How to make a photo talk with AI

Attach a portrait photo and an audio track (or a script for Recut to voice), and ask Recut to "make this photo talk". It runs a talking-avatar model that animates the face, and often the head and shoulders, to speak or sing the audio.

What to typeMake this portrait say the script below in a friendly voice.

Step by step

Attach the photoA clear, front-facing portrait with the face well lit gives the best result.
Add the voiceAttach a recording, or paste a script and Recut adds a voice step first.
Pick the modelRecut suggests talking-avatar models such as OmniHuman v1.5, Kling AI Avatar v2, HeyGen Avatar IV and InfiniTalk, each with its price.
Run itTalking-avatar runs are priced by length and take a little while. The video appears on the timeline when it's done.

What Recut does

A talking-avatar model takes one still image and a sound and generates a video where the person moves their mouth, face and head in time with the sound. Unlike lip sync, it doesn't need an existing video of the person.

Recut chains the steps for you: write the voice from a script, make the avatar, then fit the result for a platform and add captions, all in one plan you approve.

Talking-avatar models differ in what they move: some animate only the face and lips, others the head, shoulders and hands. Recut shows several side by side so you can try more than one on the same photo and keep the best.

Tips

Use a photo with some space around the head; tight crops leave the model less to animate.
Singing works too: give it a song instead of speech.

What it doesn't do

Only animate photos of yourself or of people who have agreed to it.
Movement and realism are the model's; long clips can drift from the original face.

Try it on your own video

Recut runs in your browser, on Mac, Windows and Android. Start free, attach a file and say what you want.

Open Recut in your browser

Related guides

How to lip sync a video to new audio with AIAttach a video and a voice track, and Recut runs an AI lip-sync model, such as Sync Lipsync or LatentSync, so the mouth follows the new audio.
How to add an AI voiceover to a videoPaste a script, pick a voice, and Recut reads it with an AI voice model and lays the voiceover on your video, with music turned down under it.
How to turn a photo into a video with AIAttach a photo, describe the motion, and Recut animates it with an image-to-video model such as Kling, Veo or Seedance, priced before you run.