#3131st of 67 in VoiceFor voice, speech and music

voiceink

Native macOS dictation app using local speech-to-text models

Stars
7k
License
custom license
Last commit
Oct 2026
Last release
Sep 2026
Language
Swift
Stars, last 29 weeks+2,524
10 Apr 2026: 4,463 stars17 Apr 2026: 4,556 stars24 Apr 2026: 4,625 stars1 May 2026: 4,733 stars8 May 2026: 4,816 stars15 May 2026: 4,903 stars22 May 2026: 4,986 stars29 May 2026: 5,074 stars5 Jun 2026: 5,139 stars12 Jun 2026: 5,194 stars19 Jun 2026: 5,248 stars26 Jun 2026: 5,314 stars3 Jul 2026: 5,373 stars10 Jul 2026: 5,449 stars17 Jul 2026: 5,532 stars24 Jul 2026: 5,630 stars31 Jul 2026: 5,702 stars7 Aug 2026: 5,758 stars14 Aug 2026: 5,855 stars21 Aug 2026: 6,007 stars28 Aug 2026: 6,133 stars4 Sept 2026: 6,278 stars11 Sept 2026: 6,369 stars18 Sept 2026: 6,434 stars25 Sept 2026: 6,548 stars2 Oct 2026: 6,630 stars9 Oct 2026: 6,712 stars16 Oct 2026: 6,836 stars23 Oct 2026: 6,913 stars30 Oct 2026: 6,987 stars

4,463 on 10 Apr 20266,987 on 30 Oct 2026

From GitHub's daily star counts.

Checked on GitHub.

Overview

VoiceInk is a Swift macOS app that transcribes speech to text on-device using whisper.cpp, Parakeet via FluidAudio, and GGUF models through transcribe.cpp. It adds global push-to-talk shortcuts, a personal dictionary, and per-app modes that switch settings by the active app or URL. A built-in voice assistant mode is also included.

Who it is for: Mac users who want offline dictation into any app

Strengths

  • Offline transcription; README states audio never leaves the device
  • Supports whisper.cpp, Parakeet and GGUF local models, plus SenseVoice Small
  • Per-app modes apply settings automatically by app or URL
  • Installable via Homebrew cask or buildable from source with BUILDING.md

Weaknesses

  • macOS 15.0 or later only; no Windows or Linux builds
  • Not accepting pull requests; contributions limited to issues
  • Auto-updates and priority support only in the paid compiled build

What it needs

  • Needs macOS 15.0+
  • Models: whisper.cpp (Whisper), Parakeet (FluidAudio), GGUF via transcribe.cpp, SenseVoice Small

Quick answers

Is voiceink open source?

Its code is public on GitHub under its own license terms; read them before you use it at work.

Also in Voice

See all 67
Also in Voice
RankProjectScore
1voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks97.4k starsAGPL-3.097 out of 100
2whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription54.8k starsMIT89 out of 100
3handyOffline push-to-talk dictation app that pastes transcripts into any text field36.1k starsMIT89 out of 100
#4xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control32.4k starsMIT82 out of 100
#5buzzOffline desktop app for transcribing and translating audio with Whisper22.3k starsMIT81 out of 100