On-device dictation

Speak. It types. Nothing leaves.

Hold a key, say what you mean, let go. Dictaquill types your words into whatever app you are working in. Recognition happens on your own computer, so your voice and your words never leave it.

Zero bytes uploadedRecognition runs on your computer.

Zero audio files savedSound is processed and gone.

Zero accounts to createNo login. No profile of you.

What it does today

Already working. In daily use.

01
Hold, speak, release
One key. Your words are typed where your cursor already is. No window to switch to, nothing to paste.
02
Recognised on your Mac
Speech recognition runs on-device with Apple's speech model. We measured the app and the recognition process while dictating: zero network connections.
03
Audio is never saved
Sound goes from the microphone to the recogniser and is gone. No recording is ever written to disk.
04
Nothing is lost
Dictaquill checks that your text actually arrived. If an app refuses it, the text waits on your clipboard and in your local history.
05
Stops at password fields
When a password field is active, dictation pauses. Nothing is typed and nothing is saved.
06
History you control
Kept on your Mac for 90 days, or not at all. Delete one entry or everything, whenever you like.
07
Your names, spelled your way
A personal correction list fixes the names and terms a general recogniser gets wrong.
08
Stays off your other devices
Text placed on the clipboard is marked local-only, so it does not sync to your iPhone or iPad.

Runs on Mac today (macOS 26 or later); a Windows version is planned. In early access: there is no public download yet. Neither a lawyer nor a therapist? Write to hello@dictaquill.com and say what you would use it for.