LaunchKit · 2026
Back to Skills

Extract closed captions and subtitles from YouTube videos.

1
3.0k downloads
by @therohitdas

Setup & Installation

openclaw skills install @therohitdas/captions

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install captions

Version History

v1.4.1Feb 11, 2026 - Version note by skill developer:

ClawHub variant: minimal tapi-auth.js v3.0.0, only writes to ~/.openclaw/openclaw.json

What This Skill Does

Extracts closed captions and subtitles from YouTube videos using TranscriptAPI.com. Returns timestamped JSON or plain text transcripts. Supports both auto-generated and manually created CC tracks.

Returns structured JSON with per-caption start times and durations, making it usable for accessibility tools and timing-sensitive workflows, not just reading.

When to use it

  • Pulling a transcript from a lecture video to take notes
  • Finding the exact timestamp of a spoken quote in a video
  • Reviewing video content without watching it
  • Creating accessible text versions of YouTube content
  • Extracting dialogue for translation or subtitling

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: Get the transcript for https://www.youtube.com/watch?v=dQw4w9WgXcQ

AGENT
  1. 1Check that TRANSCRIPT_API_KEY is set
  2. 2Call TranscriptAPI with the video URL, format=json, and include_timestamp=true
  3. 3Parse the transcript array from the response
  4. 4Format each entry as [MM:SS] text and return to user
OUTPUT

[00:00:18] We're no strangers to love [00:00:21] You know the rules and so do I...

Requirements

Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.

TRANSCRIPT_API_KEY environment variable (obtain from transcriptapi.com)