Offline transcription on iPhone: what your phone already does (2026)

Disclosure: this is written by Saural Audio, who make DiPLO Pocket, one of the apps listed below. We are saying so at the top rather than in small print at the bottom. We have tried to write a comparison that survives being read by a competitor.

On Android, the hard part is finding anything that transcribes offline at all. On iPhone it is the opposite, and almost nobody tells you: your phone already does it, for free, without a connection.

Since iOS 18, Voice Memos transcribes on the device. No app, no account, no upload. If that is all you need, you can stop reading after the next section and we will have done our job.

What follows is the rest of the answer: what the built-in one does not do, how to check where any app’s audio actually goes, and which apps are worth installing for the cases Apple did not cover.

On Android instead? We wrote the same comparison for Android, where the picture is completely different: Offline transcription on Android.

---

Start here: your iPhone already transcribes

Open Voice Memos, tap a recording, tap the ⋯ button, choose View Transcript. That is it.

It needs iPhone 12 or later and iOS 18 or newer, and it runs on the device — the audio is not sent anywhere. You can prove it in ten seconds: record something, turn on aeroplane mode, and ask for the transcript. It appears.

On iPhone 15 Pro and later you also get Apple Intelligence summaries of the transcript. On everything else you get the transcript, which is the part that matters.

For occasional notes, a lecture you want to skim, or a phone call you recorded and need the gist of, this is genuinely enough. It is free, it is already installed, and it is private. Most articles about “offline transcription on iPhone” never mention it, because a free feature you already own does not pay anyone’s affiliate commission.

---

What the built-in one does not do

Four things, and whether they matter depends entirely on what you record.

It speaks about thirteen languages. English, Spanish, French, German, Italian, Portuguese, Chinese, Cantonese, Japanese, Korean, Arabic, Russian and Turkish, with regional variants. That is a lot of the world, but it is not Catalan, Dutch, Polish, Swedish, Greek, Czech, Romanian, Finnish, Hungarian or the rest of Europe. If you work in one of those, Voice Memos will not help you at all.

It does not tell speakers apart. A transcript of an interview comes out as one undifferentiated block of text. For a conversation between two people that is a lot of work to untangle afterwards.

It does not take the recording seriously. Voice Memos records compressed by default — there is a lossless option buried in its settings, and almost nobody knows it is there. There is no noise handling on the way in, and no way to mark a moment while you are recording. Which brings us to the thing most comparisons skip entirely, below.

It only knows about what it recorded. A voice note somebody sent you, an old file, the audio of a video — none of that is transcribable in Voice Memos, because it is not in Voice Memos.

---

Where your audio can actually go

If you are reading this for privacy rather than convenience, this is the section that matters. There are three places a recording can end up, and an app’s marketing will not always tell you which one you are in.

1. Nowhere — it stays on the phone. The app runs a speech model on the device. Nothing leaves. Voice Memos works this way, and so do the Whisper-based apps below.

2. Apple’s servers. This is the one people walk into without noticing. Apple’s speech recognition has both an on-device mode and a server mode, and an app that uses the system recogniser gets to choose. Voice Memos transcripts are on-device. A third-party dictation app built on the same framework may not be, depending on how its developer configured it and on your device and language. The developer can honestly call it “offline” and still, on your particular handset, be making a round trip.

3. A third-party transcription API. Plenty of apps are a thin front end over someone else’s speech service. That is a perfectly legitimate way to build an app, and the good ones say so. It is only a problem when you assumed otherwise.

How to check, rather than trust

Read the App Privacy section on the App Store listing. Every developer has to declare what their app collects and links to you, and Apple publishes that answer on the listing itself, under “App Privacy”. It is the developer’s own statement, so it is not proof — but it is a statement they are accountable for, and it is a great deal more specific than the marketing copy. Look for whether Audio or User Content appears at all.

Then do the aeroplane-mode test anyway. Declarations describe intent; aeroplane mode describes behaviour. Record, disconnect, transcribe. Anything that stalls needed the network, whatever the listing said.

For the record, and so you can check it the same way you check everyone else: DiPLO’s App Privacy entry says Data Not Collected. There are no accounts, no analytics, no telemetry and no crash reporting. The only outbound connection the app ever makes is downloading the speech model itself, once, over HTTPS, and the Wi-Fi transfer feature serves your library from the phone to your own browser on your own network — there is no server of ours in the middle to be breached or subpoenaed.

The cloud services are not hiding any of this either. Otter, Notta and Transkriptor tell you plainly that they process on their servers; that is the product. The ones worth being careful about are the apps in the middle, where “offline” is doing work in the marketing that it does not quite do in the code.

---

What most comparisons miss: the transcript is only half the job

Every list of transcription apps compares accuracy, languages and price, and then stops. Which is odd, because the single biggest factor in how accurate your transcript comes out is not the model at all. It is the recording.

No speech model recovers words that were never captured cleanly. A phone lying on a café table, picking up the espresso machine and the table next to you, will defeat Whisper and Parakeet equally. The apps that treat recording as a formality — a red button and nothing else — are quietly handing you a worse transcript than the same model would produce from better audio.

There is a second thing this hides, and it is specific to iPhone. Almost every offline transcription app on iOS is file-first: you record somewhere else, then import the file and wait. That is fine for a lecture you already have. It is a poor fit for walking out of an interview wanting the text.

So when you compare, look at what happens before the model runs:

• Can it record at all, or does it only import?
• Can it record uncompressed, or only a lossy format?
• Is there any noise handling on the way in?
• Can you mark a moment while you are recording, or only hunt for it afterwards?
• Where does the audio file end up, and can you get it out?

---

The real options

DiPLO is ours, and it is listed in the position it earns: the only one built around the recording. Everything below says where each of the others is the better answer, including where we are not.

Voice Memos (Apple)

Covered above, and it deserves the top of the table. Free, on-device, already installed, thirteen languages, no speaker labels, and nothing at all for the recording side. If your needs are occasional, this is the answer and everything below is a waste of your money.

Whisper Transcription

The iPhone and iPad version of MacWhisper, from Jordi Bruin. It runs Whisper locally through whisper.cpp, so nothing is uploaded, and it is the natural choice if you already use MacWhisper on a Mac and want the same thing in your pocket. It is file-first: its job starts once you have the audio.

Good for: people who live in MacWhisper and work from files.
Not for: recording. It is not a recorder.

Aiko

From Sindre Sorhus, a one-time purchase, and the widest language coverage here: Whisper’s full 100 languages, running entirely on the device. Import from Voice Memos, from Files, or from your photo library, and it transcribes locally and exports text or subtitles.

Two things to know: it does not record, and it does not transcribe live — you bring it a finished file. And because of how iOS handles background work, you have to leave it open while it runs.

Good for: any language outside the thirteen Apple covers and the twenty-five we do. If you need Hindi, Thai, Vietnamese, Hebrew or Ukrainian, this is your answer, not ours.
Not for: recording, or transcribing as you go.

Whisper Notes

The same idea at a lower price, a one-off purchase rather than a subscription, running Whisper on the device across Apple hardware. Worth a look if Aiko’s price is the thing stopping you and you do not need a hundred languages.

Good for: cheap, local, file-based transcription.
Not for: the recording side, again.

DiPLO Pocket

Ours. It is the only one here built by audio engineers rather than app developers, and that shows up in what it does with the recording rather than what it does with the text.

It records properly. WAV at 48 kHz and 24/32-bit if you want the master, MP3 if you want the space. Three processors tuned for speech run on the way in — a noise reducer, a voice cleanup stage and a de-esser — which is the difference between a usable transcript of a noisy café interview and a page of guesses. You can drop markers while recording, so the moment someone says the thing you came for is findable later without scrubbing.

Then the transcription. It uses Parakeet, from NVIDIA, not Whisper — faster on phone hardware, and it detects the language itself across 25 European languages with no menu to set. Punctuation and casing come out clean, every line is timestamped, and tapping a line jumps the audio to that moment. Speaker separation is in beta. You can search inside every transcript you have ever made.

It also works on audio you did not record. Import a file from the phone — an old recording, a lecture someone sent you, even a video, in which case it takes the audio track and leaves the rest. Or skip the file picker entirely: DiPLO appears in the share sheet of every other app, so a voice note that lands in your messaging app goes straight into DiPLO from the message itself, several at once if you want. That four-minute voice note you cannot listen to right now becomes something you can read in a few seconds. WAV and MP3 come across untouched, markers and all; anything else is converted on the way in.

And when you want it off the phone, it serves your whole library to your computer’s browser over your own Wi-Fi, behind a PIN — no cloud, no account, no upload.

Free to use, with a premium tier. iPhone and Android — App Store, Google Play.

Good for: interviews, lectures, meetings and field recording — anywhere the audio is worth keeping, not just the words.
Not for: three things, and we would rather say them than have you find out. It does not do automatic summaries. The 25 languages are European: if you need Hindi, Arabic, Chinese or Japanese, use something Whisper-based instead. And if all you ever want is the occasional transcript of something you recorded yourself, Voice Memos is already on your phone and it is free.

What is not offline

Otter, Notta, Transkriptor and most of the names you already know upload your audio to a server. They are good at what they do — collaboration, integrations, summaries — and they make sense if that is what you need. But if you came here because you want the audio to stay on the phone, they are not the answer, however often the word offline appears on their listing.

---

The part nobody mentions before you install: the first download

Any app that really transcribes on-device has to download a model, and these are hundreds of megabytes. DiPLO’s is about 416 MB; Whisper-based apps vary with the model size they picked, anywhere from around 80 MB to over 1 GB.

Which means three things:

• The first run needs internet, even though nothing after it does.
• It takes up space, permanently.
• The first transcription looks broken. This is the single biggest cause of people giving up: they think the app has frozen when what it is doing is downloading. Let it finish, on Wi-Fi, with the screen on.

Voice Memos is the exception. Apple ships its model with the system, which is part of why it is the right place to start.

And once a model is there, transcribing takes time. A phone is not a server. As a rough guide, expect a fraction of the audio’s duration — and on older hardware, considerably more.

---

So which one?

You want the occasional transcript of something you recorded yourself → Voice Memos. It is already on your phone, it is free, it is on-device, and you do not need us.

And the rest, honestly:

• You record things that matter — interviews, lectures, meetings, fieldwork — and you want the audio to be as good as the transcript → DiPLO Pocket. It is the only one here that treats the recording as the job and the text as what you get out of it.
• You need a language Apple does not cover → Aiko, or another Whisper-based app. A hundred languages beats our twenty-five and Apple’s thirteen.
• You mostly want to read voice notes other people send you → DiPLO, for the share sheet: the file never has to touch a file picker. Aiko will import them too if you would rather go via Files.
• You already use MacWhisper on a Mac → Whisper Transcription, for the same thing on the phone.
• You work in a team and the audio can leave the phone → Otter or Notta, and skip everything above.

And whatever you pick: aeroplane mode, then test it. It is the only way to find out where your audio actually ends up.