ECO.V1 KodaVoice · part of the Koda ecosystem

Hold a key.
Speak.
It's typed.

KodaVoice is push-to-talk voice typing for Windows. Hold Right Ctrl in any app — your editor, browser, chat, or a Koda agent pane — say what you're thinking, release, and your words are typed at the cursor. Transcription runs entirely on your machine with Whisper: private, offline, no cloud round-trip.

Windows 10/11 · local Whisper transcription · works offline

kodavoice — push-to-talk · any focused window engine ready · mic armed
100%
local transcription
0
audio uploaded. ever.
1
hotkey — works in any app
3
GPU vendors accelerated
ECO.V2 The whole kit

Dictation that keeps up
with how you work

One hotkey, every app. KodaVoice stays out of the way in your system tray and turns speech into text wherever your cursor is.

SEC/TRUST LOCAL-FIRST
ECO.V3 Built the honest way

Your voice never
leaves your machine.

KodaVoice runs faster-whisper locally. Audio is recorded, transcribed, and discarded on your own hardware — there's no KodaVoice server, no account, and nothing to subscribe your microphone to.

Same principle as everything in the Koda ecosystem: local-first, and honest about what runs where.

  • On-device WhisperThe speech model downloads once (~1.6 GB) and runs offline from then on.
  • No audio uploadsRecordings never leave your PC. No telemetry on what you say.
  • GPU acceleratedNVIDIA via CUDA; AMD & Intel via Vulkan — no CUDA or ROCm install needed.
ECO.V4 Better together

The voice of the
Koda ecosystem

Koda gives your coding agents a command deck. KodaVoice gives you a faster way to drive it — hold the key and speak your prompts, task cards, and replies straight into any agent pane instead of typing them. Two apps, one design language, one local-first philosophy.

ECO.V5 Questions

Frequently asked

Is my voice sent to the cloud?

No. Transcription runs entirely on your machine using faster-whisper. The speech model is downloaded once (~1.6 GB) on first launch, and after that KodaVoice works fully offline. Your audio is never uploaded anywhere.

How does push-to-talk work?

Hold the hotkey (default Right Ctrl), speak, and release. A beep confirms recording started and stopped, a live meter shows your level, and a moment later your words are typed into whatever window has focus. Every transcript is also kept in the app's history panel. You can rebind the hotkey to any key in Settings.

What hardware do I need?

Any reasonably modern Windows 10/11 PC works on CPU. For much faster transcription, flip on Use GPU in Settings — it supports NVIDIA (CUDA) and AMD / Intel (via Vulkan, no CUDA or ROCm install needed). The toggle only enables when a compatible GPU is detected.

Does it work inside Koda?

Yes — KodaVoice types wherever your cursor is, and Koda's agent panes are ordinary terminals. Hold the key, describe the task, release, and your prompt lands in the pane ready to send. It's the fastest way to brief an agent.

Can I fix words it gets wrong?

Yes. The Vocabulary setting takes whole-word find→replace rules applied to every transcript — perfect for names, jargon, and acronyms the recognizer trips on (e.g. "clod" → "Claude"). You can also say "new line" or "new paragraph" while dictating to insert line breaks.

Why does Windows warn me on first launch?

KodaVoice isn't code-signed with a paid certificate yet, so Microsoft Defender SmartScreen shows a one-time caution — the same one Koda shows. Click More infoRun anyway, once. Signed builds are on the roadmap.

What platforms are supported?

Windows 10/11 today. KodaVoice installs per-user (no admin rights), lives in your system tray, can start with Windows, and updates itself — when a new release is out, an Update button appears and the app swaps itself over in one click.

V

Stop typing
what you could
just say.

Get KodaVoice and put a push-to-talk key under everything you write.

First launch: if SmartScreen appears, click More infoRun anyway, once.