Skip to main content
Generate Lipsync animates a face from an image or video so it matches a connected audio track.

​
When to use

  • Talking avatars
  • Dubbed clips
  • Presenter videos
Common patterns: upload_image → generate_lipsync, or upload_video → generate_lipsync.

​
Inputs

Connect an image or a video source, plus an audio track to drive the lipsync.
​
image
A still face to animate. Optional. Supports loop mode. Connect this or Video.
​
video
A video face to animate. Optional. Supports loop mode. Connect this or Image.
​
audio
required
The audio track that drives the lip movement. Required.

​
Outputs

​
video
The lipsynced video.
This node runs on a selectable model and consumes credits. Model-specific options (such as resolution and audio handling) are available depending on the model you choose. Pick the model in the node’s config panel. See Video models for the options, and Model settings for what each setting does.