VoiceInk
VoiceInk is a macOS dictation app under GPL-3.0 whose own GitHub description names Superwhisper and Wispr Flow as the tools it replaces. It runs the speech model on the Mac, with whisper.cpp, NVIDIA Parakeet and SenseVoice models, and adds per-application modes, a personal dictionary and an AI assistant mode. The maintainers sell a compiled build with automatic updates; the source builds for free.
What does VoiceInk do?
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.
Key facts
- Licence: GPL-3.0 on the code. The compiled build sold on tryvoiceink.com adds automatic updates and priority support; the README says the licence is unchanged.
- Models credited in the README: whisper.cpp, NVIDIA Parakeet through FluidAudio, transcribe.cpp GGUF models, and SenseVoice Small.
- Offline: the README says 100 percent offline processing ensures your data never leaves your device.
- Push-to-talk with configurable keyboard or mouse shortcuts.
- Modes apply pre-configured settings per application or website; a context-aware mode reads what is on screen; an AI assistant mode the README compares to a ChatGPT-style conversation.
- A personal dictionary with custom words and text replacements.
- Requires macOS 14.4 or later; install from tryvoiceink.com, with brew install --cask voiceink, or build from source per the building guide.
- The README's accuracy figure of 99 percent is the project's own claim, made without a stated test.
What does it replace, and where does it fall short?
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 does VoiceInk run?
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 is VoiceInk for?
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.
What limits does the README state?
"This project is not accepting pull requests at this time." Nothing else is listed as a known limitation.
Questions people ask
Is VoiceInk open source?
Yes. The source on GitHub is GPL-3.0, an OSI approved licence, and the README invites forking and modifying it for your own use. The maintainers also sell a compiled build with a free trial, which is a distribution choice and does not change the licence on the code.
Is VoiceInk free?
The source is free to build under GPL-3.0, and a Homebrew cask installs it. The compiled version from tryvoiceink.com is paid after a free trial and, by the README, adds automatic updates, priority support via Discord and email, and upcoming features. Which one you use is up to you.
Does VoiceInk work offline and on which Macs?
Yes, offline: the README says data never leaves the device. It requires macOS 14.4 or later. It is macOS only; there is no Windows or Linux build, which is the main reason to look at Handy or OpenWhispr instead.
How does VoiceInk compare with Superwhisper?
VoiceInk is the closest open-source match on a Mac, with the same shape: local models, per-app modes, a dictionary and an assistant. Superwhisper also ships an iPhone app and vendor support, which VoiceInk does not describe. The open-source alternatives to Superwhisper page compares the four options by need.
Does VoiceInk accept contributions?
Not at present. The README states the project is not accepting pull requests at this time. You are free to fork under the GPL-3.0, and the README says so; changes you want in the main app have to wait for the maintainers to reopen contributions.
Sources
- VoiceInk README and GPL-3.0 LICENSE: github.com/Beingpax/VoiceInk, read 2026-09-16.
Compared with the others
On the open-source alternatives to Wispr Flow page, VoiceInk is the pick for a mac, with modes per application. GPL-3.0, offline, with modes that change settings per app or site, a personal dictionary, and an AI assistant mode. Its own README names Superwhisper and Wispr Flow as the tools it replaces.
Also on that page: Handy for all three desktops, nothing else running, FluidVoice for a mac with the newest local models, SayIt for windows, with an editable cleanup step.
On the open-source alternatives to Superwhisper page, VoiceInk is the pick for a mac, with modes per application. GPL-3.0, offline, with modes that change settings per app or site, a personal dictionary, and an AI assistant mode. Its own README names Superwhisper and Wispr Flow as the tools it replaces.
Also on that page: Handy for all three desktops, nothing else running, FluidVoice for a mac with the newest local models, SayIt for windows, with an editable cleanup step.
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 GPL-3.0 macOS dictation app that runs Nemotron, Parakeet, Cohere Transcribe, Apple Speech or Whisper on the device, with command and write modes, per-app prompts, and an optional closed local enhancement model.
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.
An Apache-2.0 macOS dictation app that calls Gemini 3.5 Transcribe with your own key, writes audio to disk from the first millisecond for crash safety, and inserts polished text at your cursor without an account.
A free, open-source dictation app for macOS under Apache-2.0 that holds a shortcut, listens, and pastes the text where your cursor is, with Whisper, NVIDIA Parakeet or Apple on-device speech recognition.
Added September 16, 2026. Every claim above comes from the project's README, LICENSE or model card, read on September 16, 2026, or from the GitHub API on the date shown in the panel. Found an error? Write to reveneau@licheo.com and it is fixed in the next weekly pass. Repository: github.com/Beingpax/VoiceInk.
Want VoiceInk running on your own servers?
Reveneau sets it up on your hardware, connects it to your product, and builds the software around it.