VoiceCmd

Voice macros with key holds

Only for Mac

$19.99

Mac

Say one phrase, get a whole sequence - keys held for a beat, delays between them, clicks and typed text. Not one shortcut. A macro. Activate keyboard macros with your voice. Say "reload" and the R key happens. Say "unleash the kraken" and a whole macro happens - a sequence of keystrokes with real holds and precise delays, mouse clicks, typed text, exactly as you defined it. One phrase, many actions. MACROS, NOT SINGLE SHORTCUTS This is the part most voice tools stop short of: - Hold a key down for a set duration, then release it - not just tap it - Chain any number of steps together, with delays you control between them - Mix keys, combinations, mouse clicks, movement, scrolling and typed text in one command - Reach the whole keyboard: F1 through F24, the numpad, navigation keys, media keys IT LISTENS WHEN YOU WANT IT TO Push-to-talk or a toggle hotkey means it only acts while you say so, so it will not fire mid-sentence while you are on a call. There is an optional wake word if you would rather address it by name. Because the hotkey gates matching rather than the microphone, there is no spin-up delay when you start talking. It also stays out of the way of your normal dictation - VoiceCmd runs in the menu bar alongside it, not instead of it. PROFILES THAT FOLLOW YOU Group commands into profiles, one per app or game. VoiceCmd notices which app you switch to and loads the matching profile automatically. Export any profile as JSON to back it up or share it. FAST, AND HONEST ABOUT IT Roughly half a second from the moment you stop speaking to the keystroke landing. Recognition streams continuously rather than waiting for you to finish. A built-in debug view breaks the timing down step by step, so you can see exactly where the time goes rather than taking our word for it. UNDERSTANDS YOU, NOT JUST YOUR DICTION - Fuzzy matching tolerates typos and homophones - Longest phrase wins, so "reload weapon" never fires "reload" by mistake - Per-command and global cooldowns stop one utterance firing twice PRIVATE BY CONSTRUCTION Recognition runs on your own machine, from a model bundled inside the app. Audio is processed as a live stream and never written to a file, never uploaded, and discarded the moment it becomes text. No account, no telemetry, no servers. It works with the network switched off. PERMISSIONS VoiceCmd needs microphone access to hear you, and macOS Accessibility permission to press keys on your behalf. It asks for both on first run and explains what each is for. Without Accessibility, macOS silently discards every simulated keystroke - so the app says so plainly rather than appearing broken. Machinaut Studios LLC

  • This app hasn’t received enough ratings or reviews to display an overview.

The developer, Machinaut Studios LLC, indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy .

  • Data Not Collected

    The developer does not collect any data from this app.

    Privacy practices may vary, for example, based on the features you use or your age. Learn More

    The developer has not yet indicated which accessibility features this app supports. Learn More

    Seller
    • Machinaut Studios LLC
    Size
    • 81.4 MB
    Category
    • Productivity
    Compatibility
    Requires macOS 10.15 or later.
    • Mac
      Requires macOS 10.15 or later.
    Languages
    • English
    Age Rating
    4+
    Copyright
    • © 2026 Machinaut Studios LLC