# Make a Photo Talk

> To make a photo talk with AI you need 2 files: a front-facing portrait and a voice track. In Kenerate's Avatar Talk you upload the picture, upload or record the speech, pick one of 19 talking-photo engines and generate; the engine moves the lips, face and head in time with every word, for up to 10 minutes.

URL: https://kenerateai.com/make-photo-talk
Publisher: Kenerate AI (https://kenerateai.com)
Last updated: 6 October 2026

## Key facts
- Steps: 4
- Talking-photo engines: 19
- Longest speech: 10 min
- Photo: Up to 20 MB
- Audio: MP3, WAV, M4A and more · up to 50 MB · or the mic
- Free plan: Yes
- Kenerate Avatar (Kenerate): Photo + up to 10 min of speech → 720p or 1080p. Long talks and the sharpest everyday result.
- OmniHuman 1.5 (ByteDance): Photo + up to 60 s of audio → Engine decides. Singing photos and full-body performance.
- InfiniteTalk Duo (WaveSpeed): Photo of two + one track each → 480p or 720p. Two people in one picture.
- Sync Lipsync 3 (Sync Labs): Face photo + up to 5 min of speech → Engine decides. Mouth shapes that match every word.
- SkyReels V3 Avatar (Skywork): Photo + up to 15 s of audio → 480p or 720p. Short clips with a described emotion.
- LTX 2.3 Lipsync (Lightricks): 5–20 s of speech; the photo is optional → 480p, 720p or 1080p. Sharp short clips for social posts.
- HeyGen Presenters (HeyGen): Audio + one of 500 stock presenters → 720p, 1080p or 4K. No photo of your own.

## Steps
1. Choose the photo — A sharp face looking at the camera, mouth closed, nothing covering it; any image up to 20 MB. Paintings, cartoons and 3D characters work too.
2. Give it a voice — Upload a voice file (MP3, WAV, M4A and more, up to 50 MB), record it on the mic, or write the words in Voice Studio and pick the take from History.
3. Pick an engine — Kenerate Avatar is preselected and takes up to 10 minutes; OmniHuman 1.5 suits singing; InfiniteTalk Duo gives two people in one photo a voice each.
4. Generate and save — Add an optional direction such as "warm and friendly, gentle nods", generate, then download or share the video from your history.

## In depth

### What the engine actually does
A talking-photo engine reads the audio, works out the mouth shape for each sound and redraws the face frame by frame to match. Good engines also add blinks, small head turns and shoulder movement, so the picture doesn't look like a cut-out with a moving mouth. Some, such as OmniHuman 1.5, animate the whole body.

### Choosing the photo
The photo sets the ceiling for the result. A face that fills a good part of the frame, looks at the camera and is evenly lit gives the engine the most to work with.
- Good: a passport-style or head-and-shoulders shot, a painted portrait, a 3D character render.
- Harder: profile views, hands over the mouth, heavy shadows, group photos with small faces.
- Avoid: photos of people who haven't agreed to be animated.

### Choosing the audio
Clean speech matters more than a fancy microphone. Record in a quiet room, keep music out of the track, and trim long silences at the start. For singing, upload the vocal on its own if you can; the instrumental can go back in when you edit the final video.

## FAQ
Q: How do I make a picture talk for free?
A: Sign up and open Avatar Talk: it works on the free plan with the sign-up credits. Upload the photo, add or record the voice, keep Kenerate Avatar as the engine and generate. Short clips use less, so test with a sentence or two before you run a long script.

Q: Can I make a photo talk with my own voice?
A: Yes. Choose Record audio and speak into the microphone, or upload a recording you already have. Avatar Talk accepts common audio files such as MP3, WAV, M4A, AAC, OGG and FLAC up to 50 MB.

Q: Can I type the words instead of recording them?
A: Yes, in two steps. Write the script in Voice Studio and generate the voice there, then in Avatar Talk pick that take from History as the audio. The link to Voice Studio sits right under the audio box.

Q: Can I make an old family photo talk?
A: Yes, if the face is clear and looks roughly toward the camera. Restore or upscale a faded or blurry print first, crop to head and shoulders, then animate it. Only do this with photos your family is happy to see animated.

Q: Can I make two people in the same photo talk?
A: Yes. InfiniteTalk Duo, InfiniteTalk Fast Duo and LongCat 1.5 Duo take a photo of two people and one audio track for each, played together or in turn, so each person speaks their own lines.

Q: How long can the talking video be?
A: Up to 10 minutes of speech on Kenerate Avatar, InfiniteTalk and Kling Avatar 1 Pro; 5 minutes on Kling Avatar 2, Sync Lipsync 3 and VEED Fabric; 60 seconds on OmniHuman 1.5; 5 to 20 seconds on LTX Lipsync.

Q: Why does my talking photo look strange?
A: Usually the photo: a turned head, an open mouth, sunglasses or a very small face. Music under the voice also confuses the lip sync. Fix those first; if it still looks off, try Sync Lipsync 3 for the mouth or OmniHuman 1.5 for more natural movement.

Q: Can I make a celebrity's photo talk?
A: No. Only animate photos of yourself, characters you made, or people who agreed to it.

## Related pages
- Talking photo AI: https://kenerateai.com/talking-photo-ai
- AI lip sync: https://kenerateai.com/ai-lipsync-generator
- AI character animation: https://kenerateai.com/ai-character-animation
- Vidnoz alternative: https://kenerateai.com/vidnoz-alternative

## Sources
- Kenerate Avatar Talk: https://kenerateai.com/app/avatar-talk
- Kenerate Voice Studio: https://kenerateai.com/app/voice
- OmniHuman-1 project page: https://omnihuman-lab.github.io/