VoiceInk

Voice to text app for macOS to transcribe what you say to text almost instantly

[](https://www.gnu.org/licenses/gpl-3.0)  [](https://github.com/Beingpax/VoiceInk/releases)  

Website • YouTube

VoiceInk is a native macOS application that transcribes what you say to text almost instantly. You can find all the information and download the app from here.

After dedicating the past 5 months to developing this app, I've decided to open source it for the greater good.

My goal is to make it the most efficient and privacy-focused voice-to-text solution for macOS that is a joy to use. While the source code is now open for experienced developers to build and contribute, purchasing a license helps support continued development and gives you access to automatic updates, priority support, and upcoming features.

Features

• 🎙️ Accurate Transcription: Local AI models that transcribe your voice to text with 99% accuracy, almost instantly
• 🔒 Privacy First: 100% offline processing ensures your data never leaves your device
• ⚡ Modes: Intelligent app detection automatically applies your perfect pre-configured settings based on the app/ URL you're on
• 🧠 Context Aware: Smart AI that understands your screen content and adapts to the context
• 🎯 Global Shortcuts: Configurable keyboard or mouse shortcuts for quick recording and push-to-talk functionality
• 📝 Personal Dictionary: Train the AI to understand your unique terminology with custom words, industry terms, and smart text replacements
• 🔄 Smart Modes: Instantly switch between AI-powered modes optimized for different writing styles and contexts
• 🤖 AI Assistant: Built-in voice assistant mode for a quick chatGPT like conversational assistant

Get Started

Download

Get the latest version with a free trial from tryvoiceink.com. Your purchase helps me work on VoiceInk full-time and continuously improve it with new features and updates.

Homebrew

Alternatively, you can install VoiceInk via brew:

brew install --cask voiceink

Build from Source

As an open-source project, you can build VoiceInk yourself by following the instructions in BUILDING.md. However, the compiled version includes additional benefits like automatic updates, priority support via Discord and email, and helps fund ongoing development.

Requirements

• macOS 15.0 or later

Documentation

• Building from Source - Detailed instructions for building the project
• Contributing Guidelines - How to contribute to VoiceInk
• Code of Conduct - Our community standards

Contributing

This project is not accepting pull requests at this time. You're welcome to fork and modify VoiceInk for your own use.

You can still contribute by: - Reporting bugs via issues - Suggesting features or enhancements - Improving documentation via issues

For more details, see our Contributing Guidelines. For build instructions, see our Building Guide.

License

This project is licensed under the GNU General Public License v3.0 - see the LICENSE file for details.

Support

If you encounter any issues or have questions, please: 1. Check the existing issues in the GitHub repository 2. Create a new issue if your problem isn't already reported 3. Provide as much detail as possible about your environment and the problem

Acknowledgments

Core Technology

• whisper.cpp - High-performance inference of OpenAI's Whisper model
• FluidAudio - Used for Parakeet model implementation
• TranscribeCpp for Swift - SwiftPM distribution of transcribe.cpp, used for local GGUF transcription models
• SenseVoice Small by FunAudioLLM / Alibaba - Multilingual model available under the FunASR Model Open Source License Agreement

Essential Dependencies

• Sparkle - Keeping VoiceInk up to date
• KeyboardShortcuts - User-customizable keyboard shortcuts
• LaunchAtLogin - Launch at login functionality
• MediaRemoteAdapter - Media playback control during recording
• Zip - File compression and decompression utilities
• Swift Atomics - Low-level atomic operations for thread-safe concurrent programming

Made with ❤️ by Pax