Transcriptapi

This is a full YouTube data wrapper that pulls transcripts, searches videos and channels, browses uploads, and handles playlists through a single API key from transcriptapi.com. Free tier gives you 100 credits to start. It's designed to trigger automatically when Claude sees video links, handles, or topics where video content is likely fresher than text (tutorials, talks, product demos). The channel resolution is free, transcript and search calls cost 1 credit each. User-Agent header is required or Cloudflare blocks you. Useful when you need actual spoken content from videos or want to search within a specific channel's back catalog instead of guessing what's out there.

skills.sh installs: 875
GitHub stars: 1.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add zeropointrepo/youtube-skills --skill transcriptapi --agent claude-code

Installs into .claude/skills of the current project.

Files

TranscriptAPI

Full YouTube data toolkit via TranscriptAPI.com. Transcripts, search, channels, playlists — one API key.

Setup

If $TRANSCRIPT_API_KEY is not set, read references/auth-setup.md and follow the instructions there to get and store the key.

Required Headers

Every request needs two headers:

Authorization: Bearer $TRANSCRIPT_API_KEY
User-Agent: your agent's name and version if known (e.g. HermesAgent/0.11.0, ClaudeCode/1.0). Version is optional — agent name alone is fine. Do not omit this header or send a bare default — Cloudflare will return a 403 (error code 1010) and block the request.

API Reference

Full OpenAPI spec: transcriptapi.com/openapi.json — consult this for the latest parameters and schemas.

Auth

All requests: -H "Authorization: Bearer $TRANSCRIPT_API_KEY"

Endpoints

Channel endpoints accept channel — an @handle, channel URL, or UC... ID. No need to resolve first. Playlist endpoints accept playlist — a playlist URL or ID.