brew tap steipete/tap
brew install summarize

summarize --version
summarize --extract "https://www.youtube.com/watch?v=VIDEO_ID" --plain
summarize --extract "/path/to/document.pdf" --plain

Need content from the web?
  |
  +-- Static web page (article, docs, blog)?
  |     --> WebFetch (built-in, zero deps, faster)
  |     --> Jina r.jina.ai (zero install alternative)
  |     --> summarize ONLY if above tools fail or return garbage
  |
  +-- JS-heavy SPA / dynamic content?
  |     --> Crawl4AI crwl (full browser rendering)
  |     --> summarize will NOT help here (no JS rendering)
  |
  +-- Anti-bot / paywalled / Cloudflare-protected?
  |     --> summarize --firecrawl always (requires FIRECRAWL_API_KEY)
  |     --> browser-based workflow as fallback
  |
  +-- YouTube video?
  |     --> summarize --extract (ONLY option for transcript)
  |     --> Add --youtube web for captions-only (faster)
  |     --> Add --slides for visual slide extraction
  |
  +-- Podcast / RSS feed?
  |     --> summarize --extract (ONLY option)
  |     --> Supports Apple Podcasts, Spotify, RSS feeds, Podbean, etc.
  |
  +-- PDF (URL or local file)?
  |     --> summarize --extract (ONLY CLI option)
  |     --> Requires: uvx/markitdown (brew install uv)
  |
  +-- Image (OCR)?
  |     --> summarize --extract (ONLY CLI option)
  |     --> Requires: tesseract
  |
  +-- Audio / video file?
        --> summarize --extract (ONLY CLI option)
        --> Requires: whisper-cli (local) or OPENAI_API_KEY (cloud)

# Web page extraction (plain text, default)
summarize --extract "https://example.com" --plain

# Web page extraction (markdown format)
summarize --extract "https://example.com" --format md --plain

# YouTube transcript
summarize --extract "https://www.youtube.com/watch?v=VIDEO_ID" --plain

# YouTube transcript with timestamps
summarize --extract "https://www.youtube.com/watch?v=VIDEO_ID" --timestamps --plain

# YouTube transcript formatted as markdown (requires LLM -- uses API key)
summarize --extract "https://www.youtube.com/watch?v=VIDEO_ID" --format md --markdown-mode llm --plain

# YouTube slides + transcript
summarize --extract "https://www.youtube.com/watch?v=VIDEO_ID" --slides --plain

# Podcast (RSS feed)
summarize --extract "https://feeds.example.com/podcast.xml" --plain

# Apple Podcasts episode
summarize --extract "https://podcasts.apple.com/us/podcast/EPISODE_ID" --plain

# PDF from URL
summarize --extract "https://example.com/document.pdf" --plain

# PDF from local file
summarize --extract "/path/to/document.pdf" --plain

# Image OCR
summarize --extract "/path/to/image.png" --plain

# Audio transcription
summarize --extract "/path/to/audio.mp3" --plain

# Video transcription
summarize --extract "/path/to/video.mp4" --plain

# Stdin (pipe content)
pbpaste | summarize --extract - --plain
cat document.pdf | summarize --extract - --plain

# Summarize a URL (requires API key for the chosen model)
summarize "https://example.com" --model anthropic/claude-sonnet-4-5 --length long

# Summarize with a custom prompt
summarize "https://example.com" --prompt "Extract key technical decisions and their rationale"

# Summarize YouTube video
summarize "https://www.youtube.com/watch?v=VIDEO_ID" --length xl

# JSON output with metrics
summarize "https://example.com" --json --model openai/gpt-5-mini

# Quick: captions only (fastest, no deps beyond summarize)
summarize --extract "https://www.youtube.com/watch?v=VIDEO_ID" --youtube web --plain

# Full: with timestamps
summarize --extract "https://www.youtube.com/watch?v=VIDEO_ID" --timestamps --plain

# Formatted as clean markdown (requires LLM API key)
summarize --extract "https://www.youtube.com/watch?v=VIDEO_ID" --format md --markdown-mode llm --plain

# From RSS feed (transcribes latest episode)
summarize --extract "https://feeds.example.com/podcast.xml" --plain

# From Apple Podcasts link
summarize --extract "https://podcasts.apple.com/us/podcast/SHOW/EPISODE" --plain

# From URL
summarize --extract "https://example.com/report.pdf" --plain

# From local file
summarize --extract "/path/to/file.pdf" --plain

# Limit output length
summarize --extract "/path/to/huge.pdf" --max-extract-characters 50000 --plain

summarize --extract "/path/to/screenshot.png" --plain
summarize --extract "/path/to/scanned-doc.jpg" --plain

# Requires FIRECRAWL_API_KEY in env or config
summarize --extract "https://paywalled-site.com/article" --firecrawl always --plain

# Extract multiple YouTube videos
for url in "URL1" "URL2" "URL3"; do
  echo "=== $url ==="
  summarize --extract "$url" --plain
done

{
  "model": "auto",
  "env": {
    "FIRECRAWL_API_KEY": "fc-..."
  },
  "ui": {
    "theme": "mono"
  }
}