Download YouTube video transcripts with automatic frame extraction for visual references. Use when analyzing YouTube videos, tutorials, or conference talks.
Download and analyze YouTube video transcripts with automatic frame extraction at visual reference points.
/youtube-transcript <youtube-url>
brew install yt-dlp ffmpeg
sudo apt install ffmpeg
pip install yt-dlp
sudo pacman -S yt-dlp ffmpeg
When the user invokes /youtube-transcript <url>:
command -v yt-dlp >/dev/null 2>&1 || echo "MISSING: yt-dlp"
command -v ffmpeg >/dev/null 2>&1 || echo "MISSING: ffmpeg"
If missing, show installation instructions for the user's platform.
Use the scratchpad directory for output:
# Extract video ID from YouTube URL (POSIX-compatible, works on macOS and Linux)
# Handles: youtube.com/watch?v=ID, youtu.be/ID, youtube.com/embed/ID
URL="<url>"
VIDEO_ID=$(echo "$URL" | sed -E 's/.*[?&]v=([^&]+).*/\1/;s|.*/embed/([^?/]+).*|\1|;s|.*youtu\.be/([^?/]+).*|\1|')
OUTPUT_DIR="<scratchpad>/youtube-${VIDEO_ID}"
mkdir -p "${OUTPUT_DIR}/frames"
cd "${OUTPUT_DIR}"
# Try auto-generated subtitles first, fall back to manual
yt-dlp --write-auto-sub --sub-lang en,de --skip-download --convert-subs srt -o "transcript" "<url>" 2>/dev/null || \
yt-dlp --write-sub --sub-lang en,de --skip-download --convert-subs srt -o "transcript" "<url>"
Read the transcript and identify timestamps where visual content is referenced. Look for patterns:
German:
English:
Only if visual references were found:
# First, list available formats to find a working one
yt-dlp -F "<url>"
# Then download using a specific format ID (prefer combined formats like 18 for 360p)
# Format 18 is usually 360p mp4 with video+audio combined - most reliable
yt-dlp -f 18 -o "${OUTPUT_DIR}/video.mp4" "<url>"
# If format 18 not available, try other combined formats (22=720p, 18=360p)
# Or use: yt-dlp -f "best[height<=480]" -o "${OUTPUT_DIR}/video.mp4" "<url>"
# Extract frame at timestamp (example: 01:23)
ffmpeg -ss 00:01:23 -i "${OUTPUT_DIR}/video.mp4" -frames:v 1 -q:v 2 "${OUTPUT_DIR}/frames/01_23.jpg"
Important: Avoid -f worst or complex format selectors - they often hang due to yt-dlp JS runtime issues. Use explicit format IDs instead.
Extract frames for each detected visual reference timestamp.
Create a summary with:
Example output format:
## Video: [Title]
**Channel:** [Channel Name]
**Duration:** [Duration]
---
## Transcript
[00:00] Introduction to the topic...
[01:23] As you can see in this diagram...
[02:45] Let's move on to the next point...
---
## Extracted Frames
| Timestamp | Context | Frame |
|-----------|---------|-------|
| 01:23 | "this diagram shows..." | frames/01_23.jpg |
---
Ready to answer questions about this video.
The output directory in scratchpad will be automatically cleaned up. If the user wants to keep the files, they should copy them to their project.
No transcript found:
--sub-lang en,de,es,frVideo download stuck at 0%:
yt-dlp -F <url>), then use explicit format ID (yt-dlp -f 18 <url>)JS Runtime Warning:
brew install deno or curl -fsSL https://deno.land/install.sh | shConnection timeouts:
pkill -f "yt-dlp.*VIDEO_ID"yt-dlp errors:
pip install -U yt-dlp or brew upgrade yt-dlpffmpeg errors:
Edit PDFs with natural-language instructions using the nano-pdf CLI.
Control Sonos speakers (discover/status/play/volume/group).
Terminal Spotify playback/search via spogo (preferred) or spotify_player.
Capture frames or clips from RTSP/ONVIF cameras.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Monitor blogs and RSS/Atom feeds for updates using the blogwatcher CLI.
Category:tools