This is a really clever combination of models to translate, generate audio and lip-sync a video.

It's like HeyGen, but open source. https://t.co/TiNxnEpDMn

— fofr (@fofrAI) 3 novembre 2023

This is a really clever combination of models to translate, generate audio and lip-sync a video. It's like HeyGen, but open source.

→ View original post on X — @fofrai