LocalLLaMA

1 readers

1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 10 months ago

MODERATORS

communick@poweruser.forum

Any Good Speech-to-Speech Voice Changer Models? (alien.top)

submitted 10 months ago by HumanityFirstTheory@alien.top to c/localllama@poweruser.forum

3 comments fedilink hide all child comments

ElevenLabs just released their speech to speech thing and it’s really cool: https://elevenlabs.io/voice-changer

Now I’m wondering what’s the best similar “voice changer” or speech to speech model that I can run locally?

It doesn’t have to be in real time, I plan on using it to narrate audio books and similar.

Thanks!

top 3 comments

sorted by: hot top controversial new old

[–] a_beautiful_rhind@alien.top 1 points 10 months ago

rvc or so-vits-svc

[–] AnonymousD3vil@alien.top 1 points 10 months ago

You could do a audio transcription then TTS to achieve the similar results with whisper and coqui-ai TTS models.

https://github.com/coqui-ai/TTS

[–] JawGBoi@alien.top 1 points 10 months ago

RVC is definitely the best for this. Unlike most other methods, you don't provide text transcriptions for the training dataset - this makes RVC models really easy to train and there is no compromise of quality.