
quill
Ultraminimalist macOS recording + transcription.
The Lens
By Erik Loyd, SaaS CEO and former COO/CFO of an AWS Premier Partner.
Updated Oct 2026
Quill records a call and transcribes it without anything leaving your Mac. It's a tiny menu-bar app: one click records your mic and the call audio as separate tracks, and on stop a local speech model writes a timestamped transcript. Not the Quill.js editor; same name, different project. MIT licensed and free.
There's no app to download. You clone the repo, build it with Apple's Swift toolchain, then run sudo ./scripts/install-macos. It needs macOS 15 or later, and the first transcription pulls about 600 MB of model files. Transcription is English-only and fast on Apple Silicon. Speaker labels are just "me" and "them", because your mic is one track and everything the Mac plays is the other, notification dings included. No summaries; an on_stop hook hands the folder to your own script. Solo: free, and cheaper than Otter for raw transcripts. Teams get no sharing or sync.
The catch: it records everyone on the call with no bot and no notice to them, and in all-party-consent states like California getting permission is on you. It's also a young, mostly one-developer project with no tagged releases, and nothing has merged since September 27 while outside fixes sit in open pull requests.
Free vs Self-Hosted vs Paid
fully freeFree: MIT licensed, no paid tier. Records your mic and all system audio as separate tracks and transcribes on-device with Parakeet TDT 0.6B v2 (English) through FluidAudio's Core ML port.
Self-hosted: Runs locally; there is no server and no prebuilt app. Build from source with ./scripts/build-macos (Swift Package Manager) and install with sudo ./scripts/install-macos; optional quill install --launch-at-login. Requires macOS 15+, Apple Silicon recommended. Models (about 600 MB) download once on first transcription. Windows and Linux are planned, not working.
Paid: No paid tier and no cloud service. There are no built-in summaries; if you wire the on_stop hook to a hosted model, that provider's usage pricing applies.
Free, MIT and fully local. The price is building it from source yourself and living with English-only, me-versus-them transcripts.
What to do by team size
- Solo
- free; build it from source on macOS 15+
- Small team
- free per person, but there's no sharing or sync
- Medium team
- free per person, but nothing for teams; anarlog or Granola handle shared notes
- Large team
- free per person, but no admin, consent or retention controls; not a fit
Get tools like this every Wednesday
One featured tool, three on the radar. No fluff.
Similar Tools

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

Voice-to-text dictation app with local (Nvidia Parakeet/Whisper) and cloud models (BYOK). Privacy-first and available cross-platform.

Open source Granola AI Alternative

Robust Speech Recognition via Large-Scale Weak Supervision

Transcribe on your own!

Every meeting, every idea, every voice note, searchable by your AI. Open-source, privacy-first conversation memory layer.
A low score is not a verdict on quality. Young and niche tools start low by design. How we calculate scores
Trust Signals
About
- Owner
- Digital Automata (Organization)
- Stars
- 3,939
- Forks
- 292
Explore Further
More tools in the directory
openclaw
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
392.8k ★everything-claude-code
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
286.7k ★DeepSeek Harness
DeepSeek Harness: Everything is a Plugin.
258.6k ★Featured in The Open Source Drop #20