youtube-transcript

Fetch YouTube transcripts and captions using yt-dlp, optionally via Whisper, producing .vtt files.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/KaiBoo404/agent-skills-with-project-template --skill youtube-transcript-kaiboo404
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: youtube-transcript
Source: https://github.com/KaiBoo404/agent-skills-with-project-template/tree/main/.agents/skills/youtube-transcript
Command: npx skills add https://github.com/KaiBoo404/agent-skills-with-project-template --skill youtube-transcript-kaiboo404

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Downloading and extracting transcripts, captions, and subtitles from YouTube videos is often manual, time-consuming, and inconsistent. This skill automates the process, supporting manual subtitles, auto-generated subtitles, and transcription via Whisper when subtitles are unavailable.

Core Features & Use Cases

  • Subtitle extraction: Retrieve manual or auto-generated subtitles (VTT) from YouTube videos using yt-dlp.
  • Flexible transcription: When subtitles are not available, optionally perform Whisper-based transcription after user confirmation.
  • User-friendly workflow: Handles file naming, progress feedback, and cleanup of temporary files for tidy results.

Quick Start

Provide a YouTube URL and this skill will fetch the available transcripts or start a Whisper transcription if needed.

Frequently Asked Questions about youtube-transcript

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I download YouTube transcripts automatically using yt-dlp?

To download YouTube transcripts automatically, provide a video URL and the skill uses yt-dlp to fetch manual or auto-generated subtitles, outputting VTT files while handling filename cleanup automatically.

Can I get subtitles for a YouTube video when auto-generated captions are unavailable?

Yes, when subtitles are unavailable, this skill optionally performs Whisper transcription after user confirmation to generate the missing captions. This ensures you get a transcript even for videos lacking native subtitles.

Do I need to install Whisper to extract YouTube captions with this skill?

You must install yt-dlp to extract YouTube captions, but Whisper is optional and only required when you need to transcribe videos lacking available subtitles.

What is the best way to fetch YouTube subtitles as VTT files for automation workflows?

The best way to fetch YouTube subtitles as VTT files for automation is using this skill, which leverages yt-dlp to retrieve captions and manages temporary file cleanup. This provides clean VTT outputs suitable for downstream processing.

Does this YouTube transcript skill support both manual and auto-generated subtitles?

Yes, this YouTube transcript skill supports downloading both manual and auto-generated subtitles via yt-dlp. It prioritizes available subtitles before falling back to optional Whisper transcription if none exist.

Why does YouTube subtitle extraction fail for some videos and how is it handled?

YouTube subtitle extraction fails when a video has no manual or auto-generated captions available. This skill handles that limitation by optionally prompting for Whisper-based transcription to generate the missing text.