youtube-transcript

Extract YouTube video captions with yt-dlp and convert them to text transcripts.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/mrmtsuruya/hermes-backup --skill youtube-transcript-mrmtsuruya
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: youtube-transcript
Source: https://github.com/mrmtsuruya/hermes-backup/tree/main/skills/youtube-transcript
Command: npx skills add https://github.com/mrmtsuruya/hermes-backup --skill youtube-transcript-mrmtsuruya

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill addresses the challenge of obtaining transcripts from YouTube videos, ensuring users can quickly access and save the text content of any video they need.

Core Features & Use Cases

  • Transcript Extraction: Fetch and download the text captions from YouTube videos.
  • Automatic File Naming: Generates a file name based on the video's channel and title.
  • Custom Save Location: Allows users to specify a directory for the transcript file.
  • Use Case: For researchers or content creators who need to analyze the spoken content of YouTube videos without watching them.

Quick Start

Use the 'youtube-transcript' skill to get the transcript of a YouTube video by providing the video URL.

Frequently Asked Questions about youtube-transcript

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

FAQPage Schema
How do I extract the transcript text from a YouTube video?

To extract a YouTube transcript, this Skill fetches captions from a provided video URL and converts them into raw text. It automatically generates a file name based on the channel and video title for easy saving.

Do I need to install Python and yt-dlp to download YouTube captions?

Yes, you need both Python and yt-dlp installed. Yt-dlp handles downloading the subtitle data from the video, while Python processes the JSON captions and converts them into a plain text transcript.

Can I specify a custom save location for my extracted YouTube video transcript?

Yes, you can specify a custom directory for the transcript file. The Skill allows you to designate a specific save location while automatically naming the output file based on the video details.

What is the best way to analyze YouTube video content without watching the entire video?

The best way to analyze spoken content without watching is to extract the text captions. This Skill downloads subtitles via yt-dlp and converts them to a raw text format for quick reading and analysis.

Does this method work if a YouTube video only has auto-generated captions?

This Skill uses yt-dlp to fetch available subtitles or auto-generated captions from YouTube. As long as the video possesses caption data, the tool will download and convert the JSON into a readable text transcript.

Why are my YouTube transcripts extracted as JSON and how do I get plain text?

Yt-dlp downloads caption data in JSON format by default. This Skill uses Python to process that JSON data and convert it into a clean, raw text transcript file for your analysis.