Sync 3 Avatar Image to Video

Sync 3 animates the face in a still image so it speaks the provided audio; the output matches the audio length.
sync/lipsync/3.0/image-to-video

Sync 3 animates the face in a still image so it speaks the provided audio; the output matches the audio length.

Try the model

Playground

Open playground
Input
Input audio URL.

PNG, JPEG, WebP, or GIF · 20 MiB maximum

Input image URL (face / character).
Result
Example
  1. What would you like to do next?

    Open original

Saved example result. No new generation was requested.

Displayed run estimate: $0.675. Final charges follow the model’s billing rules below.

Sync 3 Avatar Image to Video

Sync 3 Avatar animates the face in a still image so it speaks the provided audio.

Fields

FieldTypeDefaultNotes
imageimage URL, required—Face to animate. JPEG, PNG, or WebP URL.
audioaudio URL, required—Speech to sync.

Billing

$0.135 per output second. The quote before submission assumes 5 seconds; the final charge uses the measured length.

OutputPrice
5s$0.675
30s$4.05
60s$8.10

Failed runs are not charged.

Also on SandBase

Related: sync/lipsync/3.0/video-to-video.