Dictum — a free companion for PowerScribe®

If you use PowerScribe, you should be using this.

Dictate with the plugin — a modern offline engine that hears you the same way every time — and the open PowerScribe report receives every word in real-time sync. Templates fill by voice, autocomplete learns how you write, and nothing ever leaves your workstation.

Free during the pilot · 64-bit Windows 10/11 · no admin rights needed

🎤  
Dictum ● Recording (F9)
You dictate here — press F9 and talk: fields fill, picklists answer to your voice, measurements come out formatted
Nuance PowerScribe One
File Edit View Insert Format Tools Speech Help
✕ Close✎ Draft✓ Sign AutoText ▾ BIU 00:00 - 00:00
Report –
User: ABAJIAN | Drafts: 7 | Overreader: None selected
PowerScribe receives the report with its fields still live — nothing about your sign-off workflow changes

Simulated demonstration. Sync runs both ways — edits in either window mirror to the other, and writing into PowerScribe only happens when you say so.

Sound familiar?

Built against PowerScribe's oldest complaints

“I dictated the exact same sentence I say twenty times a day. Different text. Again.”

Say it the same, get the same

PowerScribe's recognizer leans on a per-user voice profile that drifts, degrades, and eventually needs retraining. Dictum uses a modern transformer speech model (Parakeet-TDT) with deterministic decoding: no profile to train, no profile to corrupt — the same utterance produces the same text, with punctuation and measurements formatted the way radiologists write them. It decodes a five-second utterance in about half a second on an ordinary CPU.

“AutoText was clearly designed by someone who never dictated a case.”

Templates that fill themselves out

Import your own PowerScribe AutoText in one click — or start from the built-in template library. Every field is tab-navigable, picklists pop up with the default preselected, and voice commands drive it all: say “next field”, speak an option, keep dictating. Finished reports paste back into PowerScribe with the fields still live.

“It still doesn't know the words I use every single day.”

Autocomplete that learns you

The app quietly learns your vocabulary and phrasing from the reports you sign — locally, on disk you control. Type three letters and your own sentence finishes itself. A curated radiology corpus covers the rest, ranked by the section you're writing in.

Live mirror

The open report mirrors into the plugin in real time — fields, lists, formatting — and stays read-only unless you say otherwise. Dictation in PowerScribe always wins.

Crash-proof drafts

Work is autosaved every few seconds with full field fidelity. Kill the app, lose power, reboot — your draft comes back with tab navigation intact.

Made for reading rooms

A warm, low-glare theme that sits politely next to your PACS monitors, resizable, with your font and size remembered.

0

bytes of PHI leave your machine. No cloud, no login, no telemetry. The speech model, your templates, and everything the app learns live on your disk.

2

files to install. Unzip, double-click, done. No installer, no admin rights, no IT ticket.

1

workflow — yours. PowerScribe remains the system of record. The plugin mirrors, assists, and only writes back when you tell it to.

Get Dictum

Version 1.0.1 · ~100 MB · 64-bit Windows 10/11

Download Dictum.exe

SHA-256: published in downloads/latest.json

Windows may show a “Windows protected your PC” screen while our code-signing certificate is pending — click More info → Run anyway. On first launch Dictum offers a one-time download of its on-device AI models (~3 GB) — that's the speech and impression AI living entirely on your workstation, so nothing you dictate ever leaves it.

  1. Run Dictum.exe — no installer, no unzipping. It finds your open PowerScribe report by itself.
  2. Accept the one-time model download (~3 GB) when prompted, and let it finish in the background.
  3. Dictate. Press F9 and talk; F10 drafts your impression. Updates arrive automatically.