For therapists in private practice
Finish your notes out loud. Never record a session.
Dictaquill listens only while you hold a key, after your client has left. Your spoken summary is typed into your notes, and neither the audio nor the text leaves your Mac.
No account · no cloud
Mac today · Windows planned
Client reported improved sleep this week and practised the breathing exercise twice. Still avoiding the commute. We agreed to continue the exposure hierarchy next session.
network connections: 0audio saved: none
Zero bytes uploadedRecognition runs on your computer.
Zero audio files savedSound is processed and gone.
Zero accounts to createNo login. No profile of you.
Why this exists
AI note-takers want to sit in the room. Many clinicians, and many clients, would rather they didn’t.
A scribe that records the session needs a consent conversation, and clients may hold back once they know a machine is listening.
Dictating your own summary afterwards avoids the question. No client voice is ever captured, and what you say goes no further than your own computer.
What it does today
Already working. In daily use.
- Hold, speak, release
- One key. Your words are typed where your cursor already is. No window to switch to, nothing to paste.
- 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.
- Audio is never saved
- Sound goes from the microphone to the recogniser and is gone. No recording is ever written to disk.
- 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.
- Stops at password fields
- When a password field is active, dictation pauses. Nothing is typed and nothing is saved.
- History you control
- Kept on your Mac for 90 days, or not at all. Delete one entry or everything, whenever you like.
- Your names, spelled your way
- A personal correction list fixes the names and terms a general recogniser gets wrong.
- Stays off your other devices
- Text placed on the clipboard is marked local-only, so it does not sync to your iPhone or iPad.
NowMac. macOS 26 or later, built and tested on Apple Silicon.
PlannedWindows. Same approach: on your computer, nothing uploaded. Tell us in the form.
In development for therapists
Not built yet. You decide the order.
Everything below is planned, none of it is finished, and we would rather say so. Tick what matters in the form and that is what gets built first.
- 01SOAP, DAP and BIRP formatting, on your MacSpeak freely; Dictaquill sorts what you said into your note’s sections. It never adds a clinical judgment you did not speak.
- 02Clinical vocabulary it actually knowsModalities, diagnoses and medication names recognised correctly the first time.
- 03Your own note templateHeadings and order the way your practice already writes them.
- 04Learns from your correctionsFix a word once in your note and Dictaquill remembers, on your Mac only.
- 05Verified in browser-based practice softwareTested typing into the note fields of the tools therapists use.
You say
“client reported improved sleep and practised the breathing exercise twice my assessment is that anxiety is decreasing but avoidance persists plan is to continue the exposure hierarchy”
It writes
Data: Client reported improved sleep and practised the breathing exercise twice.
Assessment: Anxiety is decreasing but avoidance persists.
Plan: Continue the exposure hierarchy.
Plain answers
Questions worth asking.
Is it HIPAA compliant?
We do not make that claim, and would rather give you facts. Dictaquill never receives your audio or your text. There is no Dictaquill server in the path. What you dictate exists only on your Mac and in the app you dictate into. Whether that meets your obligations is a judgment for you and your compliance advisor.
Does it record my sessions?
No. The microphone opens only while you hold the key and closes when you let go, with a visible indicator the whole time. It is built for the minutes after a session, not the session itself.
Will it write my note for me?
No. Today it types exactly what you say. In development: sorting what you said into SOAP, DAP or BIRP sections on your Mac. It will not add clinical judgments you did not speak, and you review every note.
Does it work with my practice software?
Dictaquill types into whichever field has your cursor, including fields in a web browser. It is in daily use in Chrome; other browsers are being verified. Tell us in the form what you use.
Is anything sent to a server?
No. Recognition runs on your Mac and Dictaquill has no server that receives audio or text. When the paid version ships it will make two kinds of connection: a licence check and an update check. Neither carries anything you said, and both will be listed plainly in the app and the privacy policy.
Is my audio sent to Apple?
Dictaquill uses Apple's on-device speech model. On macOS 26.6 we inspected both the app and Apple's recognition process during dictation and found zero open network connections.
What do I need to run it?
Today, a Mac running macOS 26 or later; it is built and tested on Apple Silicon. A Windows version is planned, built the same way: recognition on your own computer, nothing uploaded. The form asks which you need, so we know what to build next.
What will it cost?
Not decided. The form asks what you would expect to pay, including “I wouldn’t pay for this”. An honest answer is the most useful thing you can give us.
Who makes it?
An independent developer. Joining early access puts you in direct contact with the person writing the code.