Radiology dictation · end-to-end encrypted

Dictation that can keep a secret.

RadDictate turns your speech into clean findings and conclusions inside any web-based RIS or HIS — quietly proofreads the report for the slips fatigue makes, and stores your history so encrypted that even we can't read it.

Developed by a practicing radiologist   No install on hospital servers   Works on hospital networks

01

Workflow

Press record. Speak. It lands at your cursor.

No copy-paste, no separate window to babysit. RadDictate lives inside the system you already report in.

1 —

Record where you work

A floating pill follows you around your RIS in Chrome. Or dictate on your phone while the report fills in on the PC — the phone is just a better microphone.

2 —

Speak like you report

The AI turns natural dictation into clean report language, following your templates and house style — not a generic transcript.

3 —

Text lands precisely

Findings go to the findings field, the conclusion to the conclusion field, inserted exactly where your cursor was — mid-sentence if that's where you clicked.

Chrome extension — any web HIS Mobile app — standalone or remote mic Desktop — with a fully offline option
02

Second read

Every report gets a second read.

Dictation slips are quiet: right becomes left, the sigmoid becomes the transverse, and nobody notices until it matters. RadDictate reads the finished report against itself and flags internal contradictions — it never edits silently.

Findings — as dictated
There is an irregular spiculated mass in the right breast at the 10 o'clock position, 21 × 18 mm, with posterior acoustic shadowing and adjacent architectural distortion.
Conclusion — as dictated
BI-RADS 5 lesion in the left breast at 10 o'clock. Ultrasound-guided core biopsy is recommended.
Laterality mismatch — findings describe the right breast, conclusion says left. Marked for radiologist review. Nothing was changed.

Catches what fatigue misses

Laterality, anatomic sites, contradicting statements between findings and conclusion — the unintended mistakes of a long reporting list.

Flags. Never rewrites.

A flagged report is still your report. The AI marks the discrepancy and steps back; the radiologist who signs it stays in charge.

Tuned to your protocols

Organizations can add their own checks, templates and reporting style — the second read learns your department's rules, not someone else's.

03

Zero knowledge

We store your reports. We cannot read them.

Most medical software promises not to look at your data. RadDictate is built so that looking is impossible: reports are encrypted on your device with a key derived from your password — a key we never see.

On your device

Your password is stretched into an encryption key
PBKDF2 · 600,000 rounds

Sealed locally

Each report is sealed before it leaves the browser
AES-256-GCM

What our servers hold

Ciphertext. That's all.

gK9x2mQvT7…Lr4nWc8pZaE1oDh5UyBf3TksMxIjR0eNqVu6bA…HdSw==
In transit

Everything — including your audio — travels over TLS encryption, end to end, on every client.

In processing

Speech-to-text must momentarily process audio. It runs on Google Vertex AI with zero data retention configured — audio is never stored, never used for training.

In time

History auto-deletes after 14 days by default — set 1–60 days or keep it forever. Old reports don't pile up waiting to leak.

04

Everything else

Small features that respect a radiologist's day.

Templates & house style

Your report structures, your phrasing. The AI formats to your templates — normal studies read the way you'd have typed them.

Phone as microphone

Reporting on a workstation with no mic — or one you don't trust? Dictate into your phone; the finished report appears in the browser on the PC, encrypted the whole way.

History that follows you

Reports sync across your extension, phone and desktop — end-to-end encrypted — so the study you reported on the go is at your workstation before you are.

Fully offline option

For departments that cannot send audio out at all, our on-premise desktop engine transcribes locally. No internet. No cloud. Nothing leaves the room.

Built for real networks

Hospital proxies, shared IPs, thin bandwidth — RadDictate is engineered for the networks radiology actually runs on, not a Silicon Valley office.

Accounts that behave

Per-device sign-in limits and usage quotas keep group licences honest — a feature your administrator will appreciate.

05

For organizations

Your department. Your rules.

  • Per-organization customization — templates, reporting style, and consistency checks tuned to your protocols.
  • Admin console — usage by radiologist and by day, device management, minutes quotas.
  • Invite-based onboarding — add a radiologist by email; they're dictating in five minutes, on a trial you control.

Why this exists

"The dictation systems I admired come at prices radiologists in my part of the world simply cannot afford. I refused to accept that good reporting tools are a rich-hospital privilege — so I built one that matches them, exceeds them where it matters, and costs a fraction as much."

— The founding radiologist · OUI Technologies, Pakistan

Questions

Asked and answered.

How do I get access?
RadDictate is currently invite-based. Request a free trial — we approve requests within 24 hours and you'll receive a sign-up invitation by email. No credit card, full features.
What happens if I forget my password?
Here's the honest answer: your password derives the only key that can decrypt your report history. If you reset it via email, the old history becomes permanently unreadable — by you and by us. That's not a limitation we forgot to fix; it's what zero-knowledge means. Changing your password normally (while signed in) keeps everything.
Can I include patient information?
RadDictate is designed for de-identified report content — dictate the findings, not the demographics. If you attach a report label for your own reference, it's end-to-end encrypted like everything else. See the privacy policy for the full picture.
Which systems does it work with?
Any web-based RIS/HIS you can open in Chrome — the extension inserts text into the fields you already use, no integration project required. For non-web systems there's the desktop app, and the fully offline engine for air-gapped departments.
Is my audio kept anywhere?
Not by us. Audio is encrypted in transit, transcribed, and gone — the AI provider is configured for zero data retention. Optional local backups on your own device are under your control and never uploaded.
What does it cost?
A fraction of legacy enterprise dictation — see pricing. Individual radiologists and small teleradiology groups are exactly who we built this for.

14 days · full features · no card

Dictate your next list with it.