TTS-WebUI
A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS,
What is TTS-WebUI?
A single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, MusicGen, Tortoise, RVC, Vocos, Demucs, SeamlessM4T, and Bark!
Overview of TTS-WebUI
What it is
TTS-WebUI is a single Gradio + React WebUI that provides a unified interface for multiple text-to-speech, audio/music generation, and audio conversion models. It supports extensions for models such as ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, OpenVoice, ParlerTTS, Stable Audio, MMS, StyleTTS2, MAGNet, AudioGen, MusicGen, Tortoise, RVC, Vocos, Demucs, SeamlessM4T, and Bark.
Key features
- Combines Gradio and React for a unified web interface - Supports a wide range of text-to-speech models (e.g., Bark, Tortoise, StyleTTS2, XTTSv2, CosyVoice, GPT-SoVITS, Piper TTS)
- Includes audio/music generation models (e.g., MusicGen, MAGNeT, Stable Audio, ACE-Step)
- Provides audio conversion and enhancement tools (e.g., RVC, Demucs, Vocos, Whisper, Resemble Enhance)
- Many models are available as extensions and are not installed by default - Offers an installer (TTS WebUI Ignition) for easy setup on Windows - Manual installation is also supported with Python 3.10/3.11 and PyTorch
Use cases
- Generating speech from text using various TTS models - Creating music or audio from prompts with music generation models - Converting or enhancing audio (e.g., voice conversion, source separation, denoising)
- Experimenting with different speech synthesis and audio processing techniques
Getting started
winget install TTS-WebUI.Ignition # For manual installation: git clone https://github.com/rsxdalv/tts-webui.git cd tts-webui pip install -r requirements.txt python server.py --no-react
License and pricing
The project is licensed under MIT and is open source.
Based on the project's public README and repository metadata.