Summarize or extract text from URLs, local files, YouTube videos, and podcasts using the summarize CLI. Use when the user asks to summarize a link, article, video, or document. Supports multiple output lengths and models. Do NOT use for web search (use web-search) or for content the agent can read directly.
| Input | Command |
|---|---|
| URL/article | summarize “https://...” --model openai/gpt-4.1-mini |
| Local file | summarize “/path/to/file.pdf” |
| YouTube | summarize “https://youtu.be/...” --youtube auto |
| Extract only | summarize “URL” --extract-only |
summarize "https://example.com" --model openai/gpt-4.1-mini
summarize "/path/to/file.pdf" --model anthropic/claude-3-5-sonnet
summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto
Best-effort transcript (URLs only):
summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto --extract-only
If the user asked for a transcript but it’s huge, return a tight summary first, then ask which section/time range to expand.
Set the API key for your chosen provider:
OPENAI_API_KEYANTHROPIC_API_KEYDefault model is openai/gpt-4.1-mini if none is set.
--length short|medium|long|xl|xxl|<chars>--max-output-tokens <count>--extract-only (URLs only)--json (machine readable)--youtube autoOptional config file: ~/.summarize/config.json
{ "model": "openai/gpt-5.2" }
Optional services: