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.
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).
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.
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.
Yes. If there is no caption track, FrameFetch transcribes the audio with Whisper and returns the text the same way.
Yes — add "frames" and "metadata" to the fields array in one /v1/extract call.
Yes, Shorts URLs work the same way. See the Shorts page.