"},
|
||||
{"id": "nota-ai/theme"},
|
||||
{"id": "rawrsor1/Everforest"},
|
||||
{"id": "SebastianBravo/simci_css"},
|
||||
{"id": "rottenlittlecreature/Moon_Goblin"},
|
||||
{"id": "abidlabs/test-yellow"},
|
||||
{"id": "abidlabs/test-yellow3"},
|
||||
{"id": "idspicQstitho/dracula_revamped"},
|
||||
{"id": "kfahn/AnimalPose"},
|
||||
{"id": "HaleyCH/HaleyCH_Theme"},
|
||||
{"id": "simulKitke/dracula_test"},
|
||||
{"id": "braintacles/CrimsonNight"},
|
||||
{"id": "wentaohe/whiteboardv2"},
|
||||
{"id": "reilnuud/polite"},
|
||||
{"id": "remilia/Ghostly"},
|
||||
{"id": "Franklisi/darkmode"},
|
||||
{"id": "coding-alt/soft"},
|
||||
{"id": "xiaobaiyuan/theme_land"},
|
||||
{"id": "step-3-profit/Midnight-Deep"},
|
||||
{"id": "xiaobaiyuan/theme_demo"},
|
||||
{"id": "Taithrah/Minimal"},
|
||||
{"id": "Insuz/SimpleIndigo"},
|
||||
{"id": "zkunn/Alipay_Gradio_theme"},
|
||||
{"id": "Insuz/Mocha"},
|
||||
{"id": "xiaobaiyuan/theme_brief"},
|
||||
{"id": "Ama434/434-base-Barlow"},
|
||||
{"id": "Ama434/def_barlow"},
|
||||
{"id": "Ama434/neutral-barlow"},
|
||||
{"id": "dawood/dracula_test"},
|
||||
{"id": "nuttea/Softblue"},
|
||||
{"id": "BlueDancer/Alien_Diffusion"},
|
||||
{"id": "naughtondale/monochrome"},
|
||||
{"id": "Dagfinn1962/standard"}
|
||||
]
|
||||
@@ -0,0 +1,284 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Iterable
|
||||
import gradio as gr
|
||||
|
||||
# gr.themes.builder()
|
||||
from gradio.themes.base import Base
|
||||
from gradio.themes.utils import colors, fonts, sizes
|
||||
import time
|
||||
|
||||
|
||||
class alltalk(Base):
|
||||
def __init__(
|
||||
self,
|
||||
*,
|
||||
primary_hue: colors.Color | str = colors.neutral,
|
||||
secondary_hue: colors.Color | str = colors.neutral,
|
||||
neutral_hue: colors.Color | str = colors.neutral,
|
||||
spacing_size: sizes.Size | str = sizes.spacing_md,
|
||||
radius_size: sizes.Size | str = sizes.radius_md,
|
||||
text_size: sizes.Size | str = sizes.text_lg,
|
||||
font: fonts.Font | str | Iterable[fonts.Font | str] = (
|
||||
"Syne V",
|
||||
fonts.GoogleFont("Syne"),
|
||||
"ui-sans-serif",
|
||||
"system-ui",
|
||||
),
|
||||
font_mono: fonts.Font | str | Iterable[fonts.Font | str] = (
|
||||
"ui-monospace",
|
||||
fonts.GoogleFont("Nunito Sans"),
|
||||
),
|
||||
):
|
||||
super().__init__(
|
||||
primary_hue=primary_hue,
|
||||
secondary_hue=secondary_hue,
|
||||
neutral_hue=neutral_hue,
|
||||
spacing_size=spacing_size,
|
||||
radius_size=radius_size,
|
||||
text_size=text_size,
|
||||
font=font,
|
||||
font_mono=font_mono,
|
||||
)
|
||||
self.name = ("alltalk",)
|
||||
self.secondary_100 = ("#dbeafe",)
|
||||
self.secondary_200 = ("#bfdbfe",)
|
||||
self.secondary_300 = ("#93c5fd",)
|
||||
self.secondary_400 = ("#60a5fa",)
|
||||
self.secondary_50 = ("#eff6ff",)
|
||||
self.secondary_500 = ("#3b82f6",)
|
||||
self.secondary_600 = ("#2563eb",)
|
||||
self.secondary_700 = ("#1d4ed8",)
|
||||
self.secondary_800 = ("#1e40af",)
|
||||
self.secondary_900 = ("#1e3a8a",)
|
||||
self.secondary_950 = ("#1d3660",)
|
||||
|
||||
super().set(
|
||||
# Blaise
|
||||
background_fill_primary="#110F0F",
|
||||
background_fill_primary_dark="#110F0F",
|
||||
background_fill_secondary="#110F0F",
|
||||
background_fill_secondary_dark="#110F0F",
|
||||
block_background_fill="*neutral_800",
|
||||
block_background_fill_dark="*neutral_800",
|
||||
block_border_color="*border_color_primary",
|
||||
block_border_color_dark="*border_color_primary",
|
||||
block_border_width="1px",
|
||||
block_border_width_dark="1px",
|
||||
block_info_text_color="*body_text_color_subdued",
|
||||
block_info_text_color_dark="*body_text_color_subdued",
|
||||
block_info_text_size="*text_sm",
|
||||
block_info_text_weight="400",
|
||||
block_label_background_fill="*background_fill_primary",
|
||||
block_label_background_fill_dark="*background_fill_secondary",
|
||||
block_label_border_color="*border_color_primary",
|
||||
block_label_border_color_dark="*border_color_primary",
|
||||
block_label_border_width="1px",
|
||||
block_label_border_width_dark="1px",
|
||||
block_label_margin="0",
|
||||
block_label_padding="*spacing_sm *spacing_lg",
|
||||
block_label_radius="calc(*radius_lg - 1px) 0 calc(*radius_lg - 1px) 0",
|
||||
block_label_right_radius="0 calc(*radius_lg - 1px) 0 calc(*radius_lg - 1px)",
|
||||
block_label_shadow="*block_shadow",
|
||||
block_label_text_color="*#110F0F",
|
||||
block_label_text_color_dark="*#110F0F",
|
||||
block_label_text_weight="400",
|
||||
block_padding="*spacing_xl",
|
||||
block_radius="*radius_md",
|
||||
block_shadow="none",
|
||||
block_shadow_dark="none",
|
||||
block_title_background_fill="rgb(255,255,255)",
|
||||
block_title_background_fill_dark="rgb(255,255,255)",
|
||||
block_title_border_color="none",
|
||||
block_title_border_color_dark="none",
|
||||
block_title_border_width="0px",
|
||||
block_title_padding="*block_label_padding",
|
||||
block_title_radius="*block_label_radius",
|
||||
block_title_text_color="#110F0F",
|
||||
block_title_text_color_dark="#110F0F",
|
||||
block_title_text_size="*text_md",
|
||||
block_title_text_weight="600",
|
||||
body_background_fill="#110F0F",
|
||||
body_background_fill_dark="#110F0F",
|
||||
body_text_color="white",
|
||||
body_text_color_dark="white",
|
||||
body_text_color_subdued="*neutral_400",
|
||||
body_text_color_subdued_dark="*neutral_400",
|
||||
body_text_size="*text_md",
|
||||
body_text_weight="400",
|
||||
border_color_accent="*neutral_600",
|
||||
border_color_accent_dark="*neutral_600",
|
||||
border_color_primary="*neutral_800",
|
||||
border_color_primary_dark="*neutral_800",
|
||||
button_border_width="*input_border_width",
|
||||
button_border_width_dark="*input_border_width",
|
||||
button_cancel_background_fill="*button_secondary_background_fill",
|
||||
button_cancel_background_fill_dark="*button_secondary_background_fill",
|
||||
button_cancel_background_fill_hover="*button_cancel_background_fill",
|
||||
button_cancel_background_fill_hover_dark="*button_cancel_background_fill",
|
||||
button_cancel_border_color="*button_secondary_border_color",
|
||||
button_cancel_border_color_dark="*button_secondary_border_color",
|
||||
button_cancel_border_color_hover="*button_cancel_border_color",
|
||||
button_cancel_border_color_hover_dark="*button_cancel_border_color",
|
||||
button_cancel_text_color="#110F0F",
|
||||
button_cancel_text_color_dark="#110F0F",
|
||||
button_cancel_text_color_hover="#110F0F",
|
||||
button_cancel_text_color_hover_dark="#110F0F",
|
||||
button_large_padding="*spacing_lg calc(2 * *spacing_lg)",
|
||||
button_large_radius="*radius_lg",
|
||||
button_large_text_size="*text_lg",
|
||||
button_large_text_weight="600",
|
||||
button_primary_background_fill="*primary_600",
|
||||
button_primary_background_fill_dark="*primary_600",
|
||||
button_primary_background_fill_hover="*primary_500",
|
||||
button_primary_background_fill_hover_dark="*primary_500",
|
||||
button_primary_border_color="*primary_500",
|
||||
button_primary_border_color_dark="*primary_500",
|
||||
button_primary_border_color_hover="*primary_400",
|
||||
button_primary_border_color_hover_dark="*primary_400",
|
||||
button_primary_text_color="white",
|
||||
button_primary_text_color_dark="white",
|
||||
button_primary_text_color_hover="#110F0F",
|
||||
button_primary_text_color_hover_dark="#110F0F",
|
||||
button_secondary_background_fill="transparent",
|
||||
button_secondary_background_fill_dark="transparent",
|
||||
button_secondary_background_fill_hover="*neutral_800",
|
||||
button_secondary_background_fill_hover_dark="*neutral_800",
|
||||
button_secondary_border_color="*neutral_700",
|
||||
button_secondary_border_color_dark="*neutral_700",
|
||||
button_secondary_border_color_hover="*neutral_600",
|
||||
button_secondary_border_color_hover_dark="*neutral_600",
|
||||
button_secondary_text_color="white",
|
||||
button_secondary_text_color_dark="white",
|
||||
button_secondary_text_color_hover="*button_secondary_text_color",
|
||||
button_secondary_text_color_hover_dark="*button_secondary_text_color",
|
||||
button_shadow="none",
|
||||
button_shadow_active="*shadow_inset",
|
||||
button_shadow_hover="none",
|
||||
button_small_padding="*spacing_sm calc(2 * *spacing_sm)",
|
||||
button_small_radius="*radius_lg",
|
||||
button_small_text_size="*text_md",
|
||||
button_small_text_weight="400",
|
||||
button_transition="0.3s ease all",
|
||||
checkbox_background_color="*neutral_700",
|
||||
checkbox_background_color_dark="*neutral_700",
|
||||
checkbox_background_color_focus="*checkbox_background_color",
|
||||
checkbox_background_color_focus_dark="*checkbox_background_color",
|
||||
checkbox_background_color_hover="*checkbox_background_color",
|
||||
checkbox_background_color_hover_dark="*checkbox_background_color",
|
||||
checkbox_background_color_selected="*secondary_600",
|
||||
checkbox_background_color_selected_dark="*secondary_600",
|
||||
checkbox_border_color="*neutral_700",
|
||||
checkbox_border_color_dark="*neutral_700",
|
||||
checkbox_border_color_focus="*secondary_500",
|
||||
checkbox_border_color_focus_dark="*secondary_500",
|
||||
checkbox_border_color_hover="*neutral_600",
|
||||
checkbox_border_color_hover_dark="*neutral_600",
|
||||
checkbox_border_color_selected="*secondary_600",
|
||||
checkbox_border_color_selected_dark="*secondary_600",
|
||||
checkbox_border_radius="*radius_sm",
|
||||
checkbox_border_width="*input_border_width",
|
||||
checkbox_border_width_dark="*input_border_width",
|
||||
checkbox_check="url(\"data:image/svg+xml,%3csvg viewBox='0 0 16 16' fill='white' xmlns='http://www.w3.org/2000/svg'%3e%3cpath d='M12.207 4.793a1 1 0 010 1.414l-5 5a1 1 0 01-1.414 0l-2-2a1 1 0 011.414-1.414L6.5 9.086l4.293-4.293a1 1 0 011.414 0z'/%3e%3c/svg%3e\")",
|
||||
checkbox_label_background_fill="transparent",
|
||||
checkbox_label_background_fill_dark="transparent",
|
||||
checkbox_label_background_fill_hover="transparent",
|
||||
checkbox_label_background_fill_hover_dark="transparent",
|
||||
checkbox_label_background_fill_selected="transparent",
|
||||
checkbox_label_background_fill_selected_dark="transparent",
|
||||
checkbox_label_border_color="transparent",
|
||||
checkbox_label_border_color_dark="transparent",
|
||||
checkbox_label_border_color_hover="transparent",
|
||||
checkbox_label_border_color_hover_dark="transparent",
|
||||
checkbox_label_border_width="transparent",
|
||||
checkbox_label_border_width_dark="transparent",
|
||||
checkbox_label_gap="*spacing_lg",
|
||||
checkbox_label_padding="*spacing_md calc(2 * *spacing_md)",
|
||||
checkbox_label_shadow="none",
|
||||
checkbox_label_text_color="*body_text_color",
|
||||
checkbox_label_text_color_dark="*body_text_color",
|
||||
checkbox_label_text_color_selected="*checkbox_label_text_color",
|
||||
checkbox_label_text_color_selected_dark="*checkbox_label_text_color",
|
||||
checkbox_label_text_size="*text_md",
|
||||
checkbox_label_text_weight="400",
|
||||
checkbox_shadow="*input_shadow",
|
||||
color_accent="*primary_500",
|
||||
color_accent_soft="*primary_50",
|
||||
color_accent_soft_dark="*neutral_700",
|
||||
container_radius="*radius_xl",
|
||||
embed_radius="*radius_lg",
|
||||
error_background_fill="*background_fill_primary",
|
||||
error_background_fill_dark="*background_fill_primary",
|
||||
error_border_color="*border_color_primary",
|
||||
error_border_color_dark="*border_color_primary",
|
||||
error_border_width="1px",
|
||||
error_border_width_dark="1px",
|
||||
error_text_color="#ef4444",
|
||||
error_text_color_dark="#ef4444",
|
||||
form_gap_width="0px",
|
||||
input_background_fill="*neutral_900",
|
||||
input_background_fill_dark="*neutral_900",
|
||||
input_background_fill_focus="*secondary_600",
|
||||
input_background_fill_focus_dark="*secondary_600",
|
||||
input_background_fill_hover="*input_background_fill",
|
||||
input_background_fill_hover_dark="*input_background_fill",
|
||||
input_border_color="*neutral_700",
|
||||
input_border_color_dark="*neutral_700",
|
||||
input_border_color_focus="*secondary_600",
|
||||
input_border_color_focus_dark="*primary_600",
|
||||
input_border_color_hover="*input_border_color",
|
||||
input_border_color_hover_dark="*input_border_color",
|
||||
input_border_width="1px",
|
||||
input_border_width_dark="1px",
|
||||
input_padding="*spacing_xl",
|
||||
input_placeholder_color="*neutral_500",
|
||||
input_placeholder_color_dark="*neutral_500",
|
||||
input_radius="*radius_lg",
|
||||
input_shadow="none",
|
||||
input_shadow_dark="none",
|
||||
input_shadow_focus="*input_shadow",
|
||||
input_shadow_focus_dark="*input_shadow",
|
||||
input_text_size="*text_md",
|
||||
input_text_weight="400",
|
||||
layout_gap="*spacing_xxl",
|
||||
link_text_color="*secondary_500",
|
||||
link_text_color_active="*secondary_500",
|
||||
link_text_color_active_dark="*secondary_500",
|
||||
link_text_color_dark="*secondary_500",
|
||||
link_text_color_hover="*secondary_400",
|
||||
link_text_color_hover_dark="*secondary_400",
|
||||
link_text_color_visited="*secondary_600",
|
||||
link_text_color_visited_dark="*secondary_600",
|
||||
loader_color="*color_accent",
|
||||
loader_color_dark="*color_accent",
|
||||
panel_background_fill="*background_fill_secondary",
|
||||
panel_background_fill_dark="*background_fill_secondary",
|
||||
panel_border_color="*border_color_primary",
|
||||
panel_border_color_dark="*border_color_primary",
|
||||
panel_border_width="1px",
|
||||
panel_border_width_dark="1px",
|
||||
prose_header_text_weight="600",
|
||||
prose_text_size="*text_md",
|
||||
prose_text_weight="400",
|
||||
radio_circle="url(\"data:image/svg+xml,%3csvg viewBox='0 0 16 16' fill='white' xmlns='http://www.w3.org/2000/svg'%3e%3ccircle cx='8' cy='8' r='3'/%3e%3c/svg%3e\")",
|
||||
section_header_text_size="*text_md",
|
||||
section_header_text_weight="400",
|
||||
shadow_drop="rgba(0,0,0,0.05) 0px 1px 2px 0px",
|
||||
shadow_drop_lg="0 1px 3px 0 rgb(0 0 0 / 0.1), 0 1px 2px -1px rgb(0 0 0 / 0.1)",
|
||||
shadow_inset="rgba(0,0,0,0.05) 0px 2px 4px 0px inset",
|
||||
shadow_spread="3px",
|
||||
shadow_spread_dark="1px",
|
||||
slider_color="#9E9E9E",
|
||||
slider_color_dark="#9E9E9E",
|
||||
stat_background_fill="*primary_500",
|
||||
stat_background_fill_dark="*primary_500",
|
||||
table_border_color="*neutral_700",
|
||||
table_border_color_dark="*neutral_700",
|
||||
table_even_background_fill="*neutral_950",
|
||||
table_even_background_fill_dark="*neutral_950",
|
||||
table_odd_background_fill="*neutral_900",
|
||||
table_odd_background_fill_dark="*neutral_900",
|
||||
table_radius="*radius_lg",
|
||||
table_row_focus="*color_accent_soft",
|
||||
table_row_focus_dark="*color_accent_soft",
|
||||
)
|
||||
Reference in new issue
Block a user