The model makes the clip. Video API makes it ready to ship.

MiniMax H3 Max Lip Sync Image to Video

Image Gen·minimax-h3-max·by fal

MiniMax H3 Max Lip Sync Image-to-Video turns a source image and audio into synchronized video for avatars, promos, and character clips on each::labs.

Try it now →
API reference
Runtime (p50)
-
Estimated price
$0.05–$0.32 per second, depending on resolution
Call the API
prediction.sh
sh
curl -X POST \
  -H "Authorization: Bearer $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "minimax-h3-max-lip-sync-image-to-video",
    "input": {
        "audio_url": "https://cdn-us.eachlabs.ai/defaults/dae499acb7994d1d9b6d9ba45e86c0b2.mp3",
        "image_url": "https://cdn-us.eachlabs.ai/defaults/ed7b0aecad51482db43f40af3aaa8455.png",
        "resolution": "768P",
        "enable_safety_checker": true
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/

Related models

4 models
Flux 3 | Image to Video Timestamped AI model preview
Flux 3 | Image to Video TimestampedBlack Forest Labs
Alibaba | Wan | 3.0 | Image to Video AI model preview
Alibaba | Wan | 3.0 | Image to VideoAlibaba
Pruna | P-Video 2 AI model preview
Pruna | P-Video 2Pruna AI
Google | Gemini Omni 1.1 Flash | Image to Video AI model preview
Google | Gemini Omni 1.1 Flash | Image to VideoGoogle
* FAQ

About MiniMax H3 Max Lip Sync Image to Video

01 / 03

What is MiniMax H3 Max Lip Sync Image-to-Video?

MiniMax H3 Max Lip Sync Image-to-Video generates a short video from a source image and an audio file. The model animates mouth movement to match the supplied soundtrack, making it useful for avatar clips, character dialogue, and product videos that need synchronized speech.