Voice-to-text tool that captures speech, transcribes it via Whisper, and formats the output with an LLM. Press a hotkey, speak, release β formatted text lands in your clipboard and is auto-pasted into whatever you were typing in. How It Works ββββββββββββββββββββββββ PCM chunks ββββββββββββββββββββββββββββββββββββ formatted β Wails Desktop App β ββWebSocketβββΆ β Cloudflare Worker (Durable Obj) β ββtextβββββΆ Clipboard β Auto-paste β (Go + React WebView)β βββββββββββββββ Whisper STT β LLM Formatter β ββββββββββββββββββββββββ ββββββββββββββββββββββββββββββββββββ Hold Ctrl+Cmd β focus context is captured, recording starts, overlay appears at top-center Speak into your microphone (voice level meter shows input) Release Ctrl+Cmd β audio streams to the cloud Whisper transcribes, LLM formats, result is copied to clipboard and auto-pasted into the originating app Project Structure voicebox/ βββ main.go # Wails entrypoint, app menu βββ app.go # App lifecycle, hotkey handlers, pipeline orchestration ββββ¦