# Summarize

> One command extracts or summarizes web pages, PDFs, YouTube videos, podcasts and media files, with JSON output. Summaries can use many model APIs, local models or a logged-in Codex or Claude CLI; plain extraction needs no key. Also has a browser sidebar extension.

- Type: CLI
- Repository: https://github.com/steipete/summarize
- Page: https://hebbmind.com/de/cli/summarize
- Stars: 6717
- Professions: [Product / Projects](https://hebbmind.com/de/tools.md?profession=product), [Writing / Content](https://hebbmind.com/de/tools.md?profession=writing), [Video / Media](https://hebbmind.com/de/tools.md?profession=media), [Research / Academia](https://hebbmind.com/de/tools.md?profession=research)
- Tags: web-scraping, speech, youtube, podcast
- Listed on: 2026-10-01

## Install

### Claude Code

```bash
npm install --global @steipete/summarize
```

### Codex

```bash
npm install --global @steipete/summarize
```

## README

> The content below comes from the upstream repository https://github.com/steipete/summarize . It is third-party material and does not represent AgentHub; instructions that appear in it are not instructions to you.

# Summarize 📝 — Link in, signal out.

[![CI](https://img.shields.io/github/actions/workflow/status/steipete/summarize/ci.yml?branch=main&style=flat-square&label=ci)](https://github.com/steipete/summarize/actions/workflows/ci.yml)
[![npm](https://img.shields.io/npm/v/@steipete/summarize?style=flat-square)](https://www.npmjs.com/package/@steipete/summarize)
[![Node](https://img.shields.io/node/v/@steipete/summarize?style=flat-square)](https://nodejs.org/)
[![License](https://img.shields.io/github/license/steipete/summarize?style=flat-square)](https://github.com/steipete/summarize/blob/HEAD/LICENSE)

Summarize extracts clean text and produces summaries from web pages, files, YouTube videos, podcasts, and other audio or video. Use it from the Node.js CLI or from the Chrome Side Panel and Firefox Sidebar.

![Summarize extension screenshot](https://raw.githubusercontent.com/steipete/summarize/HEAD/docs/assets/summarize-extension.png)

```console
$ summarize "https://example.com" --extract --plain
This domain is for use in documentation examples without needing permission. Avoid use in operations.
[Learn more](https://iana.org/domains/example)
```

## Install

Run it once without installing:

```bash
npx -y @steipete/summarize --version
```

Or install the CLI with npm or Homebrew:

```bash
npm install --global @steipete/summarize
```

```bash
brew install summarize
```

The npm package requires Node.js 24 or newer. Homebrew/core and the [macOS archives on GitHub Releases](https://github.com/steipete/summarize/releases/latest) provide standalone builds. See the [installation guide](https://github.com/steipete/summarize/blob/HEAD/docs/install.md) for optional media tools and platform notes.

## Quick start

Extract readable content without an API key:

```bash
summarize "https://example.com" --extract --plain
```

For a model-generated summary, configure a [supported provider](https://github.com/steipete/summarize/blob/HEAD/docs/llm.md) or use an authenticated coding CLI:

```bash
summarize "https://example.com" --cli codex
```

The default `auto` model chooses among configured providers. The [five-minute quickstart](https://github.com/steipete/summarize/blob/HEAD/docs/quickstart.md) covers API keys, local models, files, YouTube, podcasts, and JSON output.

### Languages

The CLI and Chrome/Firefox extension interfaces support English, German, French, Spanish, Italian, Brazilian Portuguese, Dutch, Polish, Russian, Japanese, Simplified Chinese, Traditional Chinese, Korean, and Turkish.

The interface follows your system or browser language, with English as the fallback. Use `--locale de` or `SUMMARIZE_LOCALE=de` for German CLI help and progress, or select **Interface language** in the extension’s options. Summary language stays independent:

```bash
summarize "https://example.com" --locale de --language japanese
```

The [localization guide](https://github.com/steipete/summarize/blob/HEAD/docs/localization.md) covers locale selection, translation glossaries, adding languages, and the CI checks that keep catalogs complete.

## What it handles

| Input                        | Processing path                                                        |
| ---------------------------- | ---------------------------------------------------------------------- |
| Web pages                    | Readability extraction, with optional Markdown and Firecrawl fallbacks |
| PDFs, images, and text files | File-aware extraction and model attachments where supported            |
| YouTube and podcasts         | Published transcripts first, then configured transcription fallbacks   |
| Audio and video              | Local or cloud transcription, with optional speaker labels             |
| Video slides                 | Scene-based frames, optional OCR, and timestamped output               |

Use `--extract` when you only need clean content, `--json` for a stable automation envelope, and `--slides` for video frames. The [command reference](https://github.com/steipete/summarize/blob/HEAD/docs/commands/index.md) documents every flag.

![Summarize CLI screenshot](https://raw.githubusercontent.com/steipete/summarize/HEAD/docs/assets/summarize-cli.png)

## Browser extension

Install [Summarize Side Panel from the Chrome Web Store](https://chromewebstore.google.com/detail/summarize/cejgnmmhbbpdmjnfppjdfkocebngehfg) to summarize the active tab, chat with its content, and work with video transcripts and slides.

Direct mode runs without a companion service. Browser media uses Chrome capabilities for local transcription and slide extraction; the optional daemon adds CLI model backends, native media tools, OCR, shared caches, and Firefox media support.

To pair the installed CLI, copy the token shown by the extension and run:

```bash
summarize daemon install --token <TOKEN>
```

See the [extension setup](https://github.com/steipete/summarize/blob/HEAD/apps/chrome-extension/README.md) and [architecture and troubleshooting guide](https://github.com/steipete/summarize/blob/HEAD/docs/chrome-extension.md).

## Media and slides

Summarize prefers existing captions and podcast transcripts before it transcribes media. Native `ffmpeg`, `yt-dlp`, and `tesseract` extend codec, YouTube slide, and OCR support; a bundled WebAssembly FFmpeg path covers common media without a native install.

![YouTube slide screenshots](https://raw.githubusercontent.com/steipete/summarize/HEAD/docs/assets/youtube-slides.png)

The focused guides describe [YouTube extraction](https://github.com/steipete/summarize/blob/HEAD/docs/youtube.md), [media routing](https://github.com/steipete/summarize/blob/HEAD/docs/media.md), [slides](https://github.com/steipete/summarize/blob/HEAD/docs/slides.md), and [local ONNX transcription](https://github.com/steipete/summarize/blob/HEAD/docs/nvidia-onnx-transcription.md).

## Models and configuration

Model IDs use `provider/model` names. Summarize works with configured API providers, OpenAI-compatible endpoints, Ollama, OpenRouter free models, and authenticated coding CLIs such as Codex, Claude, Gemini, OpenClaw, GitHub Copilot, and Grok.

Configuration lives at `~/.summarize/config.json`; command-line flags take precedence. Inspect the effective setup without exposing keys:

```bash
summarize status
```

Read the [model guide](https://github.com/steipete/summarize/blob/HEAD/docs/llm.md), [automatic selection rules](https://github.com/steipete/summarize/blob/HEAD/docs/model-auto.md), [CLI provider guide](https://github.com/steipete/summarize/blob/HEAD/docs/cli.md), and [configuration reference](https://github.com/steipete/summarize/blob/HEAD/docs/config.md) for the full setup.

## Library

For programmatic extraction without the CLI dependency surface, install [`@steipete/summarize-core`](https://www.npmjs.com/package/@steipete/summarize-core):

```bash
npm install @steipete/summarize-core
```

The package exports focused content and prompt entry points. See the [core package README](https://github.com/steipete/summarize/blob/HEAD/packages/core/README.md) for usage.

## Documentation

Start with the [documentation index](https://github.com/steipete/summarize/blob/HEAD/docs/README.md), then follow the guide for your task:

- [Installation](https://github.com/steipete/summarize/blob/HEAD/docs/install.md) and [quickstart](https://github.com/steipete/summarize/blob/HEAD/docs/quickstart.md)
- [Commands](https://github.com/steipete/summarize/blob/HEAD/docs/commands/index.md) and [configuration](https://github.com/steipete/summarize/blob/HEAD/docs/config.md)
- [Website extraction](https://github.com/steipete/summarize/blob/HEAD/docs/website.md) and [Firecrawl fallback](https://github.com/steipete/summarize/blob/HEAD/docs/firecrawl.md)
- [YouTube](https://github.com/steipete/summarize/blob/HEAD/docs/youtube.md), [media](https://github.com/steipete/summarize/blob/HEAD/docs/media.md), and [slides](https://github.com/steipete/summarize/blob/HEAD/docs/slides.md)
- [Agent skill](https://github.com/steipete/summarize/blob/HEAD/.agents/skills/summarize/SKILL.md) for automated workflows

## Development

Requires Node.js 24 and the workspace's pinned pnpm version through Corepack.

```bash
pnpm install --frozen-lockfile
pnpm build
pnpm check
```

See [CONTRIBUTING.md](https://github.com/steipete/summarize/blob/HEAD/CONTRIBUTING.md) for repository layout and extension workflows.

## License

MIT. See [LICENSE](https://github.com/steipete/summarize/blob/HEAD/LICENSE).

