--- title: "TechVoice — AI voice dictation that learns your vocabulary" description: "Dictate or upload audio: TechVoice transcribes live, corrects with your specialist vocabulary and remembers your fixes. AI dictation powered by Mistral AI." url: "https://techvoice.fr/en/" language: "en" --- # Voice dictation that learns your specialist vocabulary Speak or upload a recording: TechVoice transcribes as you talk, fixes the terminology of your field and remembers every correction. Read it over, and it’s filed. ## TechVoice at a glance - **What it is** — Online voice dictation software that transcribes your voice, corrects the terms of your profession and remembers your corrections. - **Who it’s for** — Doctors and surgeons, lawyers and legal professionals, finance and real estate professionals: any profession with a technical vocabulary. - **Language** — French and English, your choice in the app. Spanish, German and Dutch are in preparation. - **Technology** — Voxtral speech recognition, plus correction by a language model, both from Mistral AI. - **Data** — Transcribed and corrected by Mistral AI, hosted by Scaleway, in France. Audio is not kept. - **Devices** — Computer, tablet or phone, in the browser (Chrome or Safari), with nothing to install. - **Recordings** — Audio files up to 60 minutes and 100 MB: m4a, mp3, wav, ogg, flac… - **Pricing** — 100 free points, about 100 minutes of dictation, then €14 or €40 per month. ## How it works Three simple steps, and a memory that grows with every dictation. 1. **Dictate or upload** — Speak into your computer’s or phone’s microphone, or drop in a recording made elsewhere, up to 60 minutes long. 2. **TechVoice transcribes and corrects** — Text appears as you speak. When you stop, it is corrected within seconds using your vocabulary: technical terms, proper names, acronyms. 3. **You review, it learns** — Fix a misheard word: the correction is remembered, and TechVoice applies it to your next dictations. ## A memory you can see and correct Everything TechVoice learns is set out in plain view in the Memory tab: you stay in control of what it remembers. - **Your documents** — Upload sample reports or letters: TechVoice keeps the terms, not the text. - **Your field** — Enter your field: TechVoice looks up its terms in the scientific literature, in the language you dictate in. - **Your corrections** — Every word you fix becomes a “misheard → correct” pair, applied to your next dictations. ## Everything you need to write with your voice Voice dictation software built for the texts that matter, from the first word to the filed note. - **Live dictation** — Text appears while you speak, then is corrected when you stop. If the connection drops, everything transcribed so far is kept and dictation resumes. - **Upload recordings** — Voice memo, meeting, recorded consultation: drop in the file, up to 60 minutes and 100 MB. A 30-minute meeting is transcribed in about a minute. - **Your vocabulary** — Enter your field and upload a few sample documents (PDF, Word): TechVoice picks out your terminology. The text of the documents is not kept. - **Correction memory** — Every word you correct becomes a rule for your next dictations. Everything TechVoice learns stays in plain view, and you can edit or delete it. - **One-click formatting** — Turn a dictation into an email, a short message or polished prose: verbal tics disappear, nothing is invented, and anything missing is left in square brackets. - **Neatly filed notes** — Your dictations become notes, organised in folders and found in an instant with search. - **Quick actions on your notes** — Summary, structured report, to-do list, email or your own instruction: a draft to review, in one click, without touching the note. Handled by Claude, from Anthropic, and only when you run them. ## Why not use general-purpose dictation? The dictation built into your phone or word processor handles everyday language well. Your profession demands more. | | Keyboard | General-purpose dictation | TechVoice | |---|---|---|---| | Speed | About 35 to 40 words per minute | As fast as you speak | As fast as you speak, with the text shown live | | Your specialist terms | Accurate, but you have to type them | Often misrecognised | Corrected with your vocabulary | | Learns from your corrections | Not applicable | Rarely | Yes, with every edit | | Fixing misheard words | Not applicable | Rarely tailored to your profession | Strictly limited and visible: nothing is reworded | | Where your text goes | It stays on your device | Depends on the provider | To Mistral AI and Scaleway, in France | ## For professions where every term counts TechVoice adapts to the vocabulary of your field, whatever it may be. - **Doctors and surgeons** — Medical dictation for consultation notes, operative reports and letters: conditions, techniques and devices spelt correctly, without patient-identifiable data. [Find out more](https://techvoice.fr/en/medical-dictation) - **Lawyers and legal professionals** — Client meeting notes, case summaries and first drafts of letters, with the exact legal terminology. [Find out more](https://techvoice.fr/en/legal-dictation) - **Finance and wealth management** — Client meeting reports and analysis notes: products, acronyms and regulatory references. - **Real estate** — Viewings, inventory reports, mandate notes: dictated on site, filed before you are back at the office. - **And your profession** — Engineering, consulting, research… Enter your field and TechVoice learns its terminology. ## True to what you say Your name goes on every report. TechVoice corrects recognition errors, never what you actually said. - **No rewording** — Correction only touches misheard words. If it strays too far from what you said, TechVoice keeps the recognised text as it was. - **Visible corrections** — One click shows what the correction changed in the recognised text, so you know exactly what you are reviewing. - **A memory that belongs to you** — Vocabulary, documents and learned corrections are all in plain view, and you can edit or delete them at any time. - **Nothing you dictate is lost** — Network drop or service outage: text already transcribed is kept. If the correction fails, you keep the raw transcript. ## Processed in France, by European providers Your voice and your texts are transcribed and corrected by Mistral AI, and hosted by Scaleway, in France. - **Audio not kept** — Your audio is used for transcription; after that, TechVoice does not keep it. - **Documents read, then forgotten** — From the documents you upload, TechVoice keeps only the terms it extracts. - **No ads, no tracking** — No analytics, no advertising cookies: only the ones you need to sign in. - **Your data, yours to delete** — Deleting your account erases your notes, your vocabulary and your corrections; encrypted backups expire within 14 days. One exception: quick actions, when you run them, send the note’s text to Anthropic (Claude) in the United States, under standard contractual clauses. Nothing is sent without your click. **TechVoice does not hold France’s certification for hosting health data (HDS).** Do not dictate anything that could identify a patient: no name, no date of birth, no record number. Full details, provider by provider, are on our [Privacy](https://techvoice.fr/confidentialite) page (in French). ## Simple pricing Start for free, no credit card required. Subscribe once TechVoice has become part of your working day. - **Free** — €0 — 100 free points, one time only, ≈ 100 minutes of dictation - **Essentiel** — €14 / month — 1,000 points per month, ≈ 16 hours of dictation per month - **Ultra** — €40 / month — 4,000 points per month, ≈ 66 hours of dictation per month Prices incl. VAT. About 1 point per minute of dictation, transcription and correction included; other features use points depending on how you use them. At each renewal, your balance is reset to your plan’s allowance: unused points do not roll over. No commitment: cancel at any time. Plans are intended for professionals: see our [terms of sale](https://techvoice.fr/cgv) (in French). ## Frequently asked questions ### Which languages does TechVoice work in? In French and in English: dictation, correction and interface. The flag at the top of the app switches language at any time. Our accuracy measurements cover French. Spanish, German and Dutch are in preparation. ### Is TechVoice free? You start for free: signing up gives you 100 points, enough for about 100 minutes of dictation, with no credit card required. After that, there are two subscriptions with no commitment: Essentiel at €14 and Ultra at €40 a month. ### How is it different from the dictation on my phone or in my word processor? General-purpose dictation handles everyday language well, but stumbles over the terms of your profession and rarely learns from your corrections. TechVoice corrects every dictation using your vocabulary and remembers every fix, without rewording what you say. ### Do I need to install any software? No. TechVoice runs in your browser, Chrome or Safari, on a computer or a phone. All you need is a microphone. ### Do I need an internet connection? Yes: transcription and correction run on Mistral AI’s servers. If the connection drops during a dictation, the text already transcribed is kept. ### Which AI models does TechVoice use? Transcription uses Voxtral, Mistral AI’s family of speech recognition models, and correction uses a Mistral AI language model. We explain this choice and share our measurements in [our hands-on review of Voxtral](https://techvoice.fr/en/blog/mistral-voxtral-speech-recognition). ### How does TechVoice learn my vocabulary? From three sources: the field you enter, the sample documents you upload (only the terms are kept) and, above all, your corrections. Every word you fix becomes a “misheard → correct” pair, applied to your next dictations. You can view and edit all of it in the Memory tab. ### Can automatic correction change the meaning of what I said? It is designed not to. It only fixes recognition errors, and an automatic check rejects it if it strays too far from the dictated text, taking word order into account: a misplaced “not” changes everything. You can see what was corrected, and you always review a text before using it. ### Can I dictate patient data? Not at the moment. TechVoice does not hold France’s certification for hosting health data (HDS): do not dictate names, dates of birth, record numbers or any other information that could identify a patient. This is a commitment set out in our [terms of sale](https://techvoice.fr/cgv) (in French). ### Where is my data processed? Your voice and your texts are transcribed and corrected by Mistral AI, and hosted by Scaleway, in France. Audio is not kept after transcription. Sign-in is handled by Clerk and payment by Stripe, with possible transfers of your email address and name outside the European Union. Everything is detailed on our [Privacy](https://techvoice.fr/confidentialite) page (in French). ### What happens to my notes when I use quick actions? The note’s text and your instruction are sent to Anthropic (Claude), in the United States, under standard contractual clauses, and only when you click. Anthropic does not train its models on this content. The note itself is left unchanged: you get a draft to review. ### What happens if the connection drops during a dictation? Text already transcribed is kept and TechVoice reconnects to carry on. If the correction fails, you keep the raw transcript, clearly marked as such. ### Can I upload recordings made elsewhere? Yes: an audio file of up to 60 minutes and 100 MB (m4a, mp3, wav, ogg, flac…), such as a voice memo from your phone or a meeting recording. It is transcribed and corrected just like a dictation. ### How much does a dictation cost? About 1 point per minute, transcription and correction included. The 100 free points you get when you sign up cover about 100 minutes; paid plans renew your balance every month. See [pricing](https://techvoice.fr/en/#pricing). ### Can I cancel at any time? Yes, from your account and at no cost: your subscription ends at the close of the period you have paid for, and your remaining points can be used until then. ## Solutions - [Medical dictation: your reports dictated, your terms spelt right](https://techvoice.fr/en/medical-dictation) — Medical dictation software for reports and letters: TechVoice transcribes live, corrects your specialty’s terms and remembers your fixes. Free trial. - [Legal dictation: notes, summaries and letters dictated in the language of the law](https://techvoice.fr/en/legal-dictation) — Legal dictation for client notes, case summaries and first drafts: TechVoice transcribes, corrects legal terms and remembers your fixes. Free trial. - [Transcribe audio recordings to text, with your own vocabulary](https://techvoice.fr/en/audio-transcription) — 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. ## From the blog - [Dictating instead of typing: how much time do you really save?](https://techvoice.fr/en/blog/voice-dictation-time-savings) — 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. - [Voxtral, Mistral AI’s speech recognition: how good is it for professional dictation?](https://techvoice.fr/en/blog/mistral-voxtral-speech-recognition) — Models, languages, pricing, open weights: all about Voxtral, Mistral AI’s speech recognition, and what we measured when using it for professional dictation. - [AI voice dictation: how it learns your specialist vocabulary](https://techvoice.fr/en/blog/how-ai-dictation-works) — Speech recognition, AI correction, correction memory: how modern voice dictation works, and why it stumbles over the technical terms of your profession.