Dictate live and watch the words land as you speak — correct yourself out loud, call your normals by voice — and RadTypist turns it into a finished radiology report in your exact .docx layout, in seconds. No typing, no reformatting, no typing pool. Your first 5 reports are free.
Most radiology dictation software stops at a transcript — a wall of raw text you still have to structure, format and correct before it's a usable report. RadTypist is different. It's AI dictation for radiologists that produces the finished report: your dictation goes in, and a clean radiology report comes out in your own template, with findings and conclusion already structured. It follows you the way a good typist would — your corrections, your commands, your normals — and does the typing and the formatting, so the only step left is your review.
Press Dictate or F9 and talk the way you already do — natural speech, medical terminology, even code-switched language. Words appear as you speak. Or upload a recording (WAV, MP3, M4A and FLAC). No patient identifiers needed.
Your draft is rewritten into a clean, structured radiology report — findings and conclusion, in your exact template layout — in about 30 seconds.
Preview the finished report in your browser, with changes highlighted against your draft, then download a real Word document to sign off. No retyping, no reformatting.
Ordinary dictation software gives you raw text you still have to structure and format. RadTypist returns a complete, properly-formatted radiology report.
“Medial, sorry, lateral.” “Scratch that.” “Correction, change 8 to 6 mm.” Correct yourself naturally — no fixed command phrases to memorise, and the slip never reaches the draft.
Say “call template knee normal, but small joint effusion” and the report keeps your normal wording around the change. Insert one with Ctrl+K, too.
Dictate in up to three languages in one breath — English with Cantonese or Mandarin, for example — and get the report in the language you choose.
Sections, headings and numbering come out in your own template — and on Plus, each study is routed to the right template by keyword.
No typing the report yourself, and no waiting on a typing pool. Dictate, review, sign off — the turnaround is seconds, not hours.
Whether you type your own reports or hand dictation to a typing pool, the report still costs you time — typing, chasing typos, and reformatting to match your layout. RadTypist removes that step entirely. Dictate the study, watch it land in the draft, and a formatted report is ready in about 30 seconds, tuned for radiology terminology and mixed-language dictation, with no typos to chase. Radiology typing becomes review-and-sign-off.
Try it free| RadTypist | Traditional dictation software | Medical typist | |
|---|---|---|---|
| Output | Finished, formatted report | Raw transcript text | Typed report (hours later) |
| Live words as you speak | |||
| Natural spoken corrections | Fixed commands | — | |
| Normals by voice, with changes | Fixed macros | Manual | |
| In your .docx template | Manual | ||
| Structures findings & conclusion | Manual | ||
| Mixed-language dictation | Varies | — | |
| Turnaround | ~30 seconds | Real-time, then reformat | Hours to next day |
| Cost per report | From ~53¢ | Licence + your time | Typist salary |
Radiology dictation software converts a radiologist's spoken dictation into a written report. Traditional tools stop at a raw transcript. RadTypist goes further: it structures and formats the dictation into a finished radiology report in your exact .docx layout, ready for review and sign-off.
Generic dictation and speech-to-text apps give you a live transcript that you still have to structure, format and correct, using fixed command phrases. RadTypist also shows your words live, but understands natural corrections (“medial, sorry, lateral”), calls your normals by voice, and returns a complete, formatted report — findings and conclusion in your template — so there's nothing to reformat.
Yes. Save your normals as text templates and call them while you dictate — “call template knee normal, but the ACL is completely torn”. The report uses the template's wording with your changes applied.
For most reporting workflows, yes. You dictate, RadTypist produces the formatted report in seconds, and you review and sign off — no typing pool and no overnight turnaround.
You can mix up to three languages in one dictation and choose the language the report is written in, including Traditional or Simplified Chinese. English, Cantonese and Mandarin are the most tested.
Yes. On the Plus plan you upload your own .docx templates and route each study to the right one by keyword, so every report comes out in the format your practice already uses.
Yes — WAV, MP3, M4A and FLAC. An upload is transcribed into the same draft you dictate into, so you can mix both on one report.
A report counts toward your month from its first dictation, upload or Generate — typing a draft is free. Each report includes up to 20 minutes of audio and 5 generates; past that, we ask before counting it as another report.
RadTypist is for de-identified dictation — don’t include patient identifiers. Live dictation audio streams to the speech recogniser and is never stored by RadTypist; uploaded recordings are deleted as soon as they’re transcribed. Your drafts and reports stay in your account until you delete them. Data is encrypted in transit and at rest.