Can I get a live summary during a meeting on my Mac?
Yes, but not from macOS itself. A Mac ships both halves of a live summary separately: Live Captions shows a live transcript of speech from any app, processed on the device, and Apple Intelligence can summarize a Notes recording when you ask, which in practice means after the call. Zoom, Teams, Meet, and Webex add their own AI, but it's on demand and gated by the host's plan and admin. For a summary that updates while the meeting is happening, in any app, use a real-time summarizer. Canary is a real-time, bot-free meeting summarizer. It captures your computer's system audio (no bot in the call, no plugin) and shows a live, multi-resolution rolling summary — from what's being said right now to the whole call — so you can catch up the instant your name is called. On a Mac it runs from the menu bar as a small always-on-top panel beside your call, on macOS 14 or later.
Last updated September 13, 2026
Yes, but not from macOS, and not from most of the notetakers you can install on a Mac. The Mac already ships both halves of a live summary, separately: Live Captions can put every word of a call on screen as it’s spoken, from any app, and Apple Intelligence can summarize a recording once it’s over. What nothing built in does is the thing in between: tell you, mid-call, what the last five minutes were about. That’s the gap a real-time meeting summarizer fills.
Your Mac already has both halves, separately
The live half is a transcript. In recent versions of macOS, Live Captions (System Settings → Accessibility) captions speech from any app as it plays: Zoom, Teams, a Meet tab in Safari, a video. It’s processed on the device, it’s a genuinely good accessibility feature, and it’s a useful free option in a call held in your second language. It needs an Apple silicon Mac and is offered only in some languages and regions, so check your version. What it shows is words: a caption stream moving at the speed people talk. That’s a live transcript, not a live summary. When you’ve drifted for three minutes, reading three minutes of captions while new ones arrive is the same problem again, now with your eyes.
The summary half arrives after. Apple Intelligence can summarize the transcript of an Apple Notes recording when you ask. That’s on supported devices and languages, and the feature set moves between releases. You ask once, after you stop, and get one answer at one resolution. And at the time of writing, Notes on the Mac records from a microphone rather than capturing the call’s audio, so on a headphones call it hears only you. Canary vs Apple Notes walks through why.
So macOS gives you words now, or meaning later. A live summary is meaning now: the conversation condensed continuously while it’s still happening, at more than one zoom level. That’s the one combination nothing on the Mac ships.
What each option shows you during the call
Here’s everything you can run on a Mac, scored on the one question this page is about: what’s on your screen while the meeting is still going?
| Option on your Mac | What you see during the call | Live summary? | The catch |
|---|---|---|---|
| macOS Live Captions | Word-for-word captions of any app’s audio, processed on-device | No, it’s a live transcript | Apple silicon only; some languages and regions; moves at speaking pace |
| Apple Notes + Apple Intelligence | A transcript filling in as it records | No, it’s a summary when you ask, after | Records through the mic (at the time of writing); on headphones it hears only you |
| Zoom / Teams / Meet / Webex built-in AI | Captions, plus an on-demand catch-up on some | Only on request, one answer at a time | The host’s plan and admin decide; one platform each |
| Notetaker bots (Otter, Fireflies, Fathom) | A live transcript or highlight buttons, depending on the tool | No, the summary comes after the call | A bot joins the participant list; your Mac isn’t doing the listening |
| ChatGPT record mode | A recording in progress | No, notes arrive once you stop | Built for the note afterward |
| Bot-free Mac notepads (Granola, Jamie) | Your own typed notes, if you take any | No, the AI note is written after the call | Built for the document, not the moment |
| Canary | A rolling summary at four horizons: now, 2 min, 5 min, full call | Yes, continuously | Processed in the cloud; hears audio, not the screen; English-first |
Two rows deserve a second look.
The meeting platforms’ own AI has become the closest built-in thing. Webex’s Catch Me Up and Meet’s join-late summary are genuinely useful. But they’re on demand: you have to notice you’re lost, stop, and ask, in the exact moment you’re trying to recover. And whether they exist on a given call is decided by the host’s plan and admin, not by you. Platform-native meeting AI explains why, and the not-the-host answer covers what it means on someone else’s call.
The bot-free Mac apps are where the Mac is best served, and almost all of them are built for the document you read afterward. Does Granola show a summary during the meeting? explains why that’s a design choice rather than a missing feature.
On a Mac, listening is the solved half
Here’s the good news specific to the Mac. The hard-sounding part, getting a call’s audio into an app, is something macOS now does natively. Live Captions is the proof: it can caption any app because the operating system can hear every app. A third-party tool gets the same access by asking permission, not by installing anything.
That means none of the old plumbing: no BlackHole or Loopback, no virtual audio device, and no multi-output device to rebuild so you can still hear the call. How to record system audio on a Mac without a virtual device covers that history. And system-audio capture reads the digital stream before it reaches your ears, so it doesn’t matter whether you’re on speakers, a USB headset, or AirPods. The headphones answer explains why that’s the property that matters most on a video call.
The thing that surprises people is the permission prompt. In recent versions of macOS, the setting that governs capturing other apps’ audio lives under Privacy & Security → Screen & System Audio Recording, the same pane as screen recording. So an audio-only tool can trigger a prompt that mentions the screen, which reads alarmingly if nobody explains it. Canary captures through Apple’s ScreenCaptureKit framework, which sits under that permission. Its request says exactly what it does: “Canary captures system audio output so it can transcribe and summarize what’s being said in your meetings in real time. No screen video is recorded.” You can see or revoke the permission in System Settings at any time.
If you decline, Canary falls back to your microphone. That works in a room, but on a headphones call it hears only your side. Allowing system audio is what makes the live summary work.
The Mac-specific half: where the summary sits
A live summary only helps if you can read it without leaving the call. That sounds trivial and isn’t. The moment you need it is the moment your name was just called, and switching to another app costs exactly the seconds you don’t have. Cmd-Tab puts the call behind something. A full-screen meeting on a Mac lives in its own Space, so anything in an ordinary window is a swipe away.
So the shape that works on a Mac is a glance, not a switch: a small panel that floats above your other windows, sits beside the call, and never takes focus from it. What that buys you is meeting situational awareness, knowing where the room is without having to go and look.
That’s how Canary is built on the Mac:
- It lives in the menu bar rather than as another app window to manage.
- The panel stays on top. It’s compact and opens at the top-right of the screen. Drag it next to the call or onto a second display.
- It never takes focus. Your meeting window stays active, and you can keep typing in Slack while the panel updates.
- The panel is the resolution matrix: now, the last 2 minutes, the last 5, and the full call. Each row is a rolling summary that re-condenses as the conversation moves.
- You can trim it. Hide the rows you don’t use in settings, or collapse the panel to a slim bar that shows just the latest line.
- Global keyboard shortcuts control it, and you can remap them in settings.
One practical tip: if you run Zoom or Teams full screen, macOS gives the call its own Space. Keep the call in a regular window, or put the panel on your other display, so both are in view at once. Catching up should be a glance, never a swipe.
What Canary does on a Mac
Canary is a real-time, bot-free meeting summarizer. It captures your computer’s system audio (no bot in the call, no plugin) and shows a live, multi-resolution rolling summary — from what’s being said right now to the whole call — so you can catch up the instant your name is called.
On a Mac that’s three steps:
- Install it (macOS 14 or later).
- Allow system audio when macOS asks.
- Click Start Listening, or connect your calendar and let it offer to start when a meeting begins. The calendar is optional, and whether a notetaker needs your calendar explains what that grant does.
Because it reads what the Mac is playing rather than joining a platform, the same panel works on Zoom, Teams, a Meet tab in Safari or Chrome, Webex, or a Slack huddle. It also runs on Windows and Linux if you don’t live on one machine. It’s free for 5 meetings a month, and Pro is $15/mo.
When someone says “…what do you think?”, glance at now, widen to last 2 min if you need the thread, and answer. What did I miss in the meeting is the whole reason the panel exists. Canary vs Granola covers how that differs from the Mac’s best-known bot-free notepad, and Canary vs Zoom AI Companion covers the built-in option most Mac users already have.
What it won’t do
Credit where it’s due, because the Mac’s built-in options win some of these outright:
- It isn’t on-device. Live Captions and Notes transcribe on the Mac; Canary doesn’t. Audio is streamed in short chunks for transcription and then discarded; the only things stored are the text transcript and the rolling summaries, encrypted at rest. If “nothing leaves the Mac” is a hard requirement, the built-in tools meet it and Canary doesn’t. On-device transcription explains what that property does and doesn’t buy you.
- It hears the call, not the screen. A number on a slide that nobody reads out isn’t in the summary. See do AI meeting notes capture screen shares?
- It starts when your Mac starts hearing. It can’t summarize the ten minutes before you joined. Joining late covers what can.
- It’s English-first. For a call held in another language, captions or a multilingual tool will serve you better. See the languages answer.
- It’s for calls on your computer. In a room with no call attached, your Mac’s microphone is the wrong input for any of these tools, Canary included. See in-person meetings.
Nothing stops you running both: captions when you want every word, the panel when you want to know where the conversation is.
Your Mac’s permissions protect you, not the call
macOS is careful about capture. It asks before any app can hear other apps, and it lists every app that holds that permission in System Settings. All of that protects you from your apps. None of it is visible to anyone else on the call. There’s no bot in their participant list and no banner in their window, and whatever indicators your Mac shows appear on your screen, not theirs. The permission you grant is a decision about your Mac. It isn’t consent from the people whose voices come through it.
So say it. A one-line heads-up at the top of the call is enough in most meetings, and here’s a short script. One-party vs two-party consent rules vary by region, and some places require everyone’s agreement. Bot-free capture on a Mac leaves a smaller footprint. It doesn’t make telling people any less necessary.
Frequently asked questions
Why does my Mac ask for Screen & System Audio Recording permission for an audio-only app?
Because macOS files capturing other apps' audio under the same privacy permission as capturing the screen. In recent versions the pane is called Screen & System Audio Recording, and apps that capture sound through Apple's ScreenCaptureKit framework, which is how Canary does it, have to request it even when they record no video. Canary's request says so in plain words: it captures system audio output to transcribe and summarize your meetings in real time, and no screen video is recorded. You can review or revoke the permission in System Settings → Privacy & Security at any time. If you decline, Canary falls back to your microphone, which on a headphones call hears only your side of the conversation.
Does macOS Live Captions summarize my meeting?
No. Live Captions shows a live transcript: the words as they're spoken, from any app, processed on the device, on Apple silicon Macs in the languages and regions it supports. It's an accessibility display for reading along, and a good free one, but it doesn't condense anything, so catching up after a few minutes away means rereading minutes of dialogue while new words keep arriving. A live summary does the opposite job: it re-condenses the conversation continuously so you read the gist at a glance. The two aren't rivals. Captions for the exact words and a rolling summary for where the conversation is will run side by side.
Do Granola or Otter show a live summary on a Mac?
No. Granola is a bot-free Mac app, but its AI note is written after the meeting: it merges what you typed with the full transcript once the call ends, and stays quiet during the call by design. Otter shows a live transcript while the meeting runs and generates its summary after the call, and its notetaker joins as a bot, so your Mac isn't doing the listening at all. Both are strong after-the-call tools. For a summary that updates while the meeting is still going, you need a tool built for that moment, which on a Mac means a real-time summarizer that captures system audio, like Canary.