YouTube Transcript Downloader

This skill helps download transcripts (subtitles/captions) from YouTube videos using yt-dlp.

When to Use This Skill

Activate this skill when the user:

• Provides a YouTube URL and wants the transcript
• Asks to "download transcript from YouTube"
• Wants to "get captions" or "get subtitles" from a video
• Asks to "transcribe a YouTube video"
• Needs text content from a YouTube video

How It Works

Priority Order:

1. Check if yt-dlp is installed - install if needed
2. List available subtitles - see what's actually available
3. Try manual subtitles first (--write-sub) - highest quality
4. Fallback to auto-generated (--write-auto-sub) - usually available
5. Last resort: Whisper transcription - if no subtitles exist (requires user confirmation)
6. Confirm the download and show the user where the file is saved
7. Optionally clean up the VTT format if the user wants plain text

Installation Check

IMPORTANT: Always check if yt-dlp is installed first:

which yt-dlp || command -v yt-dlp

If Not Installed

Attempt automatic installation based on the system:

macOS (Homebrew):

brew install yt-dlp

Linux (apt/Debian/Ubuntu):

sudo apt update && sudo apt install -y yt-dlp

Alternative (pip - works on all systems):

pip3 install yt-dlp
# or
python3 -m pip install yt-dlp

If installation fails: Inform the user they need to install yt-dlp manually and provide them with installation instructions from https://github.com/yt-dlp/yt-dlp#installation

Check Available Subtitles

ALWAYS do this first before attempting to download:

yt-dlp --list-subs "YOUTUBE_URL"

This shows what subtitle types are available without downloading anything. Look for:

• Manual subtitles (better quality)
• Auto-generated subtitles (usually available)
• Available languages

Download Strategy

Option 1: Manual Subtitles (Preferred)

Try this first - highest quality, human-created:

yt-dlp --write-sub --skip-download --output "OUTPUT_NAME" "YOUTUBE_URL"

Option 2: Auto-Generated Subtitles (Fallback)

If manual subtitles aren't available:

yt-dlp --write-auto-sub --skip-download --output "OUTPUT_NAME" "YOUTUBE_URL"

Both commands create a .vtt file (WebVTT subtitle format).

Option 3: Whisper Transcription (Last Resort)

ONLY use this if both manual and auto-generated subtitles are unavailable.

Step 1: Show File Size and Ask for Confirmation

# Get audio file size estimate
yt-dlp --print "%(filesize,filesize_approx)s" -f "bestaudio" "YOUTUBE_URL"

# Or get duration to estimate
yt-dlp --print "%(duration)s %(title)s" "YOUTUBE_URL"

IMPORTANT: Display the file size to the user and ask: "No subtitles are available. I can download the audio (approximately X MB) and transcribe it using Whisper. Would you like to proceed?"

Wait for user confirmation before continuing.

Step 2: Check for Whisper Installation

command -v whisper

If not installed, ask user: "Whisper is not installed. Install it with pip install openai-whisper (requires ~1-3GB for models)? This is a one-time installation."

Wait for user confirmation before installing.

Install if approved:

pip3 install openai-whisper

Step 3: Download Audio Only

yt-dlp -x --audio-format mp3 --output "audio_%(id)s.%(ext)s" "YOUTUBE_URL"

Step 4: Transcribe with Whisper

# Auto-detect language (recommended)
whisper audio_VIDEO_ID.mp3 --model base --output_format vtt

# Or specify language if known
whisper audio_VIDEO_ID.mp3 --model base --language en --output_format vtt

Model Options (stick to base for now):

• tiny - fastest, least accurate (~1GB)
• base - good balance (~1GB) ← USE THIS
• small - better accuracy (~2GB)
• medium - very good (~5GB)
• large - best accuracy (~10GB)

Step 5: Cleanup

After transcription completes, ask user: "Transcription complete! Would you like me to delete the audio file to save space?"

If yes:

rm audio_VIDEO_ID.mp3

Getting Video Information

Extract Video Title (for filename)

yt-dlp --print "%(title)s" "YOUTUBE_URL"

Use this to create meaningful filenames based on the video title. Clean the title for filesystem compatibility:

• Replace / with -
• Replace special characters that might cause issues
• Consider using sanitized version: $(yt-dlp --print "%(title)s" "URL" | tr '/' '-' | tr ':' '-')

Post-Processing

Convert to Plain Text (Recommended)

YouTube's auto-generated VTT files contain duplicate lines because captions are shown progressively with overlapping timestamps. Always deduplicate when converting to plain text while preserving the original speaking order.

python3 -c "
import sys, re
seen = set()
with open('transcript.en.vtt', 'r') as f:
    for line in f:
        line = line.strip()
        if line and not line.startswith('WEBVTT') and not line.startswith('Kind:') and not line.startswith('Language:') and '-->' not in line:
            clean = re.sub('<[^>]*>', '', line)
            clean = clean.replace('&amp;', '&').replace('&gt;', '>').replace('&lt;', '<')
            if clean and clean not in seen:
                print(clean)
                seen.add(clean)
" > transcript.txt

Complete Post-Processing with Video Title

# Get video title
VIDEO_TITLE=$(yt-dlp --print "%(title)s" "YOUTUBE_URL" | tr '/' '_' | tr ':' '-' | tr '?' '' | tr '"' '')

# Find the VTT file
VTT_FILE=$(ls *.vtt | head -n 1)

# Convert with deduplication
python3 -c "
import sys, re
seen = set()
with open('$VTT_FILE', 'r') as f:
    for line in f:
        line = line.strip()
        if line and not line.startswith('WEBVTT') and not line.startswith('Kind:') and not line.startswith('Language:') and '-->' not in line:
            clean = re.sub('<[^>]*>', '', line)
            clean = clean.replace('&amp;', '&').replace('&gt;', '>').replace('&lt;', '<')
            if clean and clean not in seen:
                print(clean)
                seen.add(clean)
" > "${VIDEO_TITLE}.txt"

echo "✓ Saved to: ${VIDEO_TITLE}.txt"

# Clean up VTT file
rm "$VTT_FILE"
echo "✓ Cleaned up temporary VTT file"

Output Formats

• VTT format (.vtt): Includes timestamps and formatting, good for video players
• Plain text (.txt): Just the text content, good for reading or analysis

Tips

• The filename will be {output_name}.{language_code}.vtt (e.g., transcript.en.vtt)
• Most YouTube videos have auto-generated English subtitles
• Some videos may have multiple language options
• If auto-subtitles aren't available, try --write-sub instead for manual subtitles

Complete Workflow Example

VIDEO_URL="https://www.youtube.com/watch?v=dQw4w9WgXcQ"

# Get video title for filename
VIDEO_TITLE=$(yt-dlp --print "%(title)s" "$VIDEO_URL" | tr '/' '_' | tr ':' '-' | tr '?' '' | tr '"' '')
OUTPUT_NAME="transcript_temp"

# ============================================
# STEP 1: Check if yt-dlp is installed
# ============================================
if ! command -v yt-dlp &> /dev/null; then
    echo "yt-dlp not found, attempting to install..."
    if command -v brew &> /dev/null; then
        brew install yt-dlp
    elif command -v apt &> /dev/null; then
        sudo apt update && sudo apt install -y yt-dlp
    else
        pip3 install yt-dlp
    fi
fi

# ============================================
# STEP 2: List available subtitles
# ============================================
echo "Checking available subtitles..."
yt-dlp --list-subs "$VIDEO_URL"

# ============================================
# STEP 3: Try manual subtitles first
# ============================================
echo "Attempting to download manual subtitles..."
if yt-dlp --write-sub --skip-download --output "$OUTPUT_NAME" "$VIDEO_URL" 2>/dev/null; then
    echo "✓ Manual subtitles downloaded successfully!"
    ls -lh ${OUTPUT_NAME}.*
else
    # ============================================
    # STEP 4: Fallback to auto-generated
    # ============================================
    echo "Manual subtitles not available. Trying auto-generated..."
    if yt-dlp --write-auto-sub --skip-download --output "$OUTPUT_NAME" "$VIDEO_URL" 2>/dev/null; then
        echo "✓ Auto-generated subtitles downloaded successfully!"
        ls -lh ${OUTPUT_NAME}.*
    else
        # ============================================
        # STEP 5: Last resort - Whisper transcription
        # ============================================
        echo "⚠ No subtitles available for this video."

how to use youtube-transcript
CursorClaude CodeClineCodexWindsurfGooseGitHub CopilotVS CodeGemini CLIKiloOpencodeKimi CLIRoo ClineAiderContinueZedBolt.newLovablev0Replit AgentSweepSmol DeveloperDevinCavemanAmpAntigravity
How to use youtube-transcript on Cursor
AI-first code editor with Composer
1
Prerequisites
Before installing skills in Cursor, ensure your development environment meets these requirements:
›Cursor installed and configured on your development machine
›Node.js version 16.0+ with npm package manager (verify with node --version)
›Active project directory or workspace where you want to add youtube-transcript
2
Execute installation command
Execute the skills CLI command in your project's root directory to begin installation:
$npx skills add https://github.com/michalparkola/tapestry-skills-for-claude-code --skill youtube-transcriptcopy
The skills CLI fetches youtube-transcript from GitHub repository michalparkola/tapestry-skills-for-claude-code and configures it for Cursor.
3
Select Cursor when prompted
The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:
◆ Which agents do you want to install to?
│
│ ── Universal (.agents/skills) ── always included ────
│   • Amp
│   • Antigravity
│   • Cline
│   • Codex
│ ●Cursor(selected)
│   • Cursor
│   • Windsurf
4
Verify installation
Confirm successful installation by checking the skill directory location:
.cursor/skills/youtube-transcript
Reload or restart Cursor to activate youtube-transcript. Access the skill through slash commands (e.g., /youtube-transcript) or your agent's skill management interface.
⚠
Security & Verification Notice
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.
Additional Resources
›View source code on GitHub›Skills CLI documentation›Learn more about Cursor›What are agent skills?