The open-source and free alternative to WisprFlow and Granola.
Privacy-first voice-to-text dictation with AI agents, meeting transcription, and notes. Cross-platform for macOS, Windows, and Linux.
Website · Docs · Download · API · Changelog
OpenWhispr turns your voice into text, notes, and actions from your desktop. Press a hotkey, speak, and your words appear at your cursor. Choose between fully private offline transcription with local speech-to-text engines like Whisper and NVIDIA Parakeet — where your audio never leaves your device — or cloud processing for speed. No data collection, no telemetry, fully open source.
| Platform | Download |
|---|---|
| macOS (Apple Silicon) | .dmg |
| macOS (Intel) | .dmg |
| Windows | .exe |
| Linux | .AppImage / .deb / .rpm |
- Voice dictation — global hotkey to dictate into any app with automatic pasting
- AI agent — talk to GPT-5, Claude, Gemini, Groq, or local models with a named voice assistant
- Meeting transcription — auto-detect Zoom, Teams, and FaceTime calls with live speaker diarization, voice fingerprinting, and Google Calendar integration
- Local speaker diarization — on-device speaker labelling with voice fingerprint recognition across meetings, no cloud required
- Notes — create, organize, and search notes with folders, semantic search, cloud sync, and AI actions
- Local or cloud — your choice — all core features (transcription, AI reasoning, speaker diarization, semantic search) work with local models or cloud providers
- Public API & MCP — manage notes and transcriptions programmatically or connect your AI assistant via the MCP server
git clone https://github.com/OpenWhispr/openwhispr.git
cd openwhispr
npm install
npm run devRequires Node.js 24+. See the full documentation for setup guides, platform-specific instructions, and build details.
Two local Linux build paths are available:
NixPath: keep usingshell.nixif you want the existing Nix shell workflow.DockerPath: run the full Linux packaging flow inside a CI-like container and build artifacts from there.
Podman is used automatically when available, with Docker as a fallback. The Docker/Podman path mirrors the Linux GitHub Actions job by installing the same system packages, running npm ci, fetching the Linux native package overrides, downloading runtime binaries, and then invoking Electron Builder inside the container.
# Existing Nix shell path
nix-shell
npm run build:linux:appimage
# Container-only path, defaults to podman when installed
npm run build:linux:appimage:dockerYou can also build other Linux targets entirely in the container:
npm run build:linux:docker
npm run build:linux:deb:docker
npm run build:linux:rpm:dockerUseful environment variables for the container flow:
CONTAINER_ENGINE=podmanorCONTAINER_ENGINE=dockerOPENWHISPR_CI_IMAGE=openwhispr-linux-ci:localGH_TOKEN,GITHUB_TOKEN,VITE_NEON_AUTH_URL,VITE_OPENWHISPR_API_URL,VITE_OPENWHISPR_OAUTH_CALLBACK_URL
Visit docs.openwhispr.com for:
- Getting started
- Platform guides (macOS, Windows, Linux)
- API reference
- MCP server setup
- Troubleshooting
React 19, TypeScript, Tailwind CSS v4, Electron 41, better-sqlite3, whisper.cpp, sherpa-onnx, shadcn/ui
Neon is the serverless Postgres platform powering OpenWhispr Cloud.
We welcome contributions. Fork the repo, create a feature branch, and open a pull request. See the contributing guide for development setup and guidelines.
MIT — free for personal and commercial use.
- OpenAI Whisper — speech recognition model powering local and cloud transcription
- whisper.cpp — high-performance C++ implementation for local processing
- NVIDIA Parakeet — fast multilingual ASR model
- sherpa-onnx — cross-platform ONNX runtime for Parakeet inference
- Hugging Face — model hub hosting Whisper, Parakeet, and embedding model weights
- llama.cpp — local LLM inference for AI text processing
- Electron — cross-platform desktop framework
- React — UI component library
- shadcn/ui — accessible components built on Radix primitives
- Neon — serverless Postgres powering OpenWhispr Cloud