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

Minimax H3 Max Recast

Video → Video·minimax-h3-max·by Minimax

Minimax H3 Max Recast transforms video with reference photos to replace people while preserving motion, camera work, cuts, and audio for creative video editing.

Try it now →
API reference
Runtime (p50)
-
Estimated price
$0.30–$0.45 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-recast",
    "input": {
        "video_url": "https://cdn-us.eachlabs.ai/defaults/1dbe26936ee243588a10de644dfaa862.mp4",
        "resolution": "768P",
        "reference_image_urls": [
            "https://cdn-us.eachlabs.ai/defaults/583d0c9c2eb547d79bd7e9c6b28dee91.png"
        ]
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/

Related models

4 models
Google | Gemini Omni 1.1 Flash | Video Editing AI model preview
Google | Gemini Omni 1.1 Flash | Video EditingGoogle
HLS Ladder AI model preview
HLS LadderUnified AI API for hundreds models. Access video, image, and audio generation from leading providers through one integration with eachlabs.
MiniMax H3 Max Turbo Extend Video AI model preview
MiniMax H3 Max Turbo Extend Videofal
Topaz Proteus 1 AI model preview
Topaz Proteus 1topaz
* FAQ

About Minimax H3 Max Recast

01 / 03

What is Minimax H3 Max Recast?

Minimax H3 Max Recast is a video-to-video model for replacing people in an existing clip with identities from reference photos. It preserves the source motion, camera work, cuts, and audio, making character recasting the focus rather than generating an entirely new scene from text.