Support

Local Voice Support

Something not working, or a question about Local Voice? Start with the answers below, or email me directly — I’m the developer and I reply personally.

Email the developer

Include your macOS version and what you expected to happen. Screenshots help.

parthmudgal15105@gmail.com

Status & requirements

Open source — Experimental · build from source. Requires Apple silicon Mac, macOS 14 or later. Building needs Xcode Command Line Tools, Homebrew, Git, uv and several GB of model downloads..

Local Voice overview

Privacy

Local Voice has no account and no cloud sync. After setup downloads the models, local processing keeps speech recognition on your Mac. Settings and optional history stay in a folder on your Mac.

Read the privacy policy

Troubleshooting & common questions

The Fn shortcut does nothing

Grant Accessibility (Device Control) permission in Settings, then reconnect the shortcut. Disable other Fn bindings and set the macOS Globe key action to Do Nothing.

Permission is on but the app says it is unavailable

In System Settings, switch Local Voice off and on again in the relevant privacy list, then return to the app.

Setup failed or a model is missing

Check your internet connection and free disk space, then run ./setup.sh again. For the optional Qwen engine, run ./setup-asr.sh and do not select a model until its setup has finished.

Rebuilding after an update

Pull the latest source, run ./build.sh, and reopen the app.

Is there a download?

Not yet. Local Voice is an experimental source build. You build it on your own Mac with ./setup.sh. There is no notarized, Apple-trusted binary, and prebuilt app bundles copied from another Mac are not supported.

What do I need?

An Apple silicon Mac with macOS 14 or later, Xcode Command Line Tools, Homebrew, Git and uv. Setup needs internet and several GB of free disk space for models. Intel Macs are not supported. The optional Qwen engine via MLX needs macOS 26.2 or later.

Does my voice leave my Mac?

Setup downloads the models from the internet. After that, local processing keeps speech recognition on your Mac. The private-server mode is disabled in the public source.

How accurate is it?

Accuracy and speed vary with your hardware, microphone and speech. Recognition and transliteration can make mistakes, especially with names, so review text before you use it. The dictionary helps with words you use often.

How much does it cost?

It is free to build and use. The repository does not include a license file yet.

What is it built on?

whisper.cpp and Whisper for speech, optional MLX/Qwen, and AI4Bharat IndicXlit for Hinglish transliteration. Some reliability patterns were adapted from the open-source Handy and OpenWhispr projects under the MIT license; their notices are included in the repository.