boseq
7bf9646e16
- The record and Share pills sit side by side at the leading edge when they take their own row, and stay at the trailing end of the tab row when they fit beside the tabs. - An overflowing tab strip no longer draws an empty scrollbar track, and the selected tab is scrolled into view (LTR and RTL). - The header keeps its 20px inset at every width, so it lines up with the note body. - Drop classes that had no effect on the tab buttons and the controls group. - Remove the before/after screenshots from docs/; the PR description links them at a pinned commit.
OpenWhispr
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 models like Orukeet, Whisper, NVIDIA Parakeet, and Cohere Transcribe — where your audio never leaves your device — or cloud processing for speed. No data collection, no telemetry, fully open source.
Download
| Platform | Download |
|---|---|
| macOS (Apple Silicon) | .dmg |
| macOS (Intel) * | .dmg |
| Windows | .exe |
| Linux | .AppImage / .deb / .rpm / .tar.gz |
* On Intel Macs, live speaker identification and voice fingerprinting are unavailable: they depend on ONNX Runtime, which stopped shipping macOS x86_64 binaries in 1.24. Meetings still record and transcribe normally, and notes search falls back to keyword matching instead of semantic search.
Features
- Voice dictation — global hotkey to dictate into any app with automatic pasting
- Dictation translation — dedicated hotkey to dictate in one language and paste the text in another
- AI agent — talk to GPT-5, Claude, Gemini, Groq, Tinfoil, OpenRouter, or local models with a named voice assistant
- Voice Assistant hotkey — dedicated hotkey that sends what you say straight to your AI assistant as a command, no wake word needed and no cleanup pass; highlighted text is edited in place. With auto-paste enabled, answers paste at a focused text cursor or stream into a floating panel and copy to the clipboard when no writable cursor is available. You can also opt in to sending a screenshot of your current screen as context
- Meeting transcription — auto-detect Zoom, Teams, and FaceTime calls with live speaker diarization, voice fingerprinting, and Google, Microsoft, or Apple 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
- Team spaces & sharing — free for signed-in users; share notes on the web with link, domain, or invite-only visibility, and collaborate in team spaces with roles, invitations, and server-enforced membership
- Audio import — transcribe existing audio and video: drag in files, batch-upload, or paste a YouTube/audio URL, with optional speaker detection
- Local or cloud — your choice — all core features (transcription, AI reasoning, speaker diarization, semantic search) work with local models or cloud providers — including GPU-accelerated local Whisper on Metal, CUDA, and Vulkan (AMD/Intel)
- Enterprise controls — enforce organization policy, company SSO and SCIM, and centrally managed Amazon Bedrock or Azure OpenAI access without distributing cloud keys
- Public API & MCP — manage notes and transcriptions programmatically or connect your AI assistant via the MCP server
Quick start
git clone https://github.com/OpenWhispr/openwhispr.git
cd openwhispr
npm install
npm run dev
Requires Node.js 24+. See the full documentation for setup guides, platform-specific instructions, and build details.
The commands above run the desktop application, which remains at the repository root. The Expo mobile application lives in openwhispr-mobile with its own dependencies, lockfile, build configuration, and release process. See the mobile README for its setup instructions.
Documentation
Visit docs.openwhispr.com for:
- Getting started
- Platform guides (macOS, Windows, Linux)
- API reference
- MCP server setup
- Troubleshooting
Repo examples:
- Custom ASR shim for Self-Hosted transcription against non-OpenAI-compatible ASR APIs
Tech stack
React 19, TypeScript, Tailwind CSS v4, Electron 41, better-sqlite3, whisper.cpp, sherpa-onnx, shadcn/ui
Star History
Sponsors
Neon is the serverless Postgres platform powering OpenWhispr Cloud.
Contributing
We welcome contributions. Fork the repo, create a feature branch, and open a pull request. See the contributing guide for development setup and guidelines.
License
MIT — free for personal and commercial use.
Acknowledgments
- 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