News for hackers. Stuff that matters.
Re:Meta introduces Voicebox: state-of-the-art generative AI ... by gamegoblin on Monday June 19, 2023 @02:48PM (#36395057)
Just listening to it, it's subjectively not better, but if it's > 10x faster/cheaper, I would use it anyway -- it's good enough to be listenable.

Eleven Labs is the first voice synthesis that is good enough that I'd listen to an audiobook generated from it, but pricing is such that it would cost $100 to synthesize a 10 hour audiobook. A little too expensive. If they could get it down to $10 I'd cancel my Audible subscription and just synthesize audio from ebook text.

So if I can get a locally running voicebox model and just leave it running on my laptop over night transcribing an audiobook, that's even better.

Re:Meta introduces Voicebox: state-of-the-art generative AI ... by siwakotisaurav on Monday June 19, 2023 @03:03PM (#36395234)
Have you tried tortoisetts? I believe eleven labs basically forked that and made improvements on voice quality and speed there
Re:Meta introduces Voicebox: state-of-the-art generative AI ... by theLiminator on Monday June 19, 2023 @03:30PM (#36395550)
How does it compare to Voicebox in quality?
Re:Meta introduces Voicebox: state-of-the-art generative AI ... by pksebben on Monday June 19, 2023 @04:28PM (#36396094)
I would say that properly configured Tortoise is better, but that comes with the massive caveat that Tortoise:

1 - Is a real pain to get 'working right' - it's not even remotely batteries included

and, more importantly:

2 - Is incredibly slow. I've been turning Heart Of Darkness into an audiobook as a unit test and it takes ~30m per paragraph, on average. Add to that the occasional hiccup where a block gets transcribed badly (Tortoise occasionally 'drops out' of it's selected voice) and Tortoise only really works if you have a ton of compute and you still don't mind waiting forever.

Re:Meta introduces Voicebox: state-of-the-art generative AI ... by siwakotisaurav on Tuesday June 20, 2023 @02:07AM (#36400320)
FYI there’s also this fork for faster inference: https://github.com/152334H/tortoise-tts-fast
Re:Meta introduces Voicebox: state-of-the-art generative AI ... by nannal on Monday June 19, 2023 @04:25PM (#36396050)
tortoisetts is good to takes a long time to render audio even on it's fastest setting with the fast fork.

Although it wasn't clear to me how voicebox compares.

Re:Meta introduces Voicebox: state-of-the-art generative AI ... by bavell on Monday June 19, 2023 @03:01PM (#36395202)
> So if I can get a locally running voicebox model and just leave it running on my laptop over night transcribing an audiobook, that's even better.

This is basically my dream for local AI... locals models trained on my own data/code/styles. Even if they're slow, as long as they work (V/RAM) and are of high enough quality then I'm happy to wait!