Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Use existing .pth & .index files as a voice to enter text prompt #245

Open
JasonSemaan1 opened this issue Jan 12, 2024 · 1 comment
Open

Comments

@JasonSemaan1
Copy link

Hello - I have gotten the TTS Generation WebUI running successfully. I have a number of RVC trained voice model .pth and .index files and was wondering if its possible to use these existing files as a voice to feed text prompts to?
Noticed that the default 'Alice' voice is a .npz file

@rsxdalv
Copy link
Owner

rsxdalv commented Jan 12, 2024

Yes and no. RVC Models can be used for RVC, Bark voices can be used for bark. You can, however, generate with bark and then convert (or make more similar) with RVC. Additionally, you can try to make a bark voice from RVC ouput audio.

Bark voices usually are .npz but in reality that just means - zipped python arrays, and npz files are used for many other things too.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants