# Starmel/OpenSuperWhisper

macOS dictation app

Repository: https://github.com/Starmel/OpenSuperWhisper
Canonical: https://ross.abutalabs.com/products/opensuperwhisper
Language: Swift
License: MIT
License Family: permissive
Topics: macos, whisper, parakeet, dictation
Last push: 2026-08-10T19:05:31+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 61, longevity 40
- inputs: {"age_days": 573, "days_push": 23, "days_rel": 183, "gap_med": 62.0, "n_releases_24m": 7}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2721, forks 231 (observed 2026-08-28T04:07:12.074775+00:00)

## What it is
OpenSuperWhisper is a macOS dictation application that records audio and transcribes it locally using Whisper or Parakeet models. It supports global keyboard shortcuts, mouse button triggers, hold-to-record mode, and drag-and-drop file transcription.

## Use cases
- dictate text anywhere on macOS with a keyboard shortcut
- transcribe voice notes locally without cloud services
- convert audio files to text by dragging them into the app
- bind a mouse button to start and stop voice recording
- transcribe speech in multiple languages with auto-detection

## When to choose
- you want private, on-device speech-to-text on an Apple Silicon Mac
- you need system-wide dictation with customizable hotkeys
- you want a free open-source alternative to commercial dictation tools

## When to avoid
- you need Windows or Linux support
- you have an Intel Mac (Apple Silicon only)
- you need streaming real-time transcription

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, audio-processing, gui
- domain: speech-processing, developer-tools, apple-ecosystem
- platform: -
- tags: dictation, whisper, parakeet, voice-to-text, local-transcription, keyboard-shortcuts, natural-language-processing, macos

## Member repositories
- Starmel/OpenSuperWhisper (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:12.074775+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 2026-08-30T02:15:12.188558+00:00, confidence not recorded.
  - readme: https://github.com/Starmel/OpenSuperWhisper (fetched 2026-08-28T04:07:12.074775+00:00, sha 17dff71ba017)
- Data as of 2026-08-30T08:39:29.467469+00:00.