youtube-transcription

Getting Started

1. Install the skill using the command above
2. Open your AI coding agent (Claude Code, Codex, Gemini CLI, or Cursor)
3. Reference the skill in your prompt
4. The AI will use the skill's capabilities automatically

Example Prompts

• "Write a blog post about the benefits of AI-assisted development"
• "Create social media copy for the product launch announcement"

Transcribe YouTube videos to text using OpenAI Whisper and yt-dlp.

Overview

This skill downloads audio from YouTube videos using yt-dlp and transcribes it using OpenAI's Whisper model. Supports multiple output formats (txt, srt, vtt, json) and various model sizes for different accuracy/speed tradeoffs.

Instructions

1. Install dependencies

# Install whisper and yt-dlp
pip install openai-whisper yt-dlp

# Verify ffmpeg is installed (required for audio processing)
ffmpeg -version

If ffmpeg is missing:

• macOS: brew install ffmpeg
• Ubuntu/Debian: sudo apt install ffmpeg
• Windows: Download from https://ffmpeg.org/download.html

2. Download audio from YouTube

# Download best audio quality as WAV
yt-dlp -x --audio-format wav -o "%(title)s.%(ext)s" "YOUTUBE_URL"

# Download as MP3 (smaller file)
yt-dlp -x --audio-format mp3 -o "%(title)s.%(ext)s" "YOUTUBE_URL"

# Download with video ID as filename (safer for special characters)
yt-dlp -x --audio-format wav -o "%(id)s.%(ext)s" "YOUTUBE_URL"

3. Choose Whisper model

English-only models (tiny.en, base.en, small.en, medium.en) are faster for English content.

4. Run transcription

CLI approach:

# Basic transcription (auto-detect language)
whisper audio.wav --model medium

# Specify language for better accuracy
whisper audio.wav --model medium --language en

# Output specific format
whisper audio.wav --model medium --output_format srt

# All formats at once
whisper audio.wav --model medium --output_format all

# Specify output directory
whisper audio.wav --model medium --output_dir ./transcripts

Python approach:

import whisper

# Load model (downloads on first run)
model = whisper.load_model("medium")

# Transcribe
result = model.transcribe("audio.wav", language="en")

# Get plain text
print(result["text"])

# Get segments with timestamps
for segment in result["segments"]:
    print(f"[{segment['start']:.2f} - {segment['end']:.2f}] {segment['text']}")

5. One-liner pipeline

Combine download and transcription:

# Download and transcribe in one command
yt-dlp -x --audio-format wav -o "audio.wav" "YOUTUBE_URL" && whisper audio.wav --model medium --output_format all

6. Alternative: yt-whisper tool

For simpler workflow, use the dedicated yt-whisper package:

# Install
pip install git+https://github.com/m1guelpf/yt-whisper.git

# Transcribe directly from URL
yt_whisper "https://www.youtube.com/watch?v=VIDEO_ID"

# With options
yt_whisper "YOUTUBE_URL" --model medium --language en --output_format srt

Output Formats

Examples

Guidelines

• Use --language flag when you know the spoken language for significantly better accuracy
• For long videos (>1 hour), use small or medium model to balance speed and accuracy
• English-only models (.en suffix) are faster and more accurate for English content
• GPU with CUDA dramatically speeds up transcription; CPU works but is 5-10x slower
• If transcription fails, ensure ffmpeg is properly installed and in PATH
• For videos with background music, larger models (medium/large) handle it better
• Clean up audio files after transcription to save disk space
• Use --output_format all to get every format at once, then choose what you need