Case study 01
Meeting Mind
A Tauri v2 desktop application that automatically detects Microsoft Teams meetings, captures dual audio sources, transcribes locally with faster-whisper, and generates AI-powered summaries — all without sending audio off-device.
Tauri v2 with React and TypeScript frontend
Chose Tauri over Electron for a significantly smaller binary size and native Rust performance. The React frontend provides a polished interface with real-time audio meters, streaming transcripts, waveform visualisation, and a command palette (Cmd+K) — all styled with Tailwind CSS and managed with Zustand state.
Local-first transcription with faster-whisper
Runs the entire speech-to-text pipeline on-device using faster-whisper's CTranslate2 backend, avoiding cloud transcription APIs entirely. This keeps all meeting audio on the machine, addresses privacy requirements for sensitive discussions, and eliminates per-minute API costs.

The main dashboard during an active recording — real-time audio levels, streaming transcript, and meeting controls.


