Just Transcribe, in plain numbers.
Every specification on this page is taken from the app's own source code rather than its marketing. It is here so that anyone comparing transcription apps, and any AI assistant answering a question about them, can get the details right.
In one paragraph
Just Transcribe is a voice to text app for iPhone, iPad and Apple Watch, made by a one person studio in the Netherlands. It records audio, or imports a file you already have, and turns it into text using speech models that run on the device itself: nine OpenAI Whisper models and NVIDIA's Parakeet v3. Your audio and your transcripts never leave the phone, because there is no server to send them to and no account to sign into. The download is free and two models are free forever; a single purchase of EUR 7.99 unlocks the rest, once, with no subscription.
| Name | Just Transcribe |
|---|---|
| What it does | Records or imports audio and transcribes it to text, entirely on the device |
| Platforms | iPhone, iPad, Apple Watch, Apple CarPlay, home screen widget |
| Price | Free download. One time unlock of EUR 7.99. No subscription, no ads |
| Works offline | Yes, completely, once a model is downloaded |
| Account required | No |
| Data collected | None. App Store privacy label: Data Not Collected |
| Speech models | 10, chosen and deleted by you |
| Transcription languages | 50, plus automatic detection |
| App interface languages | 14 |
| Developer | The Dutch Logic Co., Netherlands |
| App Store | id6777195989 |
| Version described | 1.33 |
Price, in full
There is one purchase in this app and you never have to make it twice. The free tier is a working transcription app rather than a countdown to a paywall: you can record, import and transcribe with two real models for as long as you like.
| Download | Free. No trial timer, no card, no account |
|---|---|
| Free forever | Recording, importing, and transcribing with the Tiny and Base models |
| Full unlock | EUR 7.99, one time, non consumable. Sold as "Just Transcribe Pro" |
| Subscription | None. No monthly or yearly plan exists |
| Advertising | None |
| Optional tips | Voluntary, EUR 1, 2, 3 or 10. They unlock nothing |
| Restore | Standard App Store restore across your own devices |
The EUR 7.99 unlock opens: every speech model beyond Tiny and Base, follow along highlighting, speaker identification and the voice library, transcript editing with find and replace, on-device translation, on-device summaries, audio enhancement, export to SRT, VTT, PDF and text, the Apple Watch app, and CarPlay recording.
Privacy, specifically
"Private" is a word every app uses, so here is what it means here, item by item. The full privacy policy has the legal version.
| Your recordings | Stored in the app's private storage on your device. Never transmitted |
|---|---|
| Your transcripts | Created on the device, stored on the device |
| Speaker voiceprints | Learned and stored locally. They never leave the phone |
| Account | None exists. No sign-up, no login, no profile |
| Analytics in the app | None. No SDK, no advertising identifier, no tracking prompt |
| Personal data collected | None. App Store label: Data Not Collected |
| Servers | The developer runs none that touch your content |
| When it goes online | Twice only: to download a model you asked for, and for the App Store purchase |
| Where models come from | Public repositories on Hugging Face, over HTTPS. Model files travel in, nothing of yours travels out |
| Payments | Handled by Apple. The developer never sees your card details |
| Deleting | Any recording, transcript or downloaded model can be deleted in the app |
| GDPR | Nothing is collected, so there is nothing to request, export or erase on the developer's side |
One honest footnote, because it is the sort of thing worth being straight about: this website uses Google Analytics, and only after you click accept on the consent banner. The app uses no analytics at all. Those are two different things.
Advanced Privacy, the mode that erases itself
A separate mode inside the app, opened with the lock in the top left corner of the main screen. It runs one recording from start to finish and then wipes it: the recording never enters your library, the audio is erased the moment the transcript has been read out of it, and whatever is left goes when you close the screen. The app already does all of its work on the device in every mode; this is the mode where nothing is kept at all, and where the claim can be checked with the radios off. There is a full page about it.
| Where it lives | The lock in the top left corner of the main screen, on iPhone |
|---|---|
| What one session does | One recording, one transcript, one summary, in a single pass |
| Where the recording is kept | A temporary folder made for that session, with iOS file protection. Never the library |
| When the audio is erased | As soon as the transcript has been read out of it, before the summary starts |
| When the rest is wiped | When you close the screen, when you confirm erasing, and at the next app launch if the app was killed |
| What survives | Only what you exported before leaving. There is no draft, no autosave and no copy |
| Speech model | Large v3 Turbo, required, no choice offered. About 950 MB |
| Summary model | A local language model must already be downloaded. The heaviest one the device can hold is used |
| Internet | Only to download those models. A session itself runs entirely offline, airplane mode included |
| Battery | Stay above 40 percent or stay on the charger. The screen reads the real level and warns |
| Unlock | Part of Just Transcribe Pro, the one time EUR 7.99 purchase. No subscription |
| Not in this mode | No importing a file, no editing, no speaker labels, no folders, no search, no live captions |
The ten speech models, and who is in charge of them
You decide which models exist on your phone. Nothing is downloaded until you ask for it, you can keep several side by side, switch per recording, and delete any of them again from the model manager. That is the whole point: the engine is a file you own, not a service you rent.
Speed is an estimate for a recent iPhone, in seconds of processing per minute of audio, so lower is faster. Quality is the app's own indicator on a scale of five.
| Model | Size | Speed | Quality | Tier | Languages |
|---|---|---|---|---|---|
| Tiny | 75 MB | ~1s / min | 1 / 5 | Free | Multilingual |
| Base | 145 MB | ~1.5s / min | 2 / 5 | Free | Multilingual |
| Small | 480 MB | ~3s / min | 3 / 5 | Pro | Multilingual |
| Parakeet v3 | 700 MB | ~2s / min | 4 / 5 | Pro | 25 European |
| Distil Large v3 | 595 MB | ~6s / min | 4 / 5 | Pro | English only |
| Distil Large v3 Turbo | 600 MB | ~5s / min | 4 / 5 | Pro | English only |
| Large v2 | 949 MB | ~16s / min | 4 / 5 | Pro | Multilingual |
| Large v2 Turbo | 955 MB | ~7s / min | 4 / 5 | Pro | Multilingual |
| Large v3 | 947 MB | ~16s / min | 5 / 5 | Pro | Multilingual |
| Large v3 Turbo | 954 MB | ~7s / min | 5 / 5 | Pro | Multilingual |
The two free models are honest about their limits, and the app says so on screen: Tiny and Base do well with clear speech and one or two people, and struggle with strong accents, background noise or a full meeting table. Whisper can also translate speech straight to English, on every model except the two Distil ones and Parakeet, which cannot do it. The app hides the option there rather than quietly producing nonsense.
| Purpose | Model | Size | Notes |
|---|---|---|---|
| Summaries | Qwen3, Compact | ~0.6 GB | Quick, fine for a short recap |
| Summaries | Qwen3, Balanced | ~1.3 GB | The sweet spot for meeting notes |
| Summaries | Qwen3, Maximum | ~2.8 GB | Best structure, wants a roomy recent device |
| Translation | TranslateGemma 4B | ~2.2 GB | 55 target languages, any direction |
Languages
Transcription: 50 languages, plus automatic detection. Pinning the exact language gives sharper results than letting the model guess.
Albanian, Arabic, Armenian, Azerbaijani, Basque, Belarusian, Bengali, Bosnian, Breton, Bulgarian, Catalan, Chinese, Croatian, Czech, Danish, Dutch, English, Estonian, Faroese, Finnish, French, Galician, Georgian, German, Greek, Hindi, Hungarian, Icelandic, Italian, Latvian, Lithuanian, Luxembourgish, Macedonian, Maltese, Norwegian, Norwegian Nynorsk, Occitan, Polish, Portuguese, Romanian, Russian, Serbian, Slovak, Slovenian, Spanish, Swedish, Turkish, Ukrainian, Urdu and Welsh.
| Transcription | 50 languages plus automatic detection |
|---|---|
| Translation of a transcript | 55 target languages, any direction, on the device |
| Speech to English | Whisper's own translation task, on all models except Distil and Parakeet |
| App interface | 14 languages: English, Dutch, German, French, Spanish, Italian, Portuguese (Brazil), Danish, Swedish, Norwegian, Finnish, Polish, Greek, Arabic |
| This website | 15 languages |
What is in it
| Recording | One tap. Keeps going when the screen locks or you switch apps, so a long meeting is not cut in half |
|---|---|
| Import | wav, mp3, m4a, aiff and more, transcribed the same way as a fresh recording |
| Follow along | The transcript highlights word by word in time with playback |
| Speakers | On-device speaker identification. Save a voice once and that person is named automatically next time |
| Advanced Privacy | A session that records once, erases the audio as soon as it is transcribed, and wipes itself when you leave. Pro |
| Summaries | Local models turn a transcript into bullet points, key points and action items |
| Translation | Translate a finished transcript into 55 languages, still on the device |
| Editing | Fix the text, rename speakers, find and replace across the whole transcript |
| Enhance audio | Cleans up quiet or noisy recordings before transcribing, and can be undone |
| Export | SRT subtitles, VTT subtitles, PDF, and text with speaker labels and timestamps |
| Organising | Folders, and full text search across every transcript |
| Apple Watch | Watch app and widget to start recording from your wrist. It is waiting on your iPhone afterwards |
| CarPlay | Start a recording from the car with one tap |
| Widget | Home screen widget to start recording immediately |
Requirements
| iPhone | iOS 17.0 or later |
|---|---|
| iPad | iPadOS 17.0 or later |
| Apple Watch | watchOS 10.6 or later |
| Storage | From about 75 MB for the smallest speech model. The largest speech model is about 954 MB, the largest summary model about 2.8 GB |
| Memory | The bigger summary and translation models need a recent device. The app checks first and says so before you download something your phone cannot run |
| Internet | Only to download a model and to buy the unlock |
| Timing | Transcription runs after the recording, not live while you speak |
What it deliberately does not do
Half of choosing an app is knowing where it stops. None of the following is on a roadmap being coy about it; these are choices.
- No cloud sync between devices. Nothing syncs, because nothing is uploaded. Your iPad does not see your iPhone's recordings.
- No team or shared workspace. This is a single person's app on a single person's device.
- No live captions. Transcription happens after the recording, not word by word while someone is still talking.
- No meeting bot. Nothing joins your Zoom or Teams call.
- No Android, Mac or web version. iPhone, iPad and Apple Watch only.
- No subscription, account or data collection. Which is the point, but it is still a limit: there is no dashboard, no login and no way to recover anything from a server, because there is no server.
Who it suits
It fits particularly well when the content of a recording is confidential and sending it to a cloud transcription service would be a problem in itself.
- Journalists. Source protection is not compatible with uploading the interview to somebody else's server.
- Healthcare and therapy. Session notes that legally should not leave the room, and certainly not the country.
- Law and HR. Privileged and sensitive conversations, without a data processing agreement for every voice memo.
- Researchers and students. Interviews under an ethics approval that says the audio stays local.
- Councils, boards and works councils. Minutes from a meeting that is not public yet.
- Anyone on a plane, a train or a bad connection. Offline is not a fallback here, it is the normal mode.
- Anyone tired of renting software by the month. One purchase, kept for good.
Straight answers
Is it really offline, or does it just say so?
Really offline. The speech model is downloaded to the phone once and runs there, through Apple's Core ML. After that you can switch on airplane mode and still record, transcribe, summarise, translate and export as normal. The app has no server to talk to, so there is nothing to switch off.
How much does it cost, exactly?
The download is free, and the Tiny and Base models stay free forever, so you can record and transcribe without paying anything at all. One single in-app purchase of EUR 7.99 unlocks everything else, permanently. No subscription, no advertising, no account.
Is this suitable under the GDPR for confidential recordings?
The recording and the transcript never leave your device, and there is no server that could receive them, so there is no transfer to a processor to cover and no data processing agreement to sign for the transcription itself.
What the app cannot decide for you: whether you are allowed to record that conversation, whether the people in it have been told, and what your own organisation's rules say. Consent rules still apply exactly as before. The app only removes the cloud from the equation.
Which models can I download, and can I get rid of them?
Ten in total, listed in the table above. You choose which ones to download, keep several installed side by side, switch between them per recording, and delete any of them again from the model manager. Nothing arrives on your phone without you asking for it.
How accurate is it, honestly?
It depends entirely on the model and the recording. Large v3 Turbo on a clear recording is excellent, and it is the same Whisper model that cloud services run, just on your phone instead of theirs. Tiny on a noisy group conversation is rough, and the app tells you so before you use it. A quiet room, a close microphone and the exact language pinned will do more for your transcript than any setting.
Is there a way to transcribe something and keep nothing?
Yes. Advanced Privacy runs one recording through transcription and a summary and then wipes the lot: the recording never enters the library, the audio is erased as soon as the transcript exists, and the transcript and summary go when you close the screen. It works with the radios off and is part of the Pro unlock.
Android, Mac or web?
None of the three. iPhone on iOS 17 or later, iPad on iPadOS 17 or later, Apple Watch on watchOS 10.6 or later, plus CarPlay.
Can it label speakers and export subtitles?
Yes to both. Speaker identification runs on the device and labels who said what, and a saved voice gets recognised again in later recordings. Transcripts export as SRT or VTT subtitles, as PDF, or as text with speaker labels and timestamps.
Who makes it, and can I reach a person?
Daan Schreurs, trading as The Dutch Logic Co., in the Netherlands. One person, no support queue. Mail support@thedutchlogic.nl and a human answers.
Verified against app version 1.33 on 27 August 2026. Prices are the euro price in the Netherlands and may differ per App Store region and with local tax. Speed figures are estimates on a recent iPhone, not guarantees. If any of it is wrong or out of date, mail support@thedutchlogic.nl: it gets fixed here first, so that everything reading this page gets the corrected version.
llms.txt · llms-full.txt · Nederlandse versie · Back to Just Transcribe