Summarize
Use the
CLI as the canonical interface. Prefer a released binary on
; inside this repository, use
for the current checkout.
Start
-
Confirm the command and current contract:
bash
summarize --version
summarize --help
-
Inspect model/provider readiness when a summary needs an LLM:
bash
summarize status
summarize status --json
-
Run the narrowest workflow below. Quote URLs and paths. Add
for slow remote or media inputs.
Never print, request, or copy API-key values.
reports availability without exposing secrets.
Summarize
Web page or remote document:
bash
summarize "https://example.com/article"
summarize "https://example.com/report.pdf" --length short
Local file or stdin:
bash
summarize "./report.pdf"
summarize "./recording.m4a"
printf '%s\n' "Long text to summarize" | summarize -
Use
for unrendered Markdown/text. Use
,
,
, or
only when the task requires an override. Use
,
, or another installed CLI provider when the user requests that provider or no direct API provider is configured.
Extract without a summary
Use
to stop after extraction or transcription:
bash
summarize "https://example.com/article" --extract --format md
summarize "./report.pdf" --extract --format md
summarize "https://youtu.be/VIDEO_ID" --extract --format md
does not support stdin. Extraction can still call configured transcription, OCR, Firecrawl, or Markdown services; it only skips the final summary call.
also invokes an LLM to reshape extracted text.
YouTube, audio, and video
Default transcript selection:
bash
summarize "https://youtu.be/VIDEO_ID"
summarize "https://youtu.be/VIDEO_ID" --extract --format md --timestamps
Use
to require web captions or
to require the download/transcription path. Keep
unless the user needs a specific source.
Local or remote audio/video:
bash
summarize "./interview.mp3" --extract
summarize "./interview.mp4" --extract --timestamps
summarize "./interview.mp3" --extract --diarize
is the default. Use an explicit transcriber only when requested or diagnosing a provider. Diarization may require configured ElevenLabs or OpenAI access. Speaker identification is a separate opt-in step; do not infer identities without evidence.
For slides:
bash
summarize "https://youtu.be/VIDEO_ID" --slides
summarize "./talk.mp4" --slides --extract
Slide extraction may require
; OCR requires
.
JSON for automation
Use JSON when another command or agent will parse the result:
bash
summarize "https://example.com" --json --metrics off > result.json
jq -r '.summary // .extracted.content // empty' result.json
The stable top-level envelope contains
,
,
,
,
,
, and
.
or
can be
when extraction or a no-model path handles the input. In
mode, read extracted text from
.
JSON stays on stdout. Progress, warnings, and finish metrics stay on stderr. Do not merge stderr into stdout before parsing. Use
only when the task needs usage details.
Configuration and dependencies
Precedence: CLI flags, process environment,
, built-in defaults. Prefer flags for one run; change config only when the user asks for a persistent default.
Useful diagnostics:
bash
summarize status --verbose
summarize status --probe
summarize "INPUT" --verbose
Plain web summaries need no media tools. Media paths may use
,
, local Whisper/ONNX, or configured cloud transcription. Website fallback may use Firecrawl. Confirm the exact missing capability from the error before installing tools or changing config.
Inputs may be sent to the selected model, extraction, OCR, or transcription provider. For confidential material, confirm the approved provider or use an approved local path before running the command.
Verify
After every run:
- Require exit status .
- Require non-empty summary or extracted content.
- For JSON, parse stdout with or another JSON parser.
- For source-sensitive work, inspect , , and stderr diagnostics rather than assuming the selected path.
- Re-run the exact final command after changing provider, config, or flags.
For current option details, run
and read the repository documentation:
- Quickstart
- Main command
- Configuration
- YouTube
- Media
- Extraction
Ownership
This file is the canonical agent workflow for the Summarize product. Keep generic agent workflows in
; keep Summarize CLI behavior here. Downstream integrations should link to this file at a released tag or pinned commit and retain only their packaging or integration-specific notes. Do not maintain a second broad command guide downstream.