WaveSpeedVideo to textComing soon

wavespeed-ai/molmo2/video-understanding

wavespeed-ai/molmo2/video-understanding is a video to text tool from WaveSpeed that runs in the background and returns text. 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
text
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

FieldKindDefaultDescription
video requiredURL or file—Input video URL for understanding. Supports common video formats (MP4, MOV, WebM). Maximum 2 minutes.
taskone of
general, summary, analysis, counting, scene_description
generalType of understanding task. General: overall understanding. Summary: brief overview. Analysis: detailed breakdown. Counting: count objects/actions. Scene_description: describe scenes in sequence.
texttext—Optional guidance or specific instructions for the understanding task (e.g., 'Focus on the people' or 'Count the number of cars').

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": "wavespeed",
    "model": "wavespeed-ai/molmo2/video-understanding",
    "input": {
      "video": "<video>"
    }
  }'