transcribe-youtube

Download YouTube audio with yt-dlp and transcribe it to markdown using Whisper.

7|Updated May 28, 2026
One-click install
npx skills add https://github.com/zcaceres/skills --skill transcribe-youtube
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: transcribe-youtube
Source: https://github.com/zcaceres/skills/tree/main/skills/transcribe-youtube
Command: npx skills add https://github.com/zcaceres/skills --skill transcribe-youtube

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill eliminates the need to manually watch or listen to long YouTube videos to extract information, providing a clean, searchable markdown transcript instead.

Core Features & Use Cases

  • Automated Transcription: Uses OpenAI Whisper to generate accurate text from video audio.
  • Metadata Extraction: Automatically captures video title, channel, and upload date.
  • Use Case: Quickly generate a study guide or meeting summary from a long educational video or recorded presentation by converting the entire video content into a structured markdown file.

Quick Start

Ask the agent to transcribe the YouTube video at the provided URL and save the output to your transcripts folder.

Frequently Asked Questions about transcribe-youtube

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

FAQPage Schema
How do I convert a YouTube video to a text transcript?

To convert a YouTube video to a text transcript, the skill downloads the audio stream using yt-dlp and passes it to OpenAI Whisper to generate a searchable markdown file. This eliminates manually watching long videos to extract information.

Do I need to install yt-dlp and openai-whisper to transcribe YouTube videos?

Yes, you need local installations of yt-dlp and openai-whisper to transcribe YouTube videos. These dependencies are required to process the audio streams and convert speech to text using Whisper.

Can I extract video metadata like title and channel when transcribing YouTube audio?

Yes, you can extract video metadata like title and channel when transcribing YouTube audio. The skill automatically captures the video title, channel name, and upload date alongside the generated text transcript.

What is the best way to create a study guide from a long educational video?

The best way to create a study guide from a long educational video is to transcribe the entire video content into a structured markdown file. This provides a clean, searchable text format for quick information retrieval and repurposing.

What format are YouTube video transcriptions saved in?

YouTube video transcriptions are saved in markdown format. This structured markdown output includes the transcribed speech alongside automatically extracted metadata like the video title and upload date.