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.
Apple silicon, macOS 14 or later. Dictation is free and unlimited; Tirona Pro is $20 once and also runs on your machine — see pricing.
There is no window to switch to and nothing to click. The shortcut works in whatever you are already typing in.
Right ⌘ by default, or any combination you like. The microphone opens instantly, so nothing you say is clipped.
A small bar shows the level and the clock, so you always know the microphone is open. It says nothing else during a meeting.
Transcription runs on the Neural Engine. Typical end-to-end time is around a tenth of a second.
Text goes to the cursor — and Tirona reads the field back to check it actually arrived, rather than assuming.
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.
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.
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.
Apple silicon Macs on macOS 14 or later. The speech model downloads on first launch and then never needs the network again.
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.
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.
Yes, after the one-time model download. Transcription never needs the network, and nothing has to be activated or checked.
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.