Menu

GitHub - PrestigePvP/Voicebox
πŸ“°
0

GitHub - PrestigePvP/Voicebox

Hacker NewsΒ·3 months ago
#ZKoncStP
#github#voicebox#config#pnpm#worker#article
Reading 0:00
15s threshold

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 β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” PCM chunks β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β” formatted β”‚ Wails Desktop App β”‚ ──WebSocket──▢ β”‚ Cloudflare Worker (Durable Obj) β”‚ ──text────▢ Clipboard β†’ Auto-paste β”‚ (Go + React WebView)β”‚ ◀─────────────│ Whisper STT β†’ LLM Formatter β”‚ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜ 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/ β”œβ”€β”€ main.go # Wails entrypoint, app menu β”œβ”€β”€ app.go # App lifecycle, hotkey handlers, pipeline orchestration β”œβ”€β”€β€¦

Continue reading β€” create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.

Read More