fal
Auto Subtitle
Burns word-timed captions into a video, in the font, colors and position you choose, and returns the transcript with SRT and VTT. Billed per minute of the video. On Leap, it sits beside 131 other models in one studio.
- Captions
- Video to video
- Start free, no card
- Every top model, one account
- Pay per run, priced before it starts
- 01Describe what you want to see
- 02See the exact price, then press go
- 03Keep it in your library, or take it further
Start with an idea
Bring a photo to Auto Subtitle
Auto Subtitle works on a picture you already have. Open it in the studio, add your photo, and see the result in seconds.
Side by side
More video models on Leap
Questions
Auto Subtitle on Leap, answered.
- Is this the real Auto Subtitle?
- Yes. Leap sends your request to fal's model through its provider and gives you back what it makes. Switch to any other model in the same studio when an idea needs it.
- What does it cost?
- In dollars, per run: the provider's list price plus 10%. You see the exact price before every run, a run that fails costs nothing, and there is no subscription. Every model's price is on the pricing page.
- Do I need a fal account?
- No. One Leap account and one balance run Auto Subtitle and every other model, in the studio, through the API and from your agents.
- What happens to what I make?
- It stays in your library while your account is active, ready to use anywhere.
Your idea, Auto Subtitle.
Start free, no card. Every run shows its price before it starts.
Make it with Auto SubtitleFor developers
Run Auto Subtitle from code
- Model ID
- fal/auto-subtitle
- Makes
- Video
- Pricing
- Per run, quoted first: POST /v1/quotes
Inputs
What the model takes. Leave out anything with a default.
Videovideo
An image, requiredThe video to caption: an uploaded file, by ID. Up to 10 minutes and 100 MB.
Languagelanguage
English, Spanish, Portuguese, French, German, Italian, Dutch, Polish, Russian, Ukrainian, Turkish, Arabic, Hebrew, Persian, Hindi, Bengali, Urdu, Tamil, Indonesian, Malay, Filipino, Vietnamese, Thai, Chinese, Japanese, Korean, Swedish, Danish, Norwegian, Finnish, Greek, Czech, Romanian, Hungarian, Swahili, Yoruba. Default: EnglishThe language spoken in the video.
Fontsettings.font
Montserrat, Poppins, Inter, Bebas Neue, Oswald, Roboto. Default: Montserrat
Font sizesettings.font_size
20 to 150. Default: 100
Font weightsettings.font_weight
Normal, Bold, Black. Default: Bold
Text colorsettings.font_color
White, Black, Yellow, Orange, Red, Pink, Purple, Blue, Cyan, Green, Magenta, Gray, Brown. Default: White
Spoken word colorsettings.highlight_color
White, Black, Yellow, Orange, Red, Pink, Purple, Blue, Cyan, Green, Magenta, Gray, Brown. Default: Purple
Outline widthsettings.stroke_width
0 to 10. Default: 3
Outline colorsettings.stroke_color
White, Black, Yellow, Orange, Red, Pink, Purple, Blue, Cyan, Green, Magenta, Gray, Brown. Default: Black
Backgroundsettings.background_color
None, White, Black, Yellow, Orange, Red, Pink, Purple, Blue, Cyan, Green, Magenta, Gray, Brown. Default: None
Background opacitysettings.background_opacity
0 to 1. Default: 0
Positionsettings.position
Bottom, Center, Top. Default: Bottom
Vertical offsetsettings.y_offset
-200 to 200. Default: 75
Words at a timesettings.words_per_line
1 to 12. Default: 3
Bounce insettings.animation
On or off. Default: onEach caption bounces in as it appears.
The request
The same envelope for every model; only the model and its input change. With prefer: wait=60 the answer holds the result. Agents can call it through the MCP server at mcp.tryleap.ai.
curl https://api.tryleap.ai/v1/generations \ -H "x-api-key: $LEAP_API_KEY" \ -H "content-type: application/json" \ -H "prefer: wait=60" \ -d '{ "model": "fal/auto-subtitle", "input": { "video": "file_..." } }'