Free, open-source macOS dictation app that transcribes speech and pastes cleaned-up text into any text field, an alternative to Wispr Flow.
Beingpax/VoiceInk
Native macOS app that transcribes speech to text almost instantly, with local AI models and offline processing.
Open-source alternative to:Superwhisper
Wispr Flow
- Stars
- 7,045
- Forks
- 1,002
- Open issues
- 154
- Last commit
- 19 hours ago
What is it?
VoiceInk is a voice-to-text app for macOS that turns spoken words into text almost instantly. Transcription runs on local AI models, so audio is processed on the device without being sent to a server.
The app supports global keyboard or mouse shortcuts for starting a recording and push-to-talk use. Its personal dictionary lets users add custom words, industry terms and text replacements, and mode switching applies different settings depending on the app or URL in use. It also includes a built-in voice assistant mode.
VoiceInk requires macOS 15.0 or later and can be installed with Homebrew. The project is open source under GPL v3, but the author sells a licensed build that adds automatic updates and priority support, and the project is not currently accepting pull requests.
Key features
- 01Local AI transcription that runs offline on the device
- 02Global keyboard or mouse shortcuts with push-to-talk
- 03Personal dictionary with custom terms and text replacements
- 04Per-app and per-URL modes that apply different settings automatically
- 05Built-in voice assistant mode
Use cases
- Dictating emails, documents or chat messages on a Mac
- Writing notes hands-free while working in other apps
- Transcribing speech with domain-specific terminology
Quick start
- 1
Install via Homebrew
brew install --cask voiceink
Things to know
- macOS 15.0 or later only.
- Source code is not accepting pull requests.
- Compiled version requires a paid license for automatic updates and priority support; the free trial is available on the website.
- Licensed under GPL v3, a copyleft license.
In collections
Topics
FAQ
- What is VoiceInk?
- Native macOS app that transcribes speech to text almost instantly, with local AI models and offline processing. VoiceInk is a voice-to-text app for macOS that turns spoken words into text almost instantly. Transcription runs on local AI models, so audio is processed on the device without being sent to a server.
- Is VoiceInk free to use? What license does it have?
- VoiceInk is open source under the Other license. Check the license terms before using it in commercial products.
- Is VoiceInk still maintained?
- Actively maintained. The last commit to VoiceInk was on Nov 7, 2026.
- What can I use VoiceInk for?
- Dictating emails, documents or chat messages on a Mac Writing notes hands-free while working in other apps Transcribing speech with domain-specific terminology
- How do I install VoiceInk?
- Install via Homebrew: brew install --cask voiceink
- Where can I get VoiceInk?
- The source code and installation instructions are on GitHub: https://github.com/Beingpax/VoiceInk
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A macOS menu bar dictation app: hold fn, speak, and polished text is typed at your cursor using Gemini transcription.
Native macOS speech-to-text app that transcribes dictation on-device or via cloud APIs, then reprocesses text with reusable AI workflows.
Open-source voice dictation app for Mac: hold Fn, speak, and cleaned-up text is typed wherever your cursor is.
Local-first AI subtitle generator that runs offline and plugs into DaVinci Resolve, Premiere Pro and After Effects.
Open-source, local-first AI dictation app that turns speech into text on macOS and Windows, working offline with Whisper.