Long-Form Generation

[fakerybakery]

trafficstars

Hi, Do you know if it's possible to smoothly generate longer audio with WhisperSpeech? And dialogue with multiple characters? Thanks!

[jpc]

Both these features should be possible if we implement #52

[fakerybakery]

Nice! What about generating dialogue? Should that be done separately (ie quote extraction + attribution -> WhisperSpeech w/ voice cloning)?

[jpc]

Yes, you're right. This would give you the most control over the style and voice of each speaker.

One could probably find or train a traditional NLP preprocessing model to do this automatically.

[fakerybakery]

Thanks! Should I close this issue in favor of #52?

[jpc]

These is also #58 , which would also be useful.

Maybe this can be the umbrella task. :)