Medical dictation: your reports dictated, your terms spelt right
Cloud-based medical dictation software for doctors: dictate reports and letters in your browser; TechVoice corrects specialty terms and learns your fixes.
Dentists
Clinical notes, surgical notes, referral letters, treatment plan notes: dictate them between two patients. TechVoice writes procedures, materials and conditions the way you do, and remembers every correction.
100 free points, about 100 minutes of dictation · no credit card required
A clinical note is only useful if every term in it is right. General-purpose voice dictation recognises everyday conversation very well, but it stumbles over the very stuff of dentistry: procedures, materials, periodontal conditions, eponyms, device references. TechVoice was designed for this problem: writing a profession’s vocabulary the way the practitioner writes it, and remembering their corrections. It works in French and in English.
At every moment, a speech recognition model picks the most likely words, based on everything it heard during training. “Peri-implantitis”, “root planing” or “post and core” are rare in that material, so when the sound is ambiguous, an everyday word wins. A note in which this happens has to be fixed by hand, term after term, and it is that correction time that makes people give up on dictation.
Tooth numbers (16, 36, 47…) are dictated as numbers. Review them like everything else: a wrong tooth does not stand out the way a misspelt term does.
On top of speech recognition, TechVoice adds a correction step that knows your terms, fed by three sources:
What we have measured, and its limits: on our French corpus of orthopaedic reports, the text displayed during dictation gets about 25% of specialist terms wrong; after correction with the practitioner’s vocabulary, about 5%. These figures come from synthetic voices and are optimistic. Our other trials cover ten medical specialties (cardiology, neurology, ophthalmology…), also in French; none covers dentistry yet, and we do not present these figures as valid for it, nor for English. The details are in our article on how AI voice dictation works.
TechVoice’s correction only touches misheard words: it adds nothing, removes nothing and rewords nothing. An automatic check compares the corrected text with the recognised text, word by word and in order; if too much has changed, the raw transcript is kept. “No mobility” is not “mobility”: one misplaced negation is enough to change a note.
Every correction stays visible: one click shows what was changed. You always review a text before using it, and you remain its author.
You can also upload a voice memo recorded elsewhere: TechVoice transcribes and corrects it in the same way, up to 60 minutes long.
TechVoice does not hold HDS certification, France’s certification for hosting health data. So do not dictate anything that could identify a patient: no name, no date of birth, no record number. The simplest way to work: dictate the clinical content in TechVoice, then add the patient’s identity in your practice management software.
Your voice and your texts are transcribed and corrected by Mistral AI and hosted by Scaleway, in France. Audio is not kept after transcription. Full details are on our Privacy page (in French).
With no measurement on dental vocabulary yet, the only judgement that counts is yours, on a week of real documents: you get free points when you sign up, with no credit card required. For medical dictation in general, see our dedicated page; to estimate how much time you could save, our time-savings calculation, document by document.
It learns it from you, in French or in English: enter dentistry or your field (periodontics, implantology, endodontics, orthodontics…) when you sign up, upload a few sample notes or letters, and correct whatever needs correcting. Every correction is remembered for your next dictations.
Not yet shown. Our measurements cover orthopaedic reports and a corpus of ten medical specialties, in French and with synthetic voices; none covers dental vocabulary. The most reliable test is your own documents.
No. TechVoice does not hold France’s certification for hosting health data (HDS): do not dictate names, dates of birth or record numbers. Dictate the clinical content, then add the patient’s identity in your practice management software.
Copy the corrected text and paste it into the patient record or your word processor, with no stray formatting. Your dictations also stay filed in your notes.
Cloud-based medical dictation software for doctors: dictate reports and letters in your browser; TechVoice corrects specialty terms and learns your fixes.
Legal dictation for client notes, case summaries and first drafts: TechVoice transcribes, corrects legal terms and remembers your fixes. Free trial.
Upload a voice memo or meeting recording: TechVoice transcribes it to text, with the terms of your profession. 30 minutes of audio in about a minute.
Dragon Medical vs standard dictation software: Dragon Medical One, Heidi, Augnito, Windows, Mac and TechVoice compared on vocabulary, price and hosting.
Dictate text on your computer with nothing to install: Dictate in Word, Windows voice typing (Windows + H) and Mac Dictation, punctuation commands and limits.
Speaking is three times faster than typing, but the real gain is won or lost at review. A worked calculation and cited studies to save time on your reports.
100 free points, no credit card required. Your vocabulary starts taking shape from your very first dictation.
Try it free