Skip to main content
All tools

Video

AI Lip Sync: a photo that speaks or sings your audio

Upload a portrait and a voice clip or song, and the person in the photo speaks or sings it with perfectly synced lips, expressions and gestures.

After, straight from our test, no retouching

Add a photo to start.

What AI Lip Sync does

AI Lip Sync makes the person in your photo speak or sing your audio: upload a portrait and a voice clip or song, and the lips, expressions and gestures follow every word.

How to use AI Lip Sync

  1. Upload portrait photo and voice or song (mp3, wav), or pick it from your library.
  2. Press Generate. The instructions for the job are already set up, so there is no prompt to write.
  3. Your video shows up right on the page. Save it to your library or download it.

Tips for the best result

  • Use a front-facing portrait with the mouth visible.
  • Clean voice recordings sync the best.
  • Clips up to 60 seconds work.

Ideas for using it

  • A talking avatar for your channel.
  • A singing birthday message.
  • A product explainer voiced by your mascot.

More tools

Want motion instead? Video Effects turn one photo into a 5 second clip.

Go further

AI Lip Sync FAQ

What audio can I use?

MP3 or WAV voice clips and songs, up to 60 seconds.

Does it work with singing?

Yes. Speech and singing both sync.

Is AI Lip Sync free?

AI Lip Sync is included with every PixelDojo plan and costs a few credits per video, shown on the Generate button before you run it.

Who owns the result, and can I use it commercially?

We assign you whatever rights we hold in the result, so you can use it in your own projects, commercial ones included, as long as what you uploaded was yours to use. Unsaved results are deleted after 24 hours, so save the ones you want to keep.

Can I use a photo of someone else?

Only photos of adults, of yourself or of people who agreed to it, and only images you have the right to edit. Every upload goes through the same safety checks as the rest of PixelDojo.