youtube-transcript

Retrieve YouTube transcripts and convert VTT captions to plain text.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires yt-dlp, openai-whisper.

What problem does it solve?

Manually transcribing YouTube videos or finding reliable captions can be incredibly time-consuming and frustrating. This Skill automates the entire process of downloading available transcripts or generating new ones, saving significant effort for researchers, students, and content creators.

Core Features & Use Cases

  • Automated Transcript Download: Intelligently prioritizes manual subtitles, falls back to auto-generated, and offers Whisper transcription as a last resort if no captions are available.
  • Intelligent Installation & Checks: Automatically installs yt-dlp and openai-whisper if needed, and lists all available subtitle languages before attempting any download.
  • Clean Plain Text Output: Converts messy WebVTT (.vtt) files into clean, deduplicated plain text (.txt) for easy reading, analysis, or integration into other documents.
  • Use Case: You need to quickly extract key information from a long YouTube lecture for your research or to create a blog post. Provide the video URL, and this Skill will deliver a clean, readable text transcript, allowing you to analyze the content without watching the entire video, saving hours of manual work.

Quick Start

Download the transcript for this YouTube video: https://www.youtube.com/watch?v=dQw4w9WgXcQ

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 video transcripts as text?

Download YouTube transcripts by providing a video URL. The Skill retrieves available subtitles (manual or auto-generated) and converts them to clean plain text, or uses Whisper transcription if no captions exist, outputting a readable `.txt` file.

Can I extract captions from YouTube videos without watching them?

Yes. This Skill automatically downloads and extracts captions or generates transcriptions from YouTube videos, letting you access full text content instantly without viewing the video, ideal for research or content analysis.

What happens if a YouTube video doesn't have captions or subtitles?

If manual or auto-generated subtitles aren't available, the Skill offers Whisper-based transcription to generate a transcript from the video's audio, with user confirmation before proceeding.

Does this work with multiple subtitle languages on YouTube?

Yes. The Skill lists all available subtitle languages before downloading, allowing you to select and extract transcripts in the language you need.

How do I convert WebVTT subtitle files to plain text?

The Skill automatically converts downloaded WebVTT (`.vtt`) files into clean, deduplicated plain text (`.txt`), removing timestamps and formatting for easy reading and downstream analysis.

Do I need to install yt-dlp or Whisper separately?

No. The Skill automatically detects and installs `yt-dlp` and `openai-whisper` if needed, handling setup and dependency checks before retrieving or generating transcripts.