What you can do
Dictation
Press a hotkey, speak, and your words appear at your cursor. Works in any app.
AI agent
Talk to your AI assistant using OpenAI, Anthropic, Google, or local models.
Meeting transcription
Auto-detect Zoom, Teams, and FaceTime calls. Transcribe with speaker labels.
Notes
Create, organize, and search notes with folders, cloud sync, and AI actions.
Team spaces
Shared spaces for your workspace’s notes. Add people directly or through groups.
Processing options
Choose how your audio is processed:- OpenWhispr Cloud — sign in and transcribe instantly, no API keys needed
- Bring your own key — use your own OpenAI, Groq, xAI, Mistral, Tinfoil, OpenRouter, Corti, Deepgram, or AssemblyAI credentials
- Local processing — download Orukeet, Whisper, NVIDIA Parakeet, Nemotron, or Cohere Transcribe models for completely private transcription
Platforms
OpenWhispr runs on macOS 12+, Windows 10+, and 64-bit Linux. Download from the releases page or build from source. System requirements has the detail, including what on-device models need. There’s also an iPhone and iPad app on the App Store, with a system-wide dictation keyboard and unlimited on-device transcription. iOS covers setting it up.macOS
Apple Silicon and Intel
Windows
x64 with push-to-talk
Linux
AppImage, deb, rpm, tar.gz
iOS
iPhone and iPad, on the App Store
For developers
OpenWhispr has a public REST API and an MCP server for AI assistant integration.API reference
Manage notes, folders, transcriptions, dictionary, snippets, and usage programmatically.
MCP server
Connect Claude, Cursor, or VS Code to your OpenWhispr data.
