Skip to content
/ tldr Public

Summarize articles, papers, and videos into readable text and natural audio — a CLI built for neurodivergent workflows.

License

Notifications You must be signed in to change notification settings

asanmateu/tldr

Repository files navigation

tl;dr

Summarize anything. Understand everything.

Summarize articles, papers, and videos into readable text and natural audio — a CLI built for neurodivergent workflows.

CI Docs MIT License Powered by AI

tldr demo — summarize a URL in seconds

Why this exists

I had a pile of to-reads growing at work and it was overwhelming — not because the material was hard, but because it was all in the wrong format. That goes double if you're neurodivergent, reading in a second language, or just short on time.


Audio

Summaries are rewritten as natural spoken scripts and played back using configurable voices and personas. The result sounds like a real briefing or podcast, not a screen reader. Free with Edge TTS by default, or upgrade to OpenAI TTS for higher quality. See the Audio guide for modes, voices, and presets.


Installation

brew install asanmateu/tldr/tldr-cli

Works out of the box with Claude Code, or bring your own API key (Anthropic, OpenAI, Gemini, xAI, Ollama, Codex, etc.) — see Providers. For standalone binaries, building from source, and other install methods, see the Installation guide.


Usage

tldr "https://arstechnica.com/some-article/"     # Web article
tldr ./paper.pdf                                  # Local PDF
tldr "https://example.com/doc.pdf"                # Remote PDF
tldr "Your text to summarize here..."             # Raw text
tldr                                              # Interactive mode
tldr --batch "https://..."                        # Headless — print summary to stdout
tldr --batch url1 url2 url3                       # Process multiple URLs sequentially
tldr --batch --browse url1 url2                   # Batch then browse results interactively
tldr --batch --audio "https://..."                # Headless with audio generation

YouTube, Slack threads, and Notion pages also work — just paste the URL.

In interactive mode, you can drag and drop files from Finder directly into the terminal — paths from iTerm2, Terminal.app, and other emulators are automatically recognized.

After a summary, use the keyboard shortcuts shown at the bottom: save, save with audio, listen, copy, chat, re-summarize, or discard. In chat mode, press Ctrl+s to save the conversation — subsequent messages auto-save. You'll be notified in the prompt when a new version is available.

Type / in interactive mode to access commands like /history, /setup, /config, /theme, and /help.


How it works

  1. You give it something to read (a URL, file, or text)
  2. It extracts the content automatically
  3. Your AI provider generates a structured, learning-focused summary
  4. The summary is saved to ~/Documents/tldr/

Summaries use short sentences, bullet points, bold key terms, and put the most important information first. This isn't just formatting — it's designed around cognitive accessibility research to work better for all types of readers.


Configuration

tldr works out of the box with sensible defaults. If you want to customise it:

tldr config                          # Open the config editor
tldr --style quick "https://..."     # Quick summary instead of study notes
tldr --model sonnet "https://..."    # Use a different model

Choose from three color themes (coral, ocean, forest) and auto dark/light mode during setup, or change later with tldr config set theme.

Use built-in presets (morning-brief, deep-study, bedtime-read, etc.) or create your own for different contexts with different tones, styles, audio modes, and cognitive trait settings.

See the Configuration guide for details.


Accessibility

Cognitive accessibility is the point, not a feature. Every summary is optimised for readability by default.

Trait What it does
Dyslexia (on by default) Shorter sentences, simpler vocabulary, bold key terms
ADHD No filler, action-oriented, most important info first
Autism Literal language, explicit structure, no idioms
ESL Common words only, jargon defined inline
Visual thinker Hierarchical layout, grouped ideas, numbered steps

Traits stack. Enable multiple with tldr preset edit.


Documentation

  • Installation — Homebrew, standalone binaries, prerequisites
  • Configuration — settings, presets, tones, summary styles, audio modes
  • Providers — Claude Code, Anthropic API, Gemini, xAI, Ollama, Codex, and OpenAI-compatible setup
  • Audio — audio modes, listening to summaries, voices, save with audio
  • Use Cases — workflows from quick triage to automated daily digests

Development

Requires Bun (v1.0+).

git clone https://github.com/asanmateu/tldr.git
cd tldr
bun install
bun run dev              # Run in development
bun run test             # Run tests
bun run typecheck        # Type check
bun run check            # Lint + format check
bun link                 # Make available as `tldr` command

See CONTRIBUTING.md for architecture and project structure.

License

MIT

About

Summarize articles, papers, and videos into readable text and natural audio — a CLI built for neurodivergent workflows.

Topics

Resources

License

Contributing

Security policy

Stars

Watchers

Forks

Contributors 2

  •  
  •