TTS WebUI

GitHub   Feedback / Bug reports
HomePipelineText-to-SpeechAudio/Music GenerationAudio ConversionOutputsTools
RVCDemucsVocos Wav

Audio Conversion Models:

RVC

An easy-to-use voice conversion framework based on VITS.

Run Github

Demucs

Demucs is a post-processing model for Music Source Separation.

Run Github

Vocos Wav

Vocos Wav is a post-processing model that can refine the output of a text-to-speech model.

Run Github

Vocos NPZ

Vocos NPZ is a post-processing model that can refine the output of a Bark.

Run Github