TTS WebUI
FreeWeb UI for running multiple text-to-speech, music generation, and audio tools. #opensource
FreeFree tier
Inputs: text, audioOutputs: audio
About TTS WebUI
A single Gradio + React WebUI with extensions for numerous text-to-speech, music generation, and audio tools. Supports models including Bark, MusicGen, XTTSv2, GPT-SoVITS, CosyVoice, Kokoro, OpenVoice, ParlerTTS, Stable Audio, Demucs, RVC, and many more. Includes a recommended installer (TTS WebUI Ignition), Docker support, and integration with SillyTavern. Open source and free to use.
Key Features
Supports 50+ TTS and audio models via built-in and extension system
Dual interface: Gradio UI and React UI
Extension system for adding models like GPT-SoVITS, CosyVoice, Kimi Audio, etc.
TTS WebUI Ignition installer for simplified setup on Windows
Docker support with Dockerfile and docker-compose.yml
Integration with SillyTavern for chatbot voice output
Voice conversion and audio editing tools (RVC, Demucs, etc.)
Pros & Cons
Pros
- Extensive library of supported models covering TTS, music, and audio processing
- Free and open source with no usage limits
- Easy installation via TTS WebUI Ignition or Docker
- Active development with regular updates and community support
- Both code-first (Gradio) and user-friendly (React) interfaces available
Cons
- Large base installation size (~10.7 GB) before adding models
- Requires a GPU for most models to run efficiently
- Many models are available only as extensions, not installed by default
- Python 3.12 is not supported; requires 3.10 or 3.11
Best For
Content creation: narration, voiceovers, audiobooksMusic generation and audio synthesisVoice cloning and real-time voice conversionResearch and experimentation with different TTS and audio modelsIntegration with AI chatbots and virtual assistants
FAQ
What models are supported?
TTS WebUI supports a wide range of models including Bark, MusicGen, XTTSv2, GPT-SoVITS, CosyVoice, Kokoro, OpenVoice, ParlerTTS, Stable Audio, Demucs, RVC, and many more. A full list is available in the repository's README.
How do I install TTS WebUI?
The recommended method is TTS WebUI Ignition. On Windows: winget install TTS-WebUI.Ignition. Alternatively, download the latest release, extract it, and run the start_tts_webui script for your platform.
Is there a Docker setup?
Yes, the repository includes a Dockerfile and docker-compose.yml for containerized deployment.
Can I use TTS WebUI with SillyTavern?
Yes, TTS WebUI includes integration with SillyTavern, allowing text-to-speech output in chatbot conversations.