TikTok Transcript

Fetch TikTok captions with yt-dlp and save durable transcript artifacts. Read bounded excerpts for narrow questions or the full timestamp-free text for complete summaries. Videos without captions can be transcribed locally with mlx-whisper (Apple Silicon).

This skill mirrors the workflow shape of the sibling youtube-transcript skill.

Workflow

Resolve this skill directory and run the bundled script. Always single-quote TikTok URLs in zsh because ? can be treated as a glob.
Fetch to local artifacts with fetch (one video) or channel (a user's videos). Do not read transcript.md or transcript.json into context by default.
Use transcript.txt for summaries or other content-only work; it removes timestamps and is cheaper to read than transcript.md.
Use preview, search, excerpt, or bounded text output when later work needs only a small portion.
Read the full transcript only when the task truly requires full-document reasoning and no smaller excerpt/search path is enough.

Commands

python3 <this-skill-dir>/scripts/fetch-tiktok-transcript.py list 'https://www.tiktok.com/@user/video/VIDEO_ID'