VocalCode: Push-to-Talk Dictation for AI Coding Agents, On-Device
VocalCode is a push-to-talk voice input tool for AI-assisted coding that runs entirely on your machine. It types into the active text field of most desktop apps with no audio uploaded to a server. Available for Windows and macOS as a one-time $4.99 purchase with a 30-day free trial.
Just talk.It types.
Push-to-talk voice input for coding with AI. On your machine, in most desktop apps, without sending speech to a server.
Listening
Download for Windows · 9.5 MB Download for macOS · Apple Silicon · 10.9 MB
30 days free · no card Launch price$4.99 once 0 bytes of audio uploaded · offline after model download
What it looks like
A capsule appears, you speak, the words are already in the file.
No window to switch to, no dictation box to copy out of. VocalCode types into the active text field in most desktop apps — your editor, terminal, chat or code review.
api/session.ts — Cursor
// ask for what you want, out loud
export async function refreshSession(id: string) {
const row = await db.get(id)
//
}
On-device recognition · CPU only
Listening
mouse ⏵ forwardWindows right ⌥ OptionF13macOS — all live at once, all rebindable
LOCAL
Speech recognition on your CPU
Audio is decoded on this computer. Responsiveness varies with hardware, audio length, language and model; we do not publish an unsupported latency promise.
0bytes
of audio uploaded
Recognition sends no audio or transcript. Initial trial setup, activation, periodic licence refresh, model downloads and update checks use the internet.
26model-supported
Two on-device model routes
Choose Mandarin Chinese or one of 25 European language preferences. The European choices share one Parakeet model that detects the spoken language automatically; they are preview labels pending per-language product testing. After the model is downloaded, recognition works with the wifi off.
One-time purchase
Pay once. No subscription.
The recognition models run on your computer. The $4.99 licence has no recurring fee, includes updates within the current major version, and revalidates online at least every 30 days.
30-day full trialEvery feature, no card required$0
VocalCode licenceUse on up to 3 devices$4.99 once
Buy VocalCode — $4.99 Start the 30-day trial
Plus applicable tax · speech recognition stays on-device
Screenshots
What you get
The appWaits in the background until you hold the key.
ShortcutsSeveral keys and mouse buttons at once, rebindable in Settings.
LanguagesPick a model route; recognition runs on this computer.
See the full product gallery
FAQ
Questions
Does my voice go to the cloud?
Speech audio stays on this computer.
Recognition runs on your own CPU; audio is never uploaded
Recent transcript history stays in memory for this app session; it is not written to disk or uploaded
Starting the free trial requires the internet once and sends a stable pseudonymous device fingerprint
Manual activation sends the licence key and a stable pseudonymous device fingerprint
A paid licence is revalidated online before its 30-day signed receipt expires
Checkout polling sends that fingerprint; model downloads and update checks also use the internet
None of those requests sends audio or transcripts
After model download, recognition works offline; initial trial setup, activation and periodic licence refresh do not
Read the full privacy notice
Which key do I hold?
Windowsmouse ⏵ forward
macOSright ⌥ OptionF13mouse ⏵ forward
All of them are live at once — plug in a mouse or undock and nothing needs changing
Rebind any of them in Settings
Where can it type?
Into the active text field in most desktop apps.
Windows cannot inject text into an app running with higher administrator privileges
Password and other secure fields, plus some apps, may reject synthetic input
macOS text insertion requires Accessibility and Input Monitoring permission
Which languages?
English普通话EspañolFrançaisDeutschItalianoPortuguês (Portugal)+ 19 more
Choose Mandarin Chinese or one of Parakeet's 25 listed European languages
The European choices share one auto-detecting model; choosing a label does not constrain decoding
Those 25 European choices are model-supported previews while release-binary tests are completed
Mandarin Chinese uses a dedicated bilingual Chinese–English Paraformer model
Cantonese, Korean, Japanese, Thai and Vietnamese are not available
Is it really buy-once?
Yes. $4.99 once, plus applicable tax.
No subscription, no account, no seat
Use on up to 3 devices
Free updates within the major version
30 days free first — no card
Starting the trial requires internet once; its signed receipt is then checked offline
Mac?
macOS 11 or later on Apple Silicon (arm64)
Developer ID-signed and notarised by Apple for Gatekeeper
: the i18n walker keys on whole nodes, and a sentence chopped by markup cannot be translated into a language that orders it differently. -->
First launch asks for Microphone, Accessibility and Input Monitoring
Accessibility lets VocalCode check the focused target; recognised text is sent with native macOS input events
The app names each one and why it needs it