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

Advanced voice control for Silero TTS #956

Closed
KirillRepinArt opened this issue Apr 9, 2023 · 7 comments
Closed

Advanced voice control for Silero TTS #956

KirillRepinArt opened this issue Apr 9, 2023 · 7 comments
Labels
enhancement New feature or request stale

Comments

@KirillRepinArt
Copy link

KirillRepinArt commented Apr 9, 2023

Additional voice controls for Silero TTS

I've tried elevenlabs today, and they produce very good sounding characters pretty quickly. Would it be possible to have similar options?
It would be very cool to have more control over the voice generation using silero_tts.

  1. Gender
  2. Age
  3. Accent
  4. Accent strength
    https://beta.elevenlabs.io/

Also it would be very nice to have any sort of description for the TTS voice presets, I've spent at least 5 hours today figuring out the differences between all of the TTS presets and think I got through only about a half of them. Their names are very non descriptive.
Also there's no voice generation for when the bot does some action, while it makes sense on some level, I think it would be much better if the voice would be generated for everything then tex gen produces. May be this could be optional?

@KirillRepinArt KirillRepinArt added the enhancement New feature or request label Apr 9, 2023
@Brawlence
Copy link
Contributor

Gotta check later for voice control, but voiceover for
*Asterix-enclosed actions*
is a nice and easily-made feature

@KirillRepinArt
Copy link
Author

Gotta check later for voice control, but voiceover for Asterix-enclosed actions is a nice and easily-made feature

This is how they are doing the voice control at Eleven Labs, in case you'll be looking into it, or if you haven't seen it already.
VoiceGen_example
Would implementation of a some type of the voice preset pipeline be too difficult or time consuming?
I don't really know myself, but I would guess that it would be possible to have at least some control over it, like Temperature or Seed, or something similar.
I realize that this is text-generation-webui, but I would assume that a fair amount people would be interested in such enhancements for their bots.

@da3dsoul
Copy link
Contributor

I'm not sure if silero is your game for that. Tortoise MRQ might be able to, though, and that's in a PR here

@KirillRepinArt
Copy link
Author

I'm not sure if silero is your game for that. Tortoise MRQ might be able to, though, and that's in a PR here

I would like to try it, but I can't seem to find it in the available extensions list, am I missing something?

@da3dsoul
Copy link
Contributor

I can only assume you didn't read or don't know what PR means. It's a pull request, which means it's not in the main repository yet. It's where people write a feature and ask for it to be included

@KirillRepinArt
Copy link
Author

I can only assume you didn't read or don't know what PR means. It's a pull request, which means it's not in the main repository yet. It's where people write a feature and ask for it to be included

I thought it could mean a pull request, wasn't sure though, still new to this. I though it was possible that I just didn't understand something.
Can't wait to try this new extension, though, hope it will be in the main repository soon!

@github-actions github-actions bot added the stale label Oct 10, 2023
@github-actions
Copy link

This issue has been closed due to inactivity for 6 weeks. If you believe it is still relevant, please leave a comment below. You can tag a developer in your comment.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request stale
Projects
None yet
Development

No branches or pull requests

3 participants