# digimata/quill

Ultra-minimalist macOS recording + transcription.

Repository: https://github.com/digimata/quill
Canonical: https://ross.abutalabs.com/products/digimata-quill
Language: Swift
License: MIT
License Family: permissive
Last push: 2026-07-30T08:11:29+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 35, longevity 2
- inputs: {"age_days": 40, "days_push": 34, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3874, forks 269 (observed 2026-08-28T04:08:27.763611+00:00)

## What it is
Quill is an ultra-minimalist, fully local macOS meeting recorder and transcriber that runs as a single Swift menu-bar binary. It records microphone and system audio as separate tracks, then transcribes both on-device into a speaker-tagged transcript without any data leaving the machine.

## Use cases
- record and transcribe meetings locally on macOS
- transcribe calls with speaker separation for free
- capture both mic and system audio in one recording
- run on-device transcription without sending audio to the cloud
- get speaker-tagged meeting transcripts automatically
- record Zoom or Teams calls from the Mac side

## When to choose
- you want fully local, private meeting transcription on Apple Silicon
- you need mic and system audio as separate tracks for free two-party diarization
- you prefer a lightweight menu-bar tool over a full app bundle
- you want crash-safe recordings that survive a mid-meeting process death

## When to avoid
- you need Windows or Linux support
- you need multilingual transcription beyond English
- you want cloud-based transcription with higher accuracy models
- you need a GUI with editing and export features

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, audio-processing, cli
- domain: speech-processing, developer-tools, apple-ecosystem
- platform: cli
- tags: menu-bar-app, meeting-recorder, transcription, local-first, diarization, parakeet, core-ml, privacy, macos, swift

## Member repositories
- digimata/quill (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:27.763611+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:25:46.605415+00:00, confidence not recorded.
  - readme: https://github.com/digimata/quill (fetched 2026-08-28T04:08:27.763611+00:00, sha 5655cb005be3)
- Data as of 2026-08-30T08:39:29.467469+00:00.