falImage to textComing soon
falfal-ai/marlin
fal-ai/marlin is an image to text tool from fal 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 pendingPricing
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
| Field | Kind | Default | Description |
|---|---|---|---|
video_url required | URL or file | — | URL of the video to caption. Up to ~2 minutes is supported. |
prompt required | text | — | Caption prompt sent to the model. The example value is Marlin's canonical training prompt — overriding usually degrades output quality. |
max_tokens | number (whole) 64 to 4096 | 2048 | Maximum number of tokens to generate for the caption. |
do_sample | true or false | false | If true, sample with temperature/top_p; if false, use greedy decoding. |
temperature | number 0 to 2 | 1 | Sampling temperature. Only used when do_sample is true. |
top_p | number … to 1 | 1 | Nucleus sampling threshold. Only used when do_sample is true. |
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/marlin",
"input": {
"video_url": "https://v3b.fal.media/files/b/0a913346/ZbEaRKcU1dMNYkHl9g1Zz_T4QEyOJ3R3WzuQS9.mp4",
"prompt": "Provide a spatial description of this clip followed by time-ranged events.\nFor each event, give the time range as <start - end> and a short description."
}
}'