# digimata/parrot

Ultra-minimalist macOS dictation.

Repository: https://github.com/digimata/parrot
Canonical: https://ross.abutalabs.com/products/parrot
Homepage: https://digimata.github.io/parrot/
Language: Swift
License: MIT
License Family: permissive
Last push: 2026-07-30T08:11:35+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 83, longevity 8
- inputs: {"age_days": 115, "days_push": 34, "days_rel": 115, "gap_med": 0.0, "n_releases_24m": 5}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1185, forks 111 (observed 2026-08-28T04:03:54.901934+00:00)

## What it is
Parrot is an ultra-minimalist push-to-talk dictation daemon for macOS that transcribes speech entirely on-device using WhisperKit on the Apple Neural Engine. Holding the fn key records audio, and the transcript is typed directly at the cursor within a few hundred milliseconds.

## Use cases
- dictate text anywhere on macOS with a push-to-talk key
- transcribe speech to text locally without cloud services
- insert voice-dictated text at the cursor in any app
- run a background dictation daemon that launches at login
- use whisper models on Apple Silicon for fast on-device transcription

## When to choose
- you want private, fully on-device dictation on an Apple Silicon Mac
- you prefer a minimal hold-key interface with no buttons or accounts
- you need low-latency voice-to-text inserted directly into any text field

## When to avoid
- you are on an Intel Mac or macOS 13 or earlier
- you need cloud-based transcription or multilingual support beyond what your chosen model offers
- you want a GUI-heavy dictation app with editing and formatting features

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, cli
- domain: speech-processing, developer-tools
- platform: cli
- tags: dictation, push-to-talk, whisper, on-device, voice-to-text, apple-silicon, command-line, macos

## Member repositories
- digimata/parrot (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:54.901934+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 2026-08-30T06:24:06.924919+00:00, confidence not recorded.
  - readme: https://github.com/digimata/parrot (fetched 2026-08-28T04:03:54.901934+00:00, sha b03a58453272)
  - homepage: https://digimata.github.io/parrot/ (fetched 2026-08-29T12:31:01.412389+00:00, sha df0c3b15b9b8)
- Data as of 2026-08-30T08:39:29.467469+00:00.