bytedance/LatentSync
Taming Stable Diffusion for Lip Sync!
This tool helps content creators, marketers, or educators quickly and accurately match spoken audio to a person's mouth movements in a video. You provide an existing video clip of a person speaking and an audio track, and it generates a new video where the person's lips are perfectly synchronized with the provided audio. This is ideal for creating realistic dubbed content, fixing out-of-sync footage, or animating characters to speak specific dialogue.
5,506 stars. No commits in the last 6 months.
Use this if you need to precisely align a person's lip movements in a video with a new or edited audio track, ensuring natural and convincing visual speech.
Not ideal if you need to generate a full human video from scratch, as this tool focuses specifically on the lip-syncing aspect of existing footage.
Stars
5,506
Forks
899
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 20, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/bytedance/LatentSync"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
PrunaAI/pruna
Pruna is a model optimization framework built for developers, enabling you to deliver faster,...
haoheliu/AudioLDM-training-finetuning
AudioLDM training, finetuning, evaluation and inference.
Text-to-Audio/Make-An-Audio
PyTorch Implementation of Make-An-Audio (ICML'23) with a Text-to-Audio Generative Model
teticio/audio-diffusion
Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead...
ivanvovk/WaveGrad
Implementation of WaveGrad high-fidelity vocoder from Google Brain in PyTorch.