YouTube Transcript API

Get the transcript of any YouTube video from a single URL. FrameFetch returns the caption track when one exists, and falls back to a Whisper transcription when it does not — plus metadata, view/like counts, and frames if you want them.

Read the docsPricing

What you get

For this platform FrameFetch returns metadata, insights (views/likes/comments), transcript (captions or Whisper), and parametric frames. One JSON response, billed per call (every response includes a cost block).

Quickstart

curl -X POST https://framefetch.net/v1/extract \
  -H "Authorization: Bearer <your-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://www.youtube.com/watch?v=jNQXAC9IVRw",
    "fields": ["metadata", "transcript"]
  }'

Get a key with POST /v1/keys (free credit). Full reference in the docs. Agents can pay per call with x402 (USDC) — no account.

Use it from an AI agent (MCP)

FrameFetch ships an MCP server at POST https://framefetch.net/mcp with the tools framefetch_extract and framefetch_platform_capabilities — point your agent at a YouTube URL directly.

FAQ

Does it work when a YouTube video has no captions?

Yes. If there is no caption track, FrameFetch transcribes the audio with Whisper and returns the text the same way.

Can I also get frames or metadata in the same call?

Yes — add "frames" and "metadata" to the fields array in one /v1/extract call.

Does it support YouTube Shorts?

Yes, Shorts URLs work the same way. See the Shorts page.