Skip to main content
OpenWhispr captures your voice through a global hotkey and pastes the transcribed text at your cursor. It works in any app — email, chat, code editors, documents.

​
How it works

  1. Press your hotkey (Globe/Fn on macOS, Ctrl+Win/Ctrl+Super on Windows and Linux)
  2. Speak naturally — the panel shows a recording animation
  3. Press the hotkey again to stop
  4. Text is transcribed and automatically pasted at your cursor

​
Hotkey options

Change your hotkey in Settings > Hotkey. You can use any single key or compound combinations like Ctrl+Shift+K. Each action’s hotkey supports multiple bindings — click Add another hotkey to trigger the same action (dictation, agent, voice agent, or meeting) from more than one key or keyboard.

​
Activation modes

  • Tap-to-talk — press once to start, press again to stop (default on all platforms)
  • Push-to-talk — hold to record, release to stop (Windows only, requires native binary)

​
Auto-paste

After transcription, text is automatically pasted at your cursor location. This requires:
  • macOS — Accessibility permission (System Settings > Privacy > Accessibility)
  • Windows — works out of the box
  • Linux — native paste binary included; falls back to xdotool, wtype, or ydotool
You can disable auto-paste in settings if you prefer to paste manually with Ctrl+V.

​
Auto-pause media

OpenWhispr automatically pauses media playback (Spotify, Apple Music, etc.) during dictation and resumes when you’re done. Toggle this in Settings > General.