AI Toolsby Vomini

#9 of 12 in Talking avatars · ByteDance

LatentSync

Free lip sync: make a filmed person say new audio.

FreeOpen sourceRuns on your PC
Best for
Dubbing existing videos
On your PC
Technical
Works on
Linux, Windows
License
Apache-2.0

What’s good

  • Sharp mouths on real filmed faces
  • Older version 1.5 runs on 8 GB cards
  • Commercial use allowed

Downsides

  • Only fixes lips; needs a video, not a photo
  • Version 1.6 needs 18 GB of graphics memory
  • Command line setup

// details

The details.

Version
LatentSync 1.6Released 2025-06-11
Open source
Yes, Apache-2.0
Made by
ByteDance
Website
github.com

// our verdict

Should you use it?

It is #9 of 12. Good for dubbing existing videos; for most people, HeyGen is the better start.

// on your computer

Can I run it myself?

Yes. Technical: command line or python.

Use Python scripts, Gradio app in the repo.

You need
NVIDIA GPU with 8 GB (v1.5) or 18 GB (v1.6)
Setup
TechnicalCommand line or Python
  • Laptop, 8 GBToo small
  • PC, 16 GB+Too small
  • Mac, 16 GBToo small
  • Mac, 32 GBToo small
  • Mac, 64 GB+Too small
  • PC, 8 GB GPUToo small
  • PC, 12 GB GPUToo small
  • PC, 16 GB GPUToo small
  • PC, 24 GB GPURuns
  • WorkstationRuns