search

gitmylo / audio-webui

A webui for different audio related Neural Networks
MIT License
973 stars 90 forks source link

[BUG REPORT] XTTS 2 through Coqui does not work. #177

Open dogarrowtype opened 8 months ago

dogarrowtype commented 8 months ago

Describe the bug The new model from Coqui is exceptionally high quality for open source tts. It would be awesome to use it in a workflow involving audio-webui, with RVC. Is there any chance of supporting this new model?

To Reproduce Steps to reproduce the behavior:

  1. Select Coqui TTS as the provider.
  2. Pick XTTS 2 as the model.
  3. Encounter error trying to generate.
gitmylo commented 8 months ago

I'm aware, from what I remember coqui normally gives a list of languages which you can get the same way for all models that support them. Except for XTTS, I believe it's planned to be added, but that would be an update for the TTS package, not audio-webui itsself.

ye7iaserag commented 6 months ago

is this still a problem?