Meeting transcription and summaries that run entirely on your own computer. No cloud, no uploads, no account - the recording and the transcript never leave your device.
Speech recognition runs on Whisper large-v3, a multilingual model. In our own tests it handles Polish noticeably better than the transcription built into common meeting tools.
Meeting summaries are produced by a language model running on your machine, so the transcript is not sent to any external service to be summarized.
No server-side processing, no account, no telemetry. What you record and what you transcribe stays on your disk.