Video transcription

AI agents call video.transcript to get a transcript of public media. YouTube is resolved server-side through Supadata; other public URLs use audio-only server-side extraction before ASR. The CLI’s data guarantees only text: timestamped segments are written to a local sidecar file referenced by meta.segments_file, and detected language, source, and duration are not part of the CLI’s compacted output.

Call with a public URL

cralo tools call video.transcript \
  --input '{"url":"https://www.youtube.com/watch?v=example","language":"en"}' \
  --max-price 2.00 \
  --json

URL resolution happens on the hosted worker. The CLI does not download media or install yt-dlp.

Prefer official captions

cralo tools call video.transcript \
  --input '{"url":"https://www.youtube.com/watch?v=example","use_official_transcript":true}' \
  --json

This YouTube-only path does not fall back to ASR when captions are unavailable.

Pricing and limits

ASR is billed per minute, with a one-minute minimum.
Maximum duration is 120 minutes.
YouTube is supported through Supadata. Other public URLs are accepted when their platform is supported by the worker’s audio-only extractor.
Use --async for long media and query the invocation later.

Agents must not use Cralo to bypass private, DRM-protected, or members-only media restrictions. Respect source-platform terms.

Getting started

Using Cralo

CLI reference

Video transcription

Call with a public URL

Prefer official captions

Pricing and limits

​Call with a public URL

​Prefer official captions

​Pricing and limits

Call with a public URL

Prefer official captions

Pricing and limits