← All guides

The best AI lip sync for your video or photo

Close-up of a singer at a studio microphone mid-word, mouth open on a vowel.

Dubbing footage, a head that moves with the words, or a photo that speaks: which AI lip sync to use for which job.

1 min read · last checked

A new voice on footage you have: Sync Lipsync 2

Sync Lipsync 2 puts the mouth on your audio frame by frame and keeps the rest of your shot as it was. That makes it the model for dubbing and for a vocal on a clip you filmed. It is priced on the clip, and the price follows the longer of your video and your audio.

It needs a face it can see. A wide shot with a small face, or a face turned away, gives it little to sync.

A head that moves with the words: InfiniteTalk

InfiniteTalk moves the whole face on the vocal, not only the mouth. It takes up to 9.6 seconds of audio per run, so cut a longer vocal into lines. It renders the frame again at up to 720p, so the picture comes out softer than what you put in.

A photo that speaks or sings

Starting from a still instead of a clip, the Talking photo template gives one photo your vocal or voice-over in one step. For footage that needs more than a new mouth, MiniMax H3 Max adds recast, extend and insert around its lip sync.

Read next

Sync Lipsync vs InfiniteTalkMouth only, or the whole face.Sync Lipsync 2Your video, your audio, the mouth on it.InfiniteTalkThe head moves with the words.A music video for your own trackLip sync in a full workflow.Make a photo talk or singFrom a still instead of a clip.

Put this guide to work

The studio opens in stages. We open access in the order people signed up, and you start with 1,000 free credits.

Get early access