MiniMax · video
MiniMax H3 Max Talking Photo
A photo speaks your audio with H3 Max, lips in sync, up to 15 seconds and 2K.
Talking photo
- Resolution
- 480p, 768p, 1080p, 2K
- References
- Up to 2 image or audio files
About MiniMax H3 Max Talking Photo
MiniMax H3 Max Talking Photo makes a photo speak: the mouth is synchronized to the audio you upload, using MiniMax's H3 Max. Priced at $0.13 per second of audio, at 480p, 768p, 1080p and 2K.
The resolution is part of the price: $0.20 per second at the default setting, more at 2K. A typical generation takes about 4 min.
Good for
- Short talking clips from a photo, with a choice of resolution up to 2K
Getting good results
- The provider needs an audio track of a few seconds at least; the video lasts exactly as long as the audio.
- The output takes the supported shape nearest to your image, so crop the photo to the shape you want first.
MiniMax H3 Max Talking Photo questions
How is MiniMax H3 Max Talking Photo priced?
By the seconds of audio and the resolution: $2.00 for a short line at the default resolution, $3.00 for the longest audio accepted.