What can Aurora do today, and what can't it?

As of 19 October 2026, the iPhone beta records, transcribes live, separates speakers, names them when the conversation says who they are, and writes summaries and action items on the device, with plain-text export and opt-in iCloud sync of conversation text (never the audio). In development: grounded answers from Ask Aurora, recognizing a voice in a later meeting, search across conversations, and the Mac app. It suits you if you record on an iPhone in the room; it does not if you need a Mac app now, or want a meeting bot that joins the call.

Aurora at a glance

Aurora at a glance: each row restates a line further down this page, with its status label where the row is a capability.
Question	Aurora
Where the speech pipeline runs	On the iPhone itself: recording, live transcription, speaker separation, summaries and action items. Available in beta.
Whether anything joins the call	Nothing joins your call as a participant. Aurora records from the room, through the microphone of the iPhone you are holding. Available in beta.
Account with Aurora	There is no account with us. The beta installs through Apple's TestFlight app with your Apple Account.
Working offline	Recording, transcription, speaker separation and summaries need no connection once the speech models are installed. Available in beta.
What uses the network	Aurora is local-first, not network-free: the paths that exist are named under Data leaving the device on the Privacy Notice.
Status	Aurora is in a private beta on TestFlight, free while it lasts. Pricing is not decided.

The shape of it

Aurora is a speech workspace for iPhone. You press record in the room you are already in. Nothing joins your call as a participant, and no recording is uploaded to be transcribed. The words arrive as they are spoken, each voice in its own lane. When you stop, a language model on the device writes the session up, and you can ask it what was said.

The home page runs the interface itself, as a replica, so you can watch that happen. Aurora for iPhone is the same product from the other side: the workflow step by step, what a phone needs, and what the build you can install today cannot do.

Two labels are used across this site, and each means one thing. Available in beta is in the TestFlight build and works. In development is still being built and is not promised by a date; some of it is not in the build yet. There is no third label, and no capability on this site goes without one.

Available in beta

Recording. Aurora listens through the microphone of the iPhone you are holding, in the room or beside the laptop. No bot joins the meeting, and the audio is written to the phone that heard it.
Live transcription. Speech becomes text while people are still talking. A word is shown as confirmed only once two consecutive decodes agree on it; the unconfirmed tail stays on screen, dimmed, rather than being hidden (the rules are written up here).
Speaker separation. Aurora tells the people in the room apart as it listens and gives each one a lane. It is not perfect, and we publish what it scores rather than describing it as solved.
Speaker names the conversation gives. When someone says who they are, a model on the device reads that out of the transcript and puts the name on the lane; otherwise the lanes stay Speaker 1, Speaker 2. The name is stored with that session, and there is no control for typing one in yourself.
Summaries and action items. When you stop, a language model on the device writes the title, the summary and the follow-ups it heard. Nothing is sent away to produce them.
Working offline. Recording, transcription, speaker separation and summaries need no connection once the speech models are installed. The models are fetched on first launch, and again only when one is added or changes.
Your calendar, read on the device. Aurora can show the next event on your calendar. Aurora reads that event through the system's own calendar interface, on the phone, and uses no network to do it.
Plain-text export. A transcript leaves as plain text, to the app or place you choose. Plain text is the only export format Aurora has.
Languages other than English. Aurora transcribes conversations in other languages as well as English.
The second pass over a finished transcript. After a session ends Aurora re-reads it. That pass can revise words you watched confirm, and it can relabel a run of speech from one speaker to another.
Sessions much longer than an hour. Aurora records and transcribes sessions much longer than an hour.
Conversation sync through your iCloud. Turn on Sync conversations with iCloud and the text of your conversations (transcripts, notes, summaries, chats and folders) syncs through your own private iCloud between your devices where it is on. It starts off. The audio does not sync; it stays on the device that recorded it.

In development

Still being built, and not promised by a date. Described here so that nobody has to discover it by looking for it.

Grounded answers from Ask Aurora. The Ask Aurora chat is in the build. An answer that cites the moment in this session's transcript it came from, or says the evidence is not there instead of guessing, is in development.
Recognizing a known voice in a later meeting. A name is stored with the session it was found in, not learned as a voiceprint, so the next conversation starts from unnamed lanes again.
Searching across conversations. Search inside a session exists; search across your library does not.
The Mac app. A macOS target exists in the app's source and there is no release, so everything on this site describes the iPhone.

Where the line is

Aurora's whole speech pipeline runs on the iPhone: capture, transcription, speaker separation, summaries, action items and Ask Aurora. Recordings are not uploaded to be transcribed, because no server exists that would receive them.

We will not tell you that nothing ever leaves your phone. Aurora is local-first, not network-free: the app downloads its models, checks for a newer build, and asks our subscription provider for your subscription status when the main screen opens. On the free tier the app also tells Aurora's own free-minutes service how many minutes you record, so they can be counted against a monthly allowance; the service keeps a pseudonym of your App Store record and never receives audio, transcripts or titles, and a subscriber's app never contacts it. Your settings follow your own iCloud account, conversation text syncs through it if you turn that on, usage metrics are sent only if you agree, and a diagnostic report goes when you send one. A diagnostic report opens with its session-details switch already on (turn it off and the conversation stays where it is), while the recording has its own switch, which starts off.

Data leaving the device on the Privacy Notice carries the complete list: every path, what each one sends, to whom, and what it keeps. That table lives there and only there, so there is one copy of it to keep true.

What Aurora does not claim

That nothing ever leaves your device. Aurora is local-first, and the paths that exist are named on the Privacy Notice.
That transcription or speaker separation is perfect. The measurements are published, including the corpus where roughly two words in three carried the wrong speaker label.
That a diagnostic report excludes your content by default. Session details start switched on; only the recording starts off.
That a speaker named in one conversation is recognized in your next meeting.
A price. Aurora is free while the TestFlight beta lasts, pricing is not decided, and no number on this site is one.

Getting it

Aurora is in a private beta on TestFlight, free while it lasts. Invites go out in waves to people on the waitlist; there is no account with us.

Join the waitlist

How invites work, what you need and what the beta covers is a page of its own, and Aurora for iPhone walks through a session as the app runs it.

What Aurora does: features of an on-device AI note-taker