Voice typing for Mac.

Tiny macOS app that turns speech to text — fast, accurate, and private. Bring your own API key, connect to the best speech models, and pay only for what you use.

Download
0.5 MB macOS 15.0+
Tiny
0.5 MB app, minimal memory usage
Fast
Talks to models directly for minimal latency
Accurate
Latest models, smart context handling
Private
No middleman, no accounts, no data collection
Low-cost
Use your own API key, pay only for what you use
Customizable
Personal dictionary, app-specific rules
Scriptable
AppleScript commands for custom integrations

Models

Works with the best speech-to-text models on the market.

  • Whisper
  • GPT-4o Transcribe
  • Voxtral Mini Transcribe
  • Scribe V2

Local models coming soon.

Changelog

Here's a summary of the last 16 updates:

  • 0.31.0   May 05   Update app icon and HUD design
  • 0.30.0   May 04   Add option to copy transcripts to clipboard
  • 0.29.0   Apr 16   Redesign HUD with backdrop blur and refined shape
  • 0.28.0   Mar 18   Simplify transcript history
  • 0.27.0   Mar 18   Simplify app updater
  • 0.26.0   Mar 12   Add Recent Transcripts submenu for browsing past transcripts
  • 0.25.0   Mar 08   Redesign recording HUD and settings UI
  • 0.24.0   Mar 03   Add new transcription providers and Whisper model support
  • 0.23.0   Feb 09   Make Shift Shift the default activation shortcut
  • 0.22.0   Feb 04   Add Enter Enter shortcut to transcribe and send messages
  • 0.21.0   Feb 02   Make "Refine speech" more aggressive at detecting implicit restarts
  • 0.20.0   Jan 24   Add intent-based speech refinement for cleaner transcripts
  • 0.19.0   Jan 16   Update app icon and add dictionary editor with sidebar tabs in settings
  • 0.18.0   Jan 13   Improve paste detection for Cursor and other Electron apps
  • 0.17.0   Jan 11   Show transcript overlay when paste fails

See full changelog

Made by erusev and astoilkov