News for hackers. Stuff that matters.

A comment on Talk-Llama. Parent comment

Re:Talk-Llama by ccoreilly on Thursday November 02, 2023 @09:30AM (#38113257)
Whisper is an STT model, you can use whisperx to transcribe audios locally via the CLI or whisper-turbo.com that runs in the browser.

For TTS coqui has the best UX and models for a lot of languages although quality is not on par with commercial TTS providers.

[ Parent | on HN ]
Re:Talk-Llama by jcuenod on Thursday November 02, 2023 @03:21PM (#38118647)
I've just been looking for SOTA TTS. I found coqui.ai and elevenlabs.io (and a bunch of others). They're good (and better than older TTS), but I am not fooled by any of them. Do you have recommendations?
[ Parent | on HN ]
Re:Talk-Llama by selfhoster11 on Saturday November 04, 2023 @03:47PM (#38144474)
Gemelo was the other one listed. I doubt you'll get anything sounding more natural than ElevenLabs with the following settings:

* Model: Multilingual v2

* All options and sliders to boost similarity: set to max/yes

* Stability slider: experimentally set to a value where the model sounds natural enough without destabilising sound output

[ Parent | on HN ]