Make a photo talk or sing with AI
One photo and your audio, and the face speaks or sings it. What works, what to expect, and when to use lip sync on video instead.
1 min read · last checked
What you bring
A photo with a clear face, looking roughly towards the camera, and your audio as an MP3 or WAV: a voice recording or a song. There is no prompt. The result is as long as your audio.
What to expect
The model animates the face to match the sound. Expect a talking or singing portrait, not a walking scene. For a person moving through a shot, start from video instead and put the audio on it with lip sync.
What people use it for
Three uses that work well.
- A presenter for an explainer: record the script once and put it in the mouth of your brand character.
- Product videos in several languages: the same face, a different recording per market.
- Music and social clips: a portrait that sings the chorus.
Use your own face, an invented one, or someone who agreed to it. Above fifteen seconds the provider charges the whole clip at 1.2 times the rate; the price on the button includes it.
Read next
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