Don't type it.
Just say it.

VoxType turns your voice into polished text in any Mac app. Hold a key, speak naturally, release — done. Free, open source, and private by design.

macOS 13+ · Apple Silicon & Intel · No account · No subscription

hold fnPush-to-talk — speak while holding, release to insert.
fn fnDouble-tap for hands-free mode. Tap again to finish.
fn + ⌃Command Mode — edit selected text or generate new text by voice.
escCancel a recording anytime.

Everything you need to write 3× faster

Works everywhere you type — email, Slack, browsers, code editors, documents.

⚡️

Speak into any app

VoxType inserts text right at your cursor in whatever app is frontmost. No window switching, no copy-paste.

Auto-polish

Filler words removed, sentences capitalized, punctuation added automatically. Say "press enter" to submit.

🪄

Command Mode

Select text, hold fn+Ctrl, and say "make this more formal" or "translate to Spanish." Or generate text from scratch.

🤖

AI Auto-Edits (optional)

Plug in your own OpenAI key and an LLM rewrites your rambling into clean prose. Entirely optional.

📚

Dictionary & snippets

Teach it names and jargon so they're always spelled right. Say a cue like "my email" to expand full snippets.

🌍

14 languages

Dictate in English, Spanish, French, German, Japanese, Chinese, Hindi, Arabic, and more.

🔒

Private by design

Uses Apple's speech recognition — with an on-device option so audio never leaves your Mac. No accounts, no telemetry.

🧾

History

Every dictation saved locally so you can copy past ones. Stored only on your Mac, clearable anytime.

🆓

Free & open source

No subscription, no word limits, no upsells. Read the code, build it yourself, make it yours.

How it works

From install to first dictation in under two minutes.

1

Install

Download the DMG, drag VoxType to Applications, and open it. It lives quietly in your menu bar.

2

Grant permissions

Allow Microphone, Speech Recognition, and Accessibility — the onboarding window walks you through it.

3

Hold fn & speak

Click into any text field, hold fn, and talk. A small HUD shows your words live as you speak.

4

Release

Let go and polished text appears at your cursor. That's it — now go write that email.

Download VoxType

Free forever. macOS 13 Ventura or later.

First launch: macOS will say it "could not verify VoxType is free of malware" — that's because VoxType isn't notarized by Apple (it's a free community app). Click Done, then open System Settings → Privacy & Security, scroll down, and click Open Anyway next to VoxType. You only do this once. Or in Terminal: xattr -dr com.apple.quarantine /Applications/VoxType.app

FAQ

Quick answers to common questions.

Is VoxType really free?

Yes. It's open source (MIT). No account, no subscription, no word limits. The optional AI features use your own OpenAI API key, so you pay OpenAI directly only for what you use — everything else costs nothing.

Where does my audio go?

To Apple's speech recognition service, the same one built into macOS — or nowhere at all if you enable "prefer on-device recognition" in Settings. VoxType has no servers and collects nothing. Transcripts stay in a local file on your Mac.

Why does it need Accessibility permission?

Two reasons: to detect the fn key being held anywhere in macOS, and to insert text into the app you're using. Both happen entirely on your Mac.

The fn key opens the emoji picker — help?

Go to System Settings → Keyboard → "Press 🌐 key to" and choose Do Nothing. You can also switch the trigger to Right ⌘ or Right ⌥ in VoxType's Settings.

What's Command Mode?

Hold fn+Ctrl and speak an instruction. If text is selected, VoxType rewrites it ("fix the grammar," "make it shorter"). If nothing is selected, it generates new text ("write a polite decline to this invite"). Requires an OpenAI API key in Settings → AI.

How is this different from macOS built-in dictation?

VoxType works with a hold-to-talk key in any app, auto-removes filler words, expands snippets, enforces your custom dictionary, supports voice commands like "press enter," and adds AI-powered editing. Built-in dictation does none of that.

Can I contribute?

Please do! It's a small, readable Swift codebase (~2,000 lines, no dependencies). Open issues and PRs on GitHub.