Make a photo talk
- Type
- Video app
- Input
- Photo + Voice + optional text
- Output
- MP4 video
- Options
- Resolution: 480p, 720p
- Price
- From 4,500 credits per minute
- Plan
- All plans, including Free
Add a portrait and a voice clip, and get a video of that person speaking the words: lips in sync, natural blinks and small head movements. Good for presenters, explainers, greetings and characters.
How to make a talking video
- Photo: one person, facing the camera, face clearly visible.
- Voice: an MP3 or WAV of the words to speak, up to 2 minutes.
- Resolution: 480p for drafts and social, 720p for sharper results.
- Add direction (optional): "calm and friendly, small nods".
- Generate. It takes a few minutes, longer for long clips.
Uses
- Explainers and course videos without filming.
- Product and support videos with a consistent presenter.
- Characters and mascots that speak your script.
- Personal greetings from an illustrated or AI-made portrait.
Tips
- Clean audio, clear speech. Remove background noise first for the best lip sync.
- Match the voice to the face. A mismatch is the first thing viewers notice.
- Draft at 480p, then render the final at 720p.
- Need a voice? Write the script in Text to Speech and download the audio.