Talking Photo AI

Upload a portrait, type what it should say, pick a voice. The photo talks with matching lip movements.

A photo with a clear face

JPG, PNG or WebP, up to 10MB. Clear, well-lit photos work best.

About 1s of speech (up to 30s)0/400

Voice

About 60 credits (final price uses the real speech length)

Only use photos you have the right to use. Don't make real people say things they didn't say or wouldn't agree to.

Your video will show up here

Add a photo, write the script and pick a voice. Your talking photo is usually ready in 1 to 3 minutes.

Good to know

Talking Photo turns a single portrait into a short video where the person speaks your script. The voice comes from ElevenLabs, and the face, lips and head move in sync with it. Use it for greetings, explainer clips, social posts or to give an old family photo a voice.

  • Use a front-facing photo where the mouth is clearly visible and not covered.
  • Write the way people talk. Short sentences sound the most natural.
  • The script can be in English, Chinese or 27 other languages; the voice follows the text.

Common questions

Or try a one-tap effect

See all effects