Tirona
macOS · Android

Dictation that never leaves your machine.

Hold a key anywhere, speak, let go. The text lands where your cursor is — in any app, with no account, no upload and no subscription.

LISTENING · 0:04

Apple silicon, macOS 14 or later. Dictation is free and unlimited; Tirona Pro is $20 once and also runs on your machine — see pricing.

One gesture

Press. Speak. Release. Done.

There is no window to switch to and nothing to click. The shortcut works in whatever you are already typing in.

  1. Hold the key

    Right by default, or any combination you like. The microphone opens instantly, so nothing you say is clipped.

  2. Say it

    A small bar shows the level and the clock, so you always know the microphone is open. It says nothing else during a meeting.

  3. Let go

    Transcription runs on the Neural Engine. Typical end-to-end time is around a tenth of a second.

  4. It lands

    Text goes to the cursor — and Tirona reads the field back to check it actually arrived, rather than assuming.

What it does

Dictation, and the parts around it.

It gets names right
Teach it a correction once and it always wins. Point it at a folder of your notes and it learns the names you actually write — matched by how they sound, so “Ferrara” becomes “Ferreira” without touching the rest of the sentence.
Modes
How you want words cleaned up depends on what you are writing, not on who you are. Name a mode, say what it should do differently, and let it switch itself on in the apps you choose.
Files, not just live speech
Drop in a voice memo, an interview or a meeting recording. Long files are transcribed a window at a time, and on macOS it can split the recording by speaker and label who said what.
It knows whether it worked
Every insertion is read back and checked. When an app cannot be typed into you get the text and a plain reason rather than silence — and Tirona never presses Return on a write it could not confirm.
Privacy

Nothing to trust us with.

Most dictation apps stream your microphone to a server. Tirona does the recognition on your own hardware, which means there is no audio to leak, no account to breach and no bill that scales with how much you talk.

On-device speech
NVIDIA Parakeet on the Apple Neural Engine. Downloaded once, then it works on a plane.
No account, no check
No sign-up, no email, and nothing to activate. After the one-time model download, Tirona makes no requests of its own unless you ask it to. Usage statistics are off, and off means nothing is counted.
Where it runs

The same tool on the desk and in your pocket.

macOS
  • Global hold-to-talk shortcut, works in every app
  • Verified insertion, with a plain reason when an app refuses
  • Transcribe recordings you have, with speaker labels
  • Menu-bar only if you want no window at all
Android
  • A floating bubble above the keyboard, in any app
  • The same model, on-device
  • Hands-free continuous capture
  • The same filler removal, name correction and modes

Settings do not sync between the two. There is no account to sync them through, which is the trade: your corrections live on the device you taught them to.

Pricing

Dictation is free. Pro is one payment.

Both of these run entirely on your own machine — Pro is not a cloud tier and does not send your words anywhere. It buys more of the app, not more of our servers, which is why it is paid once rather than monthly.

FREE
$0
  • Unlimited dictation, everywhere you can type
  • The full-accuracy speech model
  • Filler removal and the cleanup pass
  • No account, no card, no expiry
TIRONA PRO · ON DEVICE
$20
  • Meeting notes, transcribed on this Mac
  • Continuous dictation
  • Destinations — send dictated text straight into other apps
  • One payment, every device, no subscription
Get Tirona Pro — $20
CLOUD · LATER
Not yet
  • For hardware without the memory to hold a speech model
  • It would be paid, because servers are a real cost
  • Or bring your own API key and pay nobody
  • Not part of this release, and not what Pro is
Download

Get started.

Apple silicon Macs on macOS 14 or later. The speech model downloads on first launch and then never needs the network again.

Questions

The obvious ones.

Why isn’t it on the Mac App Store?

Because it could not work there. Typing into another app needs the Accessibility API, which sandboxed App Store apps are not permitted to use. Every app in this category ships the same way — downloaded directly, signed and notarised by Apple.

What’s free, and what costs money?

Dictation is free — unlimited, the full-accuracy model, no account. It runs on your own hardware, so serving you costs us nothing.

Tirona Pro is $20, once. It adds meeting notes, continuous dictation and destinations. It still runs entirely on your machine — Pro is not a cloud plan, and buying it does not send your words anywhere. It is paid once rather than monthly for exactly that reason: there is no server bill behind it.

There is no third thing. Cloud transcription may arrive later for devices that cannot hold a speech model in memory, and that would be paid — but it does not exist yet and it is not what Pro is.

Does it work offline?

Yes, after the one-time model download. Transcription never needs the network, and nothing has to be activated or checked.

The name

Named for the man who invented this.

In 63 BC, a man named Marcus Tullius Tiro sat in the Roman Senate and did something nobody had done before: he wrote down a speech at the speed it was spoken.

Tiro was Cicero’s secretary, and he built a system of shorthand to keep up with him — thousands of marks standing for whole words and endings. The Romans called it notae Tironianae, Tiro’s notes. It worked well enough that scribes were still using it a thousand years later, and one of his marks is still in use today: , the Tironian et, which you can find on road signs in Ireland.

So the problem is not new. Speech has always outrun writing, and for two thousand years the answer has been to put a skilled person in the room and have them take it down. Tirona does the same job with the same constraint Tiro had — the words stay in the room they were spoken in.