A second brain that listens for you
Most of what moves your work forward is said out loud and then lost: the decision, the reason behind it, who promised what, the small thing a client mentioned once. Losing it costs you twice, once when it is forgotten and again in the follow-up call to piece it back together. Listen hears it once and keeps it: what you owe and what you are owed, where you left off with each person, and why a decision was made. Every answer opens the moment it was said, so you can act on it instead of asking again.
This looks like an Intel Mac, and Listen will not run on it.
Listen transcribes on your own machine, and that needs the Neural Engine Apple introduced with the M1 in late 2020. There is no Intel version, and there is no version that would work.
Open the Apple menu and choose About This Mac. If it says Chip rather than Processor, this guess is wrong and you can download Listen as normal.
The problem
The promise somebody made at the end of a call. Why the team rejected the first plan. The detail a client mentioned three months ago. The exact words behind a decision everybody now disagrees about. These are the things that make your next move better, and they are the first things ordinary notes lose.
How it works
Three ordinary things, and the middle one is the part nothing else does.
What it remembers
What was said becomes what happens next: the promises to keep, where you left off with each person, what changed this week, and an answer to anything you ask in Chat, each one opening the moment it was said.
Follow-through
“I’ll send you the numbers by Friday.” Promises are made in passing and kept on memory, which is why so many quietly aren’t. Listen keeps them in two columns, what you owe and what you are owed, each in the words somebody actually said.
A page per person
What they are working on, what they asked you for, what changed since last time. Each line carries the recording, the speaker and when it was said, and pressing it opens the sentence itself.
This week
A deck of cards over the week's conversations: the people and notes that arrived, what was promised, and who you are seeing next. Every card carries something to do.
The galaxy
Recordings, notes, people and your conversations with Listen, with a line wherever the library already records a relationship. Search, and the picture narrows to what matches and what it connects to.
Chat
Chat with one conversation or all of them. Every claim comes back with a numbered reference that opens the recording at the moment it came from, and if a model answers without reading anything, Listen says so.
claude mcp add listen -- /usr/local/bin/listen mcpWhat you do with it
“Catch me up before I speak to Maria again.”
What you last agreed, what she is waiting on, and the thing she mentioned in passing that you meant to follow up. Each line opens the conversation it came from.
“Why did we decide against annual pricing?”
The reasons, in the words they were argued in, with the date and the meeting. Not a summary somebody wrote afterwards.
“Draft the brief using what customers actually said.”
Your agent reads the relevant conversations over MCP and writes from them, instead of asking you to paste a folder of transcripts into the prompt.
Underneath
A memory is only worth as much as what it was built from. Recording, transcription, the voices and the search over them are free, for ever, with no meeting count and no trial clock.
Record
Your microphone on one track, everything your Mac plays on the other. Nothing joins the call, so it works on WhatsApp and FaceTime as well as it does on Zoom, Meet and Teams. You do not have to remember to start it: Listen spots the call, begins recording, and only then asks whether you want it.
Transcribe
Transcribing happens on your Mac's own chip, about 240 times faster than real time on an M4 Max. Play a meeting back and the transcript follows along, sentence by sentence, so you can find the bit you half remember without listening to the rest.
Speakers
Listen works out who spoke and puts names on the turns. Tell it who someone is once, and it recognises them in the next meeting they turn up in. On a call it never has to guess at your own voice.
Notes
Write your own notes while the meeting is still running, which is when they're worth the most: “we should upsell them” is the kind of thing no transcript will ever hold. Ask an agent for a summary and it writes a separate one. It can read yours. It cannot change them.
Dictate
Press fn + left shift wherever you're typing, say what you want written, and press it again. The words land where the cursor is, in an email, in Slack, in a search bar, and on the clipboard as well.
Your devices
Turn on sync and your transcripts, notes, people and tags follow you between Macs, through your own private iCloud rather than anybody's server. Listen seals all of it on the device first, with a key Apple never holds. There's nothing to pair and no code to scan.
Works with
Listen records the audio your Mac is already playing, so it needs nothing from the app on the other end. That includes the ones no notetaker bot can reach.
The iPhone app is in TestFlight. It records the conversations that happen in a room rather than on a call. On supported phones with iOS 26 or later it transcribes and separates voices, and writes into the same memory: a name your Mac already knows can appear with the turns. The Mac keeps the heavier transcription model, call capture and MCP server. See what works on iPhone →
Trust
There is no Listen server, so there is nothing to breach and nothing to hand over. Your meetings are saved on your own computer, and the recording, the transcript and the names on it are all made there. No account. The app sends anonymous usage counts, which you can turn off in Settings, and every one of them is listed here. The features that use an AI model, such as asking questions, profiles and promises, send the text of a conversation, never the audio, and only once you switch them on.
Three things can send anything out, and each is off until you turn it on: keeping your library in step across your own devices, putting a question to a hosted model, and building the memory, which reads passages to whichever model you point it at. Listen seals anything that travels before it leaves the device, with a key we never hold, so there is nothing readable at the far end. Point all three at a model running on your own Mac and none of it leaves the machine at all.
None of which has to be taken on trust. Listen ships a machine-readable list of every connection it is allowed to make, inside the app, which firewall tools like Little Snitch read straight out of it. Point one at Listen and watch. What runs where sets out each connection and how to check it yourself, and there are answers ready for a privacy or HIPAA review.
Somewhere with rules about this? Listen can be locked down centrally through the same device profiles an IT team already uses: sync off, questions answered only by a model on the machine, no dictation history, backups pointed wherever policy says. Deploying under HIPAA or GDPR has the detail.
Where it sits
Categories rather than named products, because naming one dates this table the week they ship something. Check any row against the tool you actually use.
| A meeting summariser | A notes app | Memory inside one AI | Listen | |
|---|---|---|---|---|
| Starts from real conversations | Yes | Only what you type | Only what you tell it | Yes |
| Carries people and projects forward | Rarely | By hand | Inside that one vendor | Yes |
| Links a claim to what was said | Sometimes | Sometimes | Rarely | Yes, every one |
| You can correct what it learned | Limited | Yes | Limited | Yes |
| Readable by the AI you choose | Limited | Varies | Usually not | In the app, and over MCP |
| Runs without a vendor server | No | Varies | No | Yes |
Who it is for
A Zoom call, a WhatsApp call on your Mac, a coffee recorded on your iPhone, a voice memo on the walk home. One a week or ten a day, Listen keeps them in a library that belongs to you rather than to a team workspace, and turns what was said into what you do next. Some of the people it suits best:
From people using it
I’ve tested many similar apps out there, and Listen is finally the one that stuck. I love owning my data, and the dictation is my daily driver.
Daniel AndradeFounder, VitalTrends
Get Listen
Download it, record one conversation, name the people in it, then ask what was said. The memory grows from there. Recording is free for ever; what it costs has the rest. Apple silicon, macOS 14 or later, and the speech model is about 2.5 GB the first time you run it.