TikTok Video Data API

Turn a TikTok video URL into structured data: metadata (author, duration), engagement insights, a Whisper transcript of the spoken audio, and parametrically-sampled frames — through one API call or an MCP tool.

Read the docsPricing

What you get

For this platform FrameFetch returns metadata, insights, Whisper transcript, 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.tiktok.com/@user/video/1234567890",
    "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 TikTok URL directly.

FAQ

Do I need TikTok login or cookies?

No. You send the public video URL; FrameFetch handles retrieval.

How are TikTok transcripts produced?

TikTok videos are transcribed from audio with Whisper, since captions are not reliably exposed.

Can I extract every frame of a TikTok?

Yes, up to 1000 frames per call; use mode "all" or "every_n" and downscale with width to control cost.