News for hackers. Stuff that matters.
Re:BASE TTS: The largest text-to-speech model to-date by maxglute on Wednesday February 14, 2024 @02:50PM (#39374338)
Are there any decent TTS models that can be ran locally that plugs into existing software like SAPI without too much lag?
Re:BASE TTS: The largest text-to-speech model to-date by Nouser76 on Wednesday February 14, 2024 @04:45PM (#39375944)
I've used coqui.ai's TTS models[0] and library[1] to great success. I was able to get cloned voice to be rendered in about 80% of the audio clip length, and I believe you can also stream the response. Do note the model license for XTTS, it is one they wrote themselves that has some restrictions.

[0] https://huggingface.co/coqui/XTTS-v2

[1] https://github.com/coqui-ai/TTS

Re:BASE TTS: The largest text-to-speech model to-date by modeless on Wednesday February 14, 2024 @04:44PM (#39375928)
XTTS has a streaming mode with ~300ms latency and sounds good, though it has hallucination issues. StyleTTS2 sounds good and doesn't hallucinate as much. It doesn't support streaming but it's fast so it can still respond quickly. But neither of them sound as good as Eleven Labs or OpenAI or this one.
Re:BASE TTS: The largest text-to-speech model to-date by dvt on Wednesday February 14, 2024 @04:11PM (#39375445)
Bark and Tortoise work fairly well. Bark does super fast inference[1] on my M1.

[1] https://github.com/SaladTechnologies/bark

Re:BASE TTS: The largest text-to-speech model to-date by turnsout on Wednesday February 14, 2024 @04:25PM (#39375638)
@dvt Is this just a containerized version of Bark? Wondering if this repo has M1-specific improvements.
Re:BASE TTS: The largest text-to-speech model to-date by dvt on Wednesday February 14, 2024 @04:39PM (#39375850)
> Is this just a containerized version of Bark

I think so.

Re:BASE TTS: The largest text-to-speech model to-date by turnsout on Wednesday February 14, 2024 @04:46PM (#39375953)
I'm finding M1 generation quite slow (CPU-only) on the stock Bark—any tips on speeding it up?
Re:BASE TTS: The largest text-to-speech model to-date by dvt on Wednesday February 14, 2024 @04:58PM (#39376114)
Sorry, haven't messed around too much with optimizations. I thought it was quite fast compared to Tortoise for example (where generation speed was at a 3:1 ratio).