TTS WebUI

TTS WebUI is a free, open source web interface that puts many local audio generation models behind a single Gradio and React application. Its extension system covers text to speech models such as Bark, Tortoise, XTTSv2, Kokoro, Piper TTS, StyleTTS2, CosyVoice, GPT SoVITS, ParlerTTS and DIA, along with music and audio generation through MusicGen, Stable Audio, MAGNeT and ACE Step, and audio conversion and tools such as RVC voice conversion, Vocos, Demucs and Whisper. It is aimed at hobbyists, creators and developers who want to run these models on their own hardware without wiring each project together by hand. The repository provides a downloadable installer, installation instructions, a Docker setup and a Silly Tavern integration, plus example videos and screenshots. Extensions are modular, so users can add only the models they need. The project is released under the MIT license and has no paid plans. Running it requires a local machine, typically with a capable GPU for the larger models, and the quality of results depends on the underlying third party models each extension installs. Support and bug reports are handled through the GitHub repository.