bytedance
LatentSync
Re-syncs a talking-face video to another audio track
- Stable Diffusion
- Whisper tiny
- SyncNet

LivePortrait animates a still face photo or video with motion from another clip. It's the official PyTorch code from Kuaishou, and it handles humans, cats and dogs. You get command-line scripts and a Gradio interface (a browser UI for the model). Animal mode needs Linux or Windows with an NVIDIA GPU.
Best for: Talking-head animators who need controllable face animation or expression transfer.
From the LivePortrait README on GitHub. Tap an image to see it full size.
Rewritten from the README. Check the repo for the latest steps.
conda activate LivePortraitgit clone https://github.com/KlingTeam/LivePortraitconda create -n LivePortrait python=3.10pip install -r requirements.txtpip install -r requirements_macOS.txthuggingface-cli download KlingTeam/LivePortrait --local-dir pretrained_weights --exclude "*.git*" "README.md" "docs"python inference.py, or set your own inputs with the command belowpython inference.py -s assets/examples/source/s9.jpg -d assets/examples/driving/d0.mp4python app.py; for animals, build the MultiScaleDeformableAttention op first, then run python app_animals.pyOther editing & audio projects people compare with LivePortrait.
bytedance
Re-syncs a talking-face video to another audio track
KlingAIResearch
Tool that redraws a video character's mouth to match a new audio track
MeiGen-AI
Lip-synced video or photo from new audio, any length
RVC-Boss
Clones a voice from a 5-second clip and reads your text in it
Do you maintain LivePortrait? Add this badge to your README so English speakers can find our write-up.
[](https://openmicrodrama.com/projects/klingairesearch-liveportrait)The badge links to this page. Want your description changed? Email support@openmicrodrama.com.
Reviewed Oct 1, 2026. Last push 2026-06-01, outside our 90-day window. We kept it because it's still widely used. We write these descriptions ourselves. The repo's own docs are the final word.