VoiceInk
A macOS dictation app under GPL-3.0 whose README names Superwhisper and Wispr Flow as the tools it replaces, with local models, per-app modes, a personal dictionary and an AI assistant mode.
What it does
VoiceInk is a "voice to text app for macOS to transcribe what you say to text almost instantly", in its README's words. It runs the speech model on the Mac, and the README says "100% offline processing ensures your data never leaves your device". The models it credits are whisper.cpp, NVIDIA Parakeet through FluidAudio, and SenseVoice Small.
It has push-to-talk with configurable keyboard or mouse shortcuts, modes that apply settings per application or per website, a context-aware mode that reads what is on screen, an AI assistant mode the README compares to a ChatGPT-style conversation, and a personal dictionary with custom words and text replacements. Which language model runs the assistant is not stated.
What it replaces
VoiceInk replaces Superwhisper and Wispr Flow on a Mac, and says so in its own GitHub description. The modes and the dictionary are the features that make it the closest match on this site to those two products.
Where it falls short: it is macOS only, 14.4 or later. Its accuracy figure of 99 percent is the project's own claim, made in the README without a stated test. The project is not accepting pull requests.
How it runs
Download from tryvoiceink.com, install with brew install --cask voiceink, or build from source following the project's building guide. The source is GPL-3.0. The maintainers also sell a compiled build with a free trial, which the README says adds automatic updates and priority support; that is a distribution choice and does not change the licence.
Who it fits
A Mac user who wants dictation tuned per application and a cleanup pass on the output, and who is comfortable either building the app or paying for the compiled one. Windows and Linux users should look at Handy or OpenWhispr.
Limits the README states
"This project is not accepting pull requests at this time." Nothing else is listed as a known limitation.
Sources
- VoiceInk README and GPL-3.0 LICENSE: github.com/Beingpax/VoiceInk, read 2026-09-16.
More voice dictation apps
A free, offline push-to-talk dictation app for macOS, Windows and Linux that runs Whisper or NVIDIA Parakeet on your own machine and pastes the text at your cursor, under MIT.
A dictation and meeting-notes app under MIT that runs Whisper or Parakeet locally or cloud models with your own key, detects Zoom, Teams and FaceTime calls, and labels speakers on device.
A speech-to-text app inside the Epicenter monorepo under AGPL-3.0 that records, transcribes with a provider you choose, cloud or local, optionally polishes the text, and pastes it at the cursor.
Added September 16, 2026. Found an error on this page? Write to reveneau@licheo.com and it gets fixed in the next weekly pass.
Running one of these inside your own environment, with your own data and your own security rules, is the kind of work Reveneau does. Read how a forward deployed engagement works.