falVideo to videoComing soon

fal-ai/auto-caption

fal-ai/auto-caption 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.

Priced by usage

Pricing

$0.13 per video. The final charge comes from usage.

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

FieldKindDefaultDescription
video_url requiredURL or file—URL to the .mp4 video with audio. Only videos of size <400MB are allowed.
txt_colortextwhiteColour of the text. Can be a RGB tuple, a color name, or an hexadecimal notation.
txt_fonttextStandardFont for generated captions. Choose one in 'Arial','Standard','Garamond', 'Times New Roman','Georgia', or pass a url to a .ttf file
font_sizenumber (whole)24Size of text in generated captions.
stroke_widthnumber (whole)1Width of the text strokes in pixels
left_alignJSONcenterLeft-to-right alignment of the text. Can be a string ('left', 'center', 'right') or a float (0.0-1.0)
top_alignJSONcenterTop-to-bottom alignment of the text. Can be a string ('top', 'center', 'bottom') or a float (0.0-1.0)
refresh_intervalnumber
0.5 to 3
1.5Number of seconds the captions should stay on screen. A higher number will also result in more text being displayed at once.
text_caseone of
default, upper, lower
defaultCapitalization to apply to subtitle text. 'upper' converts text to UPPERCASE, 'lower' converts to lowercase, and 'default' preserves the original casing produced by the speech recognizer.

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/auto-caption",
    "input": {
      "video_url": "<video_url>"
    }
  }'