youtube-transcript

Download YouTube video transcripts via yt-dlp and transcribe audio with Whisper.

5|2|Updated Jan 24, 2026
One-click install
npx skills add https://github.com/s1366560/agi-demos --skill youtube-transcript-s1366560
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: youtube-transcript
Source: https://github.com/s1366560/agi-demos/tree/main/.memstack/skills/youtube-transcript
Command: npx skills add https://github.com/s1366560/agi-demos --skill youtube-transcript-s1366560

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yt-dlp, openai-whisper, and includes scripts (resource) components.

What problem does it solve?

This Skill automates the process of downloading transcripts, captions, or subtitles from YouTube videos, making video content accessible as text.

Core Features & Use Cases

  • Transcript Download: Fetches manual or auto-generated subtitles from YouTube URLs.
  • Whisper Transcription: Transcribes audio using Whisper if no subtitles are available.
  • Use Case: You need to analyze the spoken content of a lecture video on YouTube for research. This Skill can download the transcript directly, saving you the effort of manual transcription.

Quick Start

Use the youtube-transcript skill to download the transcript for the YouTube video at https://www.youtube.com/watch?v=example.

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 or subtitles as text?

To download YouTube transcripts, this Skill fetches available manual or auto-generated subtitles using yt-dlp and outputs them as VTT or plain text. It directly extracts the text content from the provided YouTube video URL.

Can I transcribe YouTube audio to text if no subtitles are available?

You can transcribe YouTube audio to text using Whisper. When a video lacks available subtitles, the Skill automatically downloads the audio and performs transcription via OpenAI Whisper to generate the text.

Does this YouTube transcript tool output VTT and plain text formats?

Yes, the YouTube transcript tool supports both VTT and plain text output formats. It processes the downloaded captions or transcribed audio to deliver the final text in your preferred format.

Do I need yt-dlp and openai-whisper installed to extract YouTube captions?

Yes, you need yt-dlp and openai-whisper installed. The Skill relies on yt-dlp to fetch available subtitles and uses openai-whisper to transcribe audio when no captions are found.

What is the best way to get text from a YouTube lecture video for research?

The best way to get text from a YouTube lecture is to automate extraction with this Skill. It fetches existing video transcripts instantly or transcribes the audio, saving you from manual transcription efforts.

Are there limitations when downloading auto-generated YouTube subtitles?

A limitation occurs when a YouTube video has no available subtitles or auto-captions. In this case, the Skill must download and transcribe the audio, which requires openai-whisper and may take more processing time.