Show HN: VocalCode – push-to-talk dictation for AI coding agents, on-device

VocalCode, a push-to-talk dictation tool for AI coding agents, launches with a $4.99 one-time price and 30-day free trial, processing speech entirely on-device with zero audio uploaded. The tool, which supports Mandarin Chinese and 25 European languages via Parakeet and Paraformer models, types into the active text field in most desktop apps and works offline after model download.

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. 30 days free · no card Launch price $4.99 once 0 bytes of audio uploaded · offline after model download 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. export async function refreshSession id: string { const row = await db.get id // } 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 Responsiveness varies with hardware, audio length, language and model; we do not publish an unsupported latency promise. of audio uploaded Recognition sends no audio or transcript. Initial trial setup, activation, periodic licence refresh, model downloads and update checks use the internet. 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. 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. once 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 /privacy/ Which key do I hold? - 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? - 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 - 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