1
Download
Grab the latest release for your platform from the releases page.
2
Install and launch
Open the installer and follow the prompts. On first launch, OpenWhispr walks you through onboarding: dictation first, then Notes and meeting recording, then a live demo of the voice assistant.
3
Choose your processing method
- OpenWhispr Cloud — sign in with Google, Apple (macOS), Microsoft, or email for instant transcription
- Bring your own key — enter your OpenAI, Groq, or other API key
- Local — download a local model; Orukeet is recommended, with Whisper, Parakeet, Nemotron and Cohere Transcribe also available (no internet needed after download)
4
Grant permissions
- Microphone — required for voice recording
- Accessibility (macOS) — required for automatic text pasting
- Screen recording (macOS) — needed for meeting audio capture
5
Start dictating
Press your hotkey (Globe/Fn on macOS, Ctrl+Win on Windows, and on Linux Ctrl+Super or F8 depending on your desktop), speak, press again. Your text appears at your cursor.
Building from source
If you prefer to build from source:Requires Node.js 24+. See the contributing guide for build details.