Documentation/Wiki: Refer to the built-in documentation or view the extensive Wiki here.
Known Errors: See the Known Errors page here for troubleshooting.
Issues & Support: Report issues or bugs by opening a support ticket here.
Feature Requests: View current feature requests on the Feature Requests page here.
Community Discussions: Join discussions on AllTalk V2 in the Discussion Board here.
Please note, my available time has become VERY limited due to unexpected family commitments Please read here for details. So please DYOR, look at the Wiki here and refer to the TTS manufacturer (Links in the Gradio interface) for issues specific to THEIR TTS engines.
I would also like to say a big thank you to anyone whom has contributed to this project either with PR's (list here) or in any discussion forums/issues tickets. Your input, guidance, help and thoughts are greatly appreciated.
- Comprehensive setup utilities for Windows & Linux
- Multiple TTS engine support
- Coqui XTTS TTS
- Coqui VITS TTS
- Piper TTS
- Parler TTS
- F5 TTS
- Other TTS engines can be coded in
- Retrieval-based Voice Conversion (RVC) pipeline
- Easy integration of new TTS engines (some coding required)
- Customizable settings for each TTS engine
- In-app model downloads for each engine
- Gradio web interface for easy management
- Standalone application or integration with Text-generation-webui, SillyTavern, KoboldCPP, HomeAssistant
- Narrator function for using different voices for characters and narration
- Audio Transcoding to multiple formats (mp3, opus, etc.)
- About 50 Gradio interface themes
- Custom start-up settings
- Clear console output for troubleshooting
- Binds to all available IP addresses (0.0.0.0)
- Fully customizable Global API settings
- Transcription & Audio File Transcription
- Built-in documentation with web interface
- GitHub Wiki documentation
- DeepSpeed integration for 2-3x performance boost (Depending on TTS engine)
- Low VRAM mode for systems with limited GPU memory
- Model Finetuning for improved voice reproduction
- XTTS Multiple audio sample TTS generation for better voice reproduction
- Bulk TTS Generator/Editor for large-scale audio production
- Comprehensive API Suite
- OpenAI-compatible endpoint/API for broader software compatibility
- JSON call support for third-party applications
- Multi Engine Manager (MEM) for running multiple TTS instances simultaneously & queuing requests between them.
Screenshots are available here
- Requires Git, Microsoft C++ Build Tools, and Windows SDK.
- DeepSpeed works with NVIDIA GPUs.
- Requires specific packages based on your distribution (Debian-based or RPM-based).
- DeepSpeed works with NVIDIA GPUs.
- Limited experimental support for AMD GPUs (mainly for XTTS).
- Installation process is untested and theoretical.
- No GPU acceleration for AllTalk TTS engines.
- Some TTS engines may have limited or no support on Mac.
For more details on Mac support limitations, please refer to the Mac Support Disclaimer.
GPU support is provided by the developer of the individual TTS engine. If their TTS engine support's X GPU, then I can support X GPU, if it doesnt support X GPU, then I cannot support X GPU. Most of the engines will run on CPU, but some may be very slow on CPU.
- NVIDIA GPUs: Full support on Windows and Linux.
- AMD GPUs: Limited experimental support on Linux (mainly for XTTS).
- Intel ARC GPUs: No specific support currently.
- Apple Silicon (M1/M2): No GPU acceleration for AllTalk TTS engines currently.
For a fast and straightforward installation and recommended:
-
- For users who want to run AllTalk TTS as a standalone application.
- Available for Windows and Linux.
- Most users will want a Standalone Installation and should use this choice.
-
Text-generation-webui Installation
- For users who want to integrate AllTalk TTS as a part of Text-generation-webui.
- Available for Windows and Linux.
- Includes information on the optional/alternative TGWUI Remote Extension.
- CURRENTLY YOU SHOULD USE THE STANDALONE INSTALL METHOD AND TGWUI REMOTE EXTENSION
These methods use scripts that automate most of the installation process, making it easier for users to get started quickly.
For users who prefer more control over the installation process or need to troubleshoot:
- Manual Installation Guide
- Detailed step-by-step instructions for manual installation.
- Available for Windows, Linux, and Mac (theoretical).
- Recommended for advanced users or those with specific setup requirements.
For users who want to run AllTalk TTS in a cloud environment:
- Google Colab Installation
- Instructions for setting up and running AllTalk TTS in Google Colab.
- Ideal for users who want to try AllTalk TTS without installing it locally.
As long as you did the git clone
method to setup initially, you will be able to go into the folder and use git pull
to download updates.
It is recommended you use atsetup
to re-apply the settings file for any necessary package updates.
If you are having issues with starting AllTalk, it may well be because some of the 3rd Party packages versions have changed, or something is not right in your Python environment.
- Known Errors List: Wiki page is here
- Diagnostics tool Instructions: Wiki page is here
Whilst its impossible to constantly ensure that everything is going to work perfectly, after installation, you can use the diagnostics tool to:
- Generate a
diagnostics.log
file which contains information about your Python environment setup and performs various checks to ensure everything is installed. - Identify possible issues by comparing your
diagnostics.log
file to the AllTalk basebasediagnostics.log
stored in thealltalk_tts/system/config/
folder. - Provide some semi-automated repair of your Python environment.
Documentation & Known Error codes, please refer to the built in documentation or the Wiki here .
If you wish to code something yourself though, thats perfectly to do and youre welcome to discuss that with me if needed.
General discussions on the BETA should be here in the discussion board
If you have a specifc technical problem, please open an issue ticket here in the issues area.
Please note, my available time has become VERY limited due to unexpected family commitments. So please DYOR, look at the Wiki here and refer to the TTS manufacturer (Links in the Gradio interface) for issues specific to THEIR TTS engines.