youtube-transcript

Download YouTube video transcripts and captions using yt-dlp.

4|1|Updated Jan 13, 2026
One-click install
npx skills add https://github.com/rm2thaddeus/Aitor_Skills --skill youtube-transcript-rm2thaddeus
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: youtube-transcript
Source: https://github.com/rm2thaddeus/Aitor_Skills/tree/main/youtube-transcript
Command: npx skills add https://github.com/rm2thaddeus/Aitor_Skills --skill youtube-transcript-rm2thaddeus

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/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.
  • Transcription Fallback: Uses Whisper to transcribe audio if no subtitles are available.
  • Use Case: You need to analyze the spoken content of a lecture video on YouTube for research purposes. This Skill can download the transcript directly, saving you from manual note-taking or unreliable third-party services.

Quick Start

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 and auto-generated subtitles as plain text?

To download YouTube transcripts as plain text, the Skill fetches manual or auto-generated subtitles via yt-dlp and applies deduplication. It directly extracts subtitle tracks from the video URL and converts them into clean text.

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

Yes, you can transcribe YouTube audio to text when subtitles are missing. The Skill uses OpenAI Whisper as a fallback mechanism, extracting the audio stream first and then generating a transcript from the spoken content.

Do I need yt-dlp and Whisper installed to extract captions from a video URL?

You need yt-dlp installed to fetch video data and existing subtitles. Whisper is only required as a fallback for audio transcription if no caption tracks are found, and the Skill includes installation checks for both dependencies.

What is the difference between manual subtitles and auto-subtitles in YouTube transcript downloads?

Manual subtitles are human-authored caption tracks, while auto-subtitles are machine-generated. The Skill can list and download both types via yt-dlp, cleaning the output through plain text conversion and deduplication.

Why does my YouTube transcript download include duplicate text lines?

YouTube auto-subtitles often contain overlapping caption timestamps causing duplicate lines. The Skill addresses this by applying plain text conversion with deduplication to clean the downloaded transcript output.