All tasks / Models
LatentSync 1.6
ByteDance's open-weights lip-sync model that re-syncs mouth movements in an existing video to new audio.
- ByteDance
- Open weights
- Released 11 Jun 2025
Where it ranks
- –Avatars & dubbingModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- ByteDance
- Family
- LatentSync
- Released
- 11 Jun 2025
- Weights
- Open: download and run it yourself
- License
- OpenRAIL++
- GPU memory to run locally
- ~18 GB (README: minimum inference VRAM 18 GB for LatentSync 1.6 (8 GB for 1.5))
- Access
- Free (open weights)
- Last verified
- 18 Oct 2026
Price from huggingface.co, 18 Oct 2026.
Benchmark results
No public benchmark results recorded yet.
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.
Earlier versions
- LatentSync 1.5 · 14 Mar 2025