Lip Sync makes the person in a talking video say new words. Your footage and gestures stay exactly as they are; only the voice and the mouth change. Use it to fix a line, localize a script, or put a voiceover on a video you already have.
Who can use it
Available on paid plans
Where to find it
Studio > Tools > Lip Sync
How to use it
Under Original video, upload or pick a video of one person talking (5 seconds to 5 minutes, up to 500 MB).
Choose how the new speech is provided: Script + voice, or Voiceover.
With Script + voice, type or paste the exact script, then click Select Voice and pick the voice that will speak it. With Voiceover, upload the audio you want the person to say.
Click Generate. The result is a new video with the same footage and the new speech.
Options
Script + voice: your script is spoken word for word in the voice you pick.
Voiceover: your audio is used as it is, up to 5 minutes.
Credits
Lip Sync costs 48 credits per second of speech (each started second counts). When you use Script + voice, text to speech is added: 8 credits per started 30 seconds of speech. A voiceover you upload has no text to speech charge. Credit costs here are the standard rates. The Generate button in the app shows what each generation costs on your account.
Where it works
Studio: Tools > Lip Sync.
Workflows: the Lip Sync node, with a Script + voice or Audio input.
Mark: ask Mark to lip-sync a video. For videos with several lines, Mark works scene by scene and joins the result.
MCP: the Lip Sync tool.
Limitations
Works on videos with a single speaker.
One video at a time, at least 5 seconds long.
It does not translate for you. Bring the exact script or voiceover. To translate a video automatically, use Translate Video.