Launched this week
Vox
Voice in, voice out — with GitHub Copilot
191 followers
Voice in, voice out — with GitHub Copilot
191 followers
Vox is a GitHub Copilot CLI extension: run /vox and a reactive listening orb opens in its own window. Speak your turn, hear the agent reply. Voice in, voice out — on Windows, macOS, and Linux.
voice in / voice out for coding is the interface i keep wanting — the friction was always latency and round-tripping audio to a server. are you running the speech piece locally or in the cloud? been deep in on-device voice on my side and the tradeoffs are brutal.
@sabber_ahamed Totally hear you — Vox is 100% cloud for speech today, riding the browser's native Web Speech API, so it round-trips to Google's servers, not on-device. Zero extra latency/infra from Vox itself, but no offline mode yet — a local/offline (Whisper-based) option is on the roadmap.
launching Chromium in app mode instead of shipping Electron is such a clean hack, one-line install with no build step because the browser already has the speech APIs. more tools should steal this
the barge-in interrupt is the detail that makes voice actually usable btw, nothing worse than waiting out a wrong answer
@yarslav Thank you! Yeah, launching Chrome/Edge in app mode was the unlock — get a real desktop-style window with zero Electron overhead and the Web Speech APIs just work natively. Glad the barge-in landed too, that was the detail I iterated on most.
How does it handle background noise or interruptions mid-conversation, and is there any kind of wake-word or do I have to trigger it manually each time I want to talk to the agent?
That's clever. Any plans to support other AI coding assistants beyond GitHub Copilot?
@dhiraj_patel5 Right now it's built tightly on the Copilot CLI's extension/SDK hooks (that's how it taps into turns, streaming replies, and session state) — so it's Copilot-specific today, not agent-agnostic. That said, the voice layer itself (mic capture, barge-in, TTS queue) is a self-contained browser front-end, so porting the "wiring" to another agent's extension API is architecturally possible if there's interest — just not on the roadmap yet.
Me appreciate the simple setup process. Why not include offline support? I think limited offline features would increase reliability.
@alex_bravo1 Appreciate that! Offline is on my radar — right now it leans on the browser's native Web Speech API for simplicity/zero-install, but that does need network for recognition. A local/offline mode (likely Whisper-based) would genuinely help reliability in spotty-network or privacy-sensitive setups, so it's a good candidate for a future version.
The reactive listening orb in its own dedicated window is a really nice touch, keeps the voice interaction feeling like a proper companion rather than just another terminal pane.
@alperen397545 Thanks! That was very deliberate — I wanted it to feel like a companion you glance at and talk to, not just another pane competing for attention in your terminal. Launching it as its own chrome-less app-mode window (rather than a browser tab or Electron app) is what makes that possible while still keeping the Web Speech APIs working natively.