Nothing is uploaded
Transcription and summarisation run on the phone. The recording engine has no HTTP client compiled into it, so there is no code path by which a conversation could be sent anywhere.
iOS and Android
Remember what was decided.
Brink Debrief records a conversation, timestamps every line, pins your notes at the moment you took them, and writes the summary, with every model running on the phone. Nothing is uploaded. There’s no subscription.
Built on Brink Compute, private AI that runs on your own hardware.
The best meeting recorders send your meetings somewhere else.
Almost every tool in this category uploads the audio, transcribes it on a server and bills you monthly for the privilege. That’s a reasonable trade for some conversations. It’s the wrong trade for a salary review, a diagnosis, a term sheet, or a source who agreed to talk to you and not to a vendor.
Encrypted where it sits
Everything lands in a SQLCipher database whose 256-bit key is held by the iOS Keychain or wrapped by a non-exportable Android Keystore key — never stored beside the data it protects.
Works with no signal
A basement meeting room, a flight, a client site with guest wifi you would rather not join. The models are already on the device, so none of it matters.
No subscription
There is no server to pay for, so there is no per-minute meter. Download the models once and the app keeps working whether or not anyone is still selling it.
A transcript you can actually use afterwards.
Notes you pin land in the timeline at the moment you took them, not in a separate list you have to reconcile later. Speaker labels are honest: the app says unknown rather than guessing.
No app can record both sides of a normal phone call.
iOS exposes no way to tap the other person’s audio, and during a call the telephony stack owns the microphone outright. Android gates the same thing behind a permission no app on the store can hold. The earbuds that manage it do the recording in firmware, on the far side of that boundary, not in their app. Anyone telling you otherwise is describing hardware, or is wrong.
| Route | Picks up | Both sides |
|---|---|---|
| Bluetooth headset | You, clearly | No |
| Phone microphone | The room | No |
| Speakerphone | Both sides | Yes |
| External recorder | Both sides | Yes |
So: put the call on speaker and Brink Debrief gets both voices, because the other person is genuinely audible in the room. Wear a headset and it gets you. The app knows which of these happened and says so on the recording, rather than letting you find out later that half the conversation was never there.
Five stages, none of them a server.
- 1
Capture
Audio from the phone mic, a Bluetooth headset or the loudspeaker, normalised to 16 kHz mono whatever the hardware hands over.
- 2
Detect speech
A voice detector with a noise floor that adapts to the room decides what is speech, so the expensive stage only ever sees words.
- 3
Transcribe
Listen turns each utterance into text on the device, and every line is stamped against the wall clock.
- 4
Attribute
Two-cluster speaker attribution separates you from them by pitch. It never claims an identity, and answers “unknown” when the evidence is thin.
- 5
Summarise
Recap writes the headline, the bullets, the action items and the decisions. The app always names the engine that wrote them.
Worth knowing
Speaker attribution answers me, them or unknown, and it really does return unknown when two voices are too alike or there hasn’t been enough speech yet. It’s a two-cluster problem by design, because the only question you ever ask of a transcript is which side said it. It never claims to know a name.
From 30 MB to 1 GB, downloaded once.
Downloading the weights is the only thing the app ever uses the network for, and only from the addresses it shows you. If you’d rather it never made a request at all, import the files yourself and it never will.
Listen
181 MBThe default. Keeps up with models many times its size on English, and stays quiet during silence instead of inventing words.
Listen Nano
30 MBThe smallest English transcriber worth using, for older phones or tight storage.
Listen Wide
56 MBDetects the language being spoken and transcribes it, across dozens of languages.
Listen Wide Nano
30 MBThe same language detection and coverage as Listen Wide, at the smallest size.
Recap
1.0 GBWrites the headline, the key points, the action items and the decisions. One and a half billion parameters, compressed to fit a phone's memory budget.
Recap Nano
644 MBA lighter summariser for phones short on memory. Good at the headline and key points; less reliable at picking out actions and decisions.
It works before you download anything
With no model installed the app still records, timestamps, pins your notes and writes an extractive summary with no weights at all, and it always names the engine that wrote it, so you’re never guessing which one you’re reading.
Keep the conversation. Keep it yours.
iOS and Android. Tell us what you record and we’ll get you in early.