Beingpax/VoiceInk

The best open-source alternative to Superwhisper & Wispr Flow. Voice-to-text app for macOS with no subscription

What it solves

VoiceInk provides a fast, privacy-focused way to convert spoken words into text on macOS, eliminating the need for cloud-based transcription services that may compromise data privacy.

How it works

The application uses local AI models—including high-performance implementations of OpenAI's Whisper, Parakeet, and Cohere Transcribe—to process audio directly on the device. It features intelligent app detection to apply specific settings based on the active window or URL, and a context-aware system that adapts to screen content.

Who it’s for

macOS users who need high-accuracy voice-to-text transcription with strict privacy requirements and customizable workflows.

Highlights

  • 100% Offline Processing: Ensures data never leaves the device for maximum privacy.
  • Context Awareness: Adapts transcription based on screen content and active applications.
  • Personal Dictionary: Allows users to train the AI on unique terminology and industry-specific words.
  • Global Shortcuts: Supports push-to-talk and configurable keyboard shortcuts for rapid recording.
  • AI Assistant: Includes a built-in conversational assistant mode.

Related

  • Project
    watzon/pindrop

    An open-source, Mac-native AI dictation app that converts speech to text using local Apple Silicon engines or optional cloud services for maximum privacy.

  • Project
    OpenWhispr/openwhispr

    OpenWhispr is a cross‑platform desktop app that converts speech to text, provides live meeting transcription with speaker diarisation, and lets you talk to AI assistants (GPT‑5, Claude, Gemini, etc.) directly from your keyboard. It works offline with Whisper‑based models or via cloud services, stores notes locally (with optional cloud sync), and offers an API for programmatic use.

  • Project
    mylxsw/typeflux

    A macOS app that provides lightning-fast voice-to-text injection into any application, supporting both local and cloud-based AI models for dictation and AI assistance.

  • Project
    altic-dev/FluidVoice

    An open-source voice-to-text dictation app for macOS that enables on-device AI transcription and system control via voice commands.

  • Project
    moinulmoin/voicetypr

    An offline-first voice-to-text dictation app for macOS and Windows that transcribes speech and inserts it directly into any active application.