# Beingpax/VoiceInk

The best open-source alternative to Superwhisper & Wispr Flow. Voice-to-text app for macOS with no subscription

Repository: https://github.com/Beingpax/VoiceInk
Canonical: https://ross.abutalabs.com/products/voiceink
Homepage: https://tryvoiceink.com
Language: Swift
License: NOASSERTION
License Family: other
Topics: macos, macos-app, swift
Last push: 2026-08-26T18:40:33+00:00

## Health v2 (maintenance only)
Score: 84/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 85, longevity 48
- inputs: {"age_days": 682, "days_push": 7, "days_rel": 21, "gap_med": 3.0, "n_releases_24m": 125}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6115, forks 878 (observed 2026-08-28T04:09:36.001989+00:00)

## What it is
VoiceInk is a native macOS voice-to-text dictation app that transcribes speech to text almost instantly using local AI models (Parakeet, WhisperKit), with optional cloud providers and AI enhancement. It is open source with a one-time license purchase, positioning itself as a privacy-focused, no-subscription alternative to Superwhisper and Wispr Flow.

## Use cases
- dictate text anywhere on macOS instead of typing
- transcribe voice to text offline with full privacy
- write emails and messages by speaking
- voice-dictate prompts into AI coding tools
- clean up filler words and format spoken notes with AI
- push-to-talk voice input via global keyboard shortcuts
- custom vocabulary for names and technical terms

## When to choose
- you want a subscription-free Wispr Flow or Superwhisper alternative
- you need fully offline, on-device transcription for privacy
- you're on Apple Silicon and want fast local dictation with Parakeet or Whisper
- you want per-app modes, context awareness, and a personal dictionary

## When to avoid
- you're on an Intel Mac or Windows/Linux - it requires Apple Silicon macOS 14.4+
- you need a fully free tool without any license purchase for updates
- you need server-side or headless batch transcription rather than interactive dictation

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, nlp, llm-inference
- domain: speech-processing, developer-tools, artificial-intelligence, apple-ecosystem
- platform: -
- tags: voice-to-text, dictation, whisper, parakeet, offline-transcription, privacy-first, push-to-talk, open-source-alternative, macos, desktop, swift

## Member repositories
- Beingpax/VoiceInk (main) score 84

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:36.001989+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 2026-08-29T17:48:10.287483+00:00, confidence not recorded.
  - readme: https://github.com/Beingpax/VoiceInk (fetched 2026-08-28T04:09:36.001989+00:00, sha 81c49a873b4d)
  - homepage: https://tryvoiceink.com (fetched 2026-08-29T08:44:44.385368+00:00, sha 8047a4e435a5)
  - site_page: https://tryvoiceink.com/features (fetched 2026-08-29T08:44:44.394884+00:00, sha c34c811ba9ea)
  - site_page: https://tryvoiceink.com/docs (fetched 2026-08-29T08:44:44.398812+00:00, sha 96f2a3604642)
  - site_page: https://tryvoiceink.com/docs/introduction (fetched 2026-08-29T08:44:44.400438+00:00, sha 0290f4597cb6)
  - site_page: https://tryvoiceink.com/docs/modes (fetched 2026-08-29T08:44:44.402037+00:00, sha c0258e5a55b3)
  - site_page: https://tryvoiceink.com/docs/recommended-models (fetched 2026-08-29T08:44:44.403662+00:00, sha d75a6a33d614)
  - site_page: https://tryvoiceink.com/docs/common-issues (fetched 2026-08-29T08:44:44.406859+00:00, sha 16482d88e425)
  - site_page: https://tryvoiceink.com/pricing (fetched 2026-08-29T08:44:44.396926+00:00, sha 71c350d090fa)
  - site_page: https://tryvoiceink.com/faq (fetched 2026-08-29T08:44:44.405302+00:00, sha 7ee4134af13a)
- Data as of 2026-08-30T08:39:29.467469+00:00.