Match lips to new speech
LatentSync
LatentSync is a video-to-video model that generates lip sync animations from audio using advanced algorithms for high-quality synchronization.
Opens the avatar studio with LatentSync ready to use. You can look around as a guest. Running it takes the Pro plan or higher.
What LatentSync makes, what it needs and what you get
What it makes
Match lips to new speech
Matches the lips of a person in a video to new speech.
What you need
- A video of the person
- The new speech (an audio clip)
What you get
The same video, with the lips matched to the new speech
About LatentSync
LatentSync matches the lips of a person in a video to new speech. It is made by Open Source.
To use it, you provide a video of the person and the new speech. You get the same video, with the lips matched to the new speech.
A 5 s result costs about 250 credits. Longer or shorter results cost in proportion, about 50 credits per second. It is included from the Pro plan and up. You run it in the avatar studio, in your browser.
Best for
Typical uses for this kind of model.
- Dubbing a video into another language
- Fixing a line you re-recorded
- Making a filmed speaker say a new script
How to use LatentSync
- 1
Add a video of the person and the new speech
Upload your files, or pick them from your library. Nothing else is needed to start.
- 2
Check the settings
The defaults are a good start. If you change an option, the cost updates and is shown before you generate.
- 3
Generate your video
The same video, with the lips matched to the new speech. Your result appears in the studio, ready to download.
Other models for this job
Same job: match lips to new speech. Compare before you choose.
Replace or dub audio on an existing video with fast audio-only lip-sync.
Use React-1 from SyncLabs to refine human emotions and do realistic lip-sync without losing details!
Replace or dub audio on an existing video with high-accuracy avatar-inference lip-sync.
Generate realistic lipsync animations from audio using advanced algorithms for high-quality synchronization with PixVerse Lipsync model