falVideo to videoComing soon

fal-ai/sam-3/video-rle

Name: fal-ai/sam-3/video-rle
Brand: fal

fal-ai/sam-3/video-rle is a video 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.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: video
Longest queue wait: 3600s
Run deadline: 1800s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`video_url` required	URL or file	—	The URL of the video to be segmented.
`mask_url`	URL or file	—	The URL of the mask to be applied initially.
`prompt`	text		Text prompt for segmentation. Use commas to track multiple objects (e.g., 'person, cloth').
`point_prompts`	JSON	[]	List of point prompts with frame indices.
`box_prompts`	JSON	[]	List of box prompts with optional frame_index.
`apply_mask`	true or false	false	Apply the mask on the video.
`boundingbox_zip`	true or false	false	Return per-frame bounding box overlays as a zip archive.
`detection_threshold`	number 0.01 to 1	0.5	Detection confidence threshold (0.0-1.0). Lower = more detections but less precise. Defaults: 0.5 for existing, 0.7 for new objects. Try 0.2-0.3 if text prompts fail.
`frame_index`	number (whole)	0	Frame index used for initial interaction when mask_url is provided.

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": "fal-ai/sam-3/video-rle",
    "input": {
      "video_url": "https://v3b.fal.media/files/b/elephant/NQdDxB0Ddfo82SPLbhYDp_bedroom.mp4"
    }
  }'