youtube-transcribe

Download YouTube audio and transcribe it locally with whisper models.

Updated Apr 9, 2026
One-click install
npx skills add https://github.com/States-Media/claude-code-starter --skill youtube-transcribe-states-media
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: youtube-transcribe
Source: https://github.com/States-Media/claude-code-starter/tree/main/skills/youtube-transcribe
Command: npx skills add https://github.com/States-Media/claude-code-starter --skill youtube-transcribe-states-media

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables users to transcribe YouTube videos locally, eliminating the need for online services and API keys, which speeds up content analysis and note-taking.

Core Features & Use Cases

  • Offline Transcription: Downloads and transcribes YouTube videos without relying on internet APIs.
  • Multi-Model Support: Supports whisper.cpp and openai-whisper, allowing flexibility in transcription models.
  • Use Case: Transcribe an educational lecture from YouTube to review key points later without internet dependency or privacy concerns.

Quick Start

Use the youtube-transcribe skill to download and transcribe a YouTube video by providing its URL as an argument.

Frequently Asked Questions about youtube-transcribe

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

FAQPage Schema
How do I transcribe a YouTube video offline without an API key?

You can transcribe a YouTube video offline by downloading the audio locally and converting it to text using whisper models, which eliminates the need for internet APIs or API keys. This Skill automates that entire process.

Do I need yt-dlp and ffmpeg to download YouTube audio for transcription?

Yes, you need yt-dlp and ffmpeg to download and process YouTube audio for transcription. These libraries handle audio extraction efficiently, allowing whisper models to convert the audio into text.

Can I use whisper.cpp or openai-whisper for local speech-to-text?

Yes, you can use either whisper.cpp or openai-whisper for local speech-to-text. This Skill supports both transcription models, providing flexibility depending on your local environment and performance requirements.

What is the best way to transcribe educational lectures from YouTube for research?

The best way to transcribe educational lectures for research is using local offline transcription. This ensures privacy and allows you to review key points and document content without depending on external online services.

Does offline YouTube transcription work for privacy-sensitive content?

Yes, offline YouTube transcription is suitable for privacy-sensitive content. By downloading audio and transcribing it locally with whisper, your data never leaves your machine, ensuring complete privacy during processing.

Why use local whisper models instead of online speech-to-text services?

Local whisper models provide offline transcription without relying on internet APIs, speeding up content analysis and note-taking. This approach avoids API keys and online service dependencies, offering a faster, private workflow.