Skill3 steps

Lip-Sync Dub

Match a speaker to new audio in any language.

How it runs

The right model for every step.

Provide a video and a new voice track. The skill aligns the audio, syncs the lips frame by frame and restores resolution, so dubbed and localized content looks like it was shot that way.

Every intermediate result is kept with the run, so you can inspect a step, reuse its output or rerun it with different settings.

Input
- Video
- Audio track
01
Align the audioAudio aligner
02
Sync the lipsLipsync 2 Pro
03
Restore resolutionTopaz Video Upscale
OutputThe dubbed video at source resolution

Run it

Call the skill by name.

Send the inputs, get back a run you can wait on or follow with a webhook. The same skill is available in the studio and to AI agents through the MCP server.

You get back

The dubbed video at source resolution

run.sh

curl https://api.monogram.dev/v1/skills/lip-sync-dub/runs \
  -H "Authorization: Bearer $MONOGRAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": {
      "video_url": "https://files.example.com/interview.mp4",
      "audio_url": "https://files.example.com/interview-es.wav"
    }
  }'