falText to videoComing soon

minimax/h3-max/styles/vhs

Name: minimax/h3-max/styles/vhs
Brand: fal

minimax/h3-max/styles/vhs is a text to video tool from fal that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

$0.065 per second. Billed on duration, default 5. The final charge comes from usage.

Limits

Runs: In the background
Returns: video
Longest queue wait: 3600s
Run deadline: 3600s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`prompt` required	text	—	Describe the scene, action, camera and sound. VHS style and tape damage are applied automatically.
`image_url`	URL or file	—	Optional first-frame image. Use a 4:3 image for the classic VHS frame; the image's aspect ratio determines the output canvas.
`damage_level`	one of light, medium, heavy	medium	Tape wear: light adds subtle analog noise, medium adds visible damage, and heavy adds strong tracking errors and distortion.
`duration`	number (whole) 5 to 15	5	Requested video duration in seconds.
`aspect_ratio`	one of 21:9, 16:9, 4:3, 1:1, 3:4, 9:16	16:9	Video aspect ratio for text-only generation. Ignored when image_url is provided.
`seed`	number (whole)	—	Random seed. Omit to choose one automatically.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "minimax/h3-max/styles/vhs",
    "input": {
      "prompt": "A camcorder explores an abandoned shopping mall at midnight. A lone carousel starts turning beneath flickering fluorescent lights. Handheld push-in, mechanical…"
    }
  }'