CorentinJ: Real-Time Voice Cloning (2021)

https://github.com/CorentinJ/Real-Time-Voice-Cloning

by redbell • 10 months ago

94 23 10 months ago

github.com

blurbleblurble2• 10 months ago

Atomic bomb level technological shifts happening, open sourced online. What a time to be alive!

avereveard• 10 months ago

(2021)

p2detar• 10 months ago

It looks rather complete, but indeed - the project has 3 commits for the past 3 years.

niek_pas• 10 months ago

In fact, the YouTube video the GitHub repo links to is from 2019.

hleszek2• 10 months ago

For some reason the VibeVoice model from Microsoft (which is also able to clone voices and is also very good) has been deleted from GitHub 10 days ago even tough it was released under a MIT license. But this post shows that the cat is out of the bag for some time already now (post is from 2021) and we have to live with this technology.

qwertox• 10 months ago

The reason is known: "we discovered instances where the tool was used in ways inconsistent with the stated intent"

askl• 10 months ago

The stated intend would be scamming people I guess? What would be the other ways inconsistent with that?

nickthegreek• 10 months ago

any links still up?

hleszek2• 10 months ago

https://github.com/Enemyx-net/VibeVoice-ComfyUI

woadwarrior01• 10 months ago

There's a community maintained fork.

https://github.com/vibevoice-community/VibeVoice

whimsicalism• 10 months ago

there are many easy extant ways to do voice coding. many models are released without a “voice embedding” model but they are easy to recreate by passing the gradients through the soft prompt

shazron• 10 months ago

Try Modelscope.

ivape• 10 months ago

Does anyone know for sure if Voice ID has security measures to protect against AI voice cloning?

CorentinJ: Real-Time Voice Cloning (2021)

Related Stories