Model API

MiniMax H3 Max

Write a scene and turn it into a video of up to 15 seconds. Other modes animate a photo or change a clip you already have.

Model id

Use this in every request

minimax/h3-max/lip-sync/image-to-video

This model has other modes with their own ids: minimax/h3-max/text-to-video, minimax/h3-max/image-to-video, minimax/h3-max/camera-controls, minimax/h3-max/insert-video, minimax/h3-max/extend-video, minimax/h3-max/3d-to-video.

Run it

Quote the input, start the generation with the quote, then poll the job. Set RAYWAKE_API_KEY first; see Authentication.

# 1. Price the exact input (quotes are valid for up to 10 minutes)
curl -s https://api.raywake.com/v1/quotes \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/h3-max/lip-sync/image-to-video",
  "input": {
    "image_url": "https://example.com/input.png",
    "audio_url": "https://example.com/input.mp3"
  }
}'

# 2. Start the generation with the quote_id from step 1
curl -s https://api.raywake.com/v1/generate \
  -H "Authorization: Bearer $RAYWAKE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"model": "minimax/h3-max/lip-sync/image-to-video", "quote_id": "QUOTE_ID", "input": {"image_url":"https://example.com/input.png","audio_url":"https://example.com/input.mp3"}}'

# 3. Poll until the status is terminal
curl -s https://api.raywake.com/v1/jobs/JOB_ID \
  -H "Authorization: Bearer $RAYWAKE_API_KEY"

Input

Input fields for minimax/h3-max/lip-sync/image-to-video
Name	Type	Description
`image_url`required	string (image URL)	Image to animate. The aspect ratio must be between 0.4 and 2.5.
`audio_url`required	string (URL)	Audio to synchronize the mouth movements to, at least 5 seconds long. Supports up to 15 minutes. The output video matches the supplied audio duration.
`resolution`	string (enum)	Output resolution. Uses the supported aspect ratio nearest the image. Default: `768P` One of: `480P`, `768P`, `1080P`, `2K`
`enable_transcription`	boolean	Transcribe the supplied audio to guide lip synchronization. Turn this off if the audio has a lot of non-word sound, such as music, singing, laughter or noise, which the transcript may turn into words that were never spoken. Default: `false`
`seed`	integer	Random seed; selected randomly if omitted.

Output

A succeeded job lists its results under outputs, stored on our side. See Jobs for every field.

Job excerpt

"outputs": [
  { "type": "video", "url": "https://…", "mime_type": "video/mp4", "thumbnail_url": "https://…" }
]

Pricing

1080P · per second$0.2536/ second
2K · per second$0.5071/ second
480P · per second$0.0793/ second
768P · per second$0.1268/ second

The exact charge for your input comes from a quote. How charges settle