Tool not found.
Back to Home
Open-source, privacy-first voice-to-text dictation app with AI agents and meeting transcription, free alternative to WisprFlow and Granola.
OpenWhispr turns speech into text, notes, and actions from the desktop: press a hotkey, speak, and the words appear at the cursor. Transcription can run fully offline with local speech-to-text engines like Whisper and NVIDIA Parakeet audio never leaves the device or route through cloud providers for speed, with GPU acceleration available via Metal, CUDA, and Vulkan. Beyond dictation, it includes a voice AI agent that can talk to GPT-5, Claude, Gemini, Groq, Tinfoil, OpenRouter, or local models, plus a dedicated Voice Assistant hotkey that sends spoken commands straight to the assistant without a wake word. It auto-detects Zoom, Teams, and FaceTime meetings for live transcription with speaker diarization, voice fingerprinting, and calendar integration (Google, Microsoft, Apple), and offers a notes system with folders, semantic search, cloud sync, team spaces, and shareable links. Enterprise features cover SSO, SCIM, and centrally managed Bedrock/Azure OpenAI access. It's built with React, TypeScript, Electron, whisper.cpp, and sherpa-onnx, ships cross-platform for macOS, Windows, and Linux, and exposes a public API and MCP server for programmatic control.
