Fokus

Meeting Scribe Agent (MSA)

Record meetings without a bot in the room — and get back a note with the summary written, the action items extracted, and every word searchable.

Paid add-on

The Meeting Scribe Agent is an optional add-on, billed separately from your plan — turn it on in Settings → Billing. It's free to use during the public beta.

You know the feeling: great meeting, everyone agreed on everything, and two days later nobody remembers who owned what. The Meeting Scribe Agent (MSA) exists so that never happens again. Record the conversation — no bot joining your call — and a few moments later there's a note in your workspace with the summary written, decisions captured, and action items ready to become tasks.

This is a real meeting, transcribed by Scribe:

A Scribe meeting note: audio player plus an AI summary organized into topics, decisions, and action items

Nobody typed any of that. The topic headings, the bullets, the decisions — all drawn from the audio. The player at the top holds the original recording, so the source of truth is always one click away.

Scribe works in the browser, the desktop app, and on mobile. The differences between them are real but small, and they're all in one table further down.

Two ways to capture

Both live in a Meeting Scribe card at the top of the Notes panel — Record meeting and Upload recording, side by side:

The Meeting Scribe card at the top of the Notes panel, with Record meeting and Upload recording buttons

Record live. One click when the meeting starts; that's the whole workflow. No calendar event required — walk into a room, hit record. Calendar events also carry their own Record meeting button, which links the recording to that event automatically and lets Scribe use the attendee list when it works out who's speaking.

Upload a recording. Already have the audio? Use Upload recording in the same card. Voice memos, exported meeting audio, an interview from your phone — Fokus transcribes it and drafts the same meeting note.

The card only appears once the add-on is on. If you don't see it, that's why.

While the meeting is running

The transcript fills in while you're still talking. Audio uploads in chunks as it's captured, each chunk is transcribed the moment it lands, and the lines appear in the meeting note as they come back — the first one usually within about half a minute.

A meeting note mid-recording: the live transcript filling in above the editor, with the recording pill at the bottom of the screen

A recording pill follows you around the app, so you can go answer an email without losing the controls:

The recording pill: elapsed time, a Mic only badge, expand, pause, split, and stop controls

From left to right, that's the elapsed time, a Mic only badge when system audio isn't being captured, and then:

Expand

The chevron opens the transcript so far, right in the pill. It stays collapsed by default — an hour-long meeting is hundreds of lines, and there's no reason to stream them all unless you're looking.

Pause

Speak off the record. Nothing is captured while paused, and paused time doesn't count toward your Scribe minutes.

Split

End this meeting and start the next. Back-to-back calls become two separate notes without touching the recorder in between.

Stop

Ends the recording and hands it over for the summary.

Forgot to press stop? After five minutes of silence Scribe stops on its own and keeps everything up to that point. An empty room won't quietly burn through your minutes overnight.

Rough live captions (browser only)

In a browser you'll also see faint live captions ahead of the real transcript — a rough running draft, replaced by the proper text as each chunk comes back. Nothing about them is saved.

Where your browser can recognise speech on the device itself, they never leave your machine. Where it can't, your browser's own speech service does the recognition, which means the microphone stream goes to your browser vendor for the length of the recording. Hover the marker to see which of the two is running.

The desktop app doesn't show live captions — the browser engine it's built on has no speech recogniser available. The transcript still fills in as chunks come back, exactly as it does on the web.

The transcript Fokus stores always comes from Fokus's own transcription, on every platform.

In the desktop app

The desktop app is the one to use for online meetings, because it captures system audio as well as your microphone. That's why no bot has to join, and why it works with any meeting tool — Zoom, Meet, Teams, a phone on speaker. It also means the two sides of the conversation arrive on separate channels, so speakers come out as a clean you / them and stay that way for the whole meeting.

The floating recorder

Meetings happen in someone else's window. When you minimise Fokus or switch away, the recorder detaches into a small always-on-top bar with the same controls:

The floating desktop recorder: elapsed time, a mic-only indicator, and pause, split, stop, and open-Fokus buttons

It appears on its own when the main window isn't visible, follows you onto full-screen spaces, and never steals focus. Drag it anywhere — it remembers where you put it. Closing it does not end the meeting; the recording belongs to the app, not the bar. The last button reopens the main window.

"Are you in a meeting?"

The meetings that get lost are the unplanned ones — the "hop on for five minutes" call that was never on anyone's calendar. So the desktop app watches for sustained microphone use and offers:

A toast reading Are you in a meeting? Your mic has been live for a while, with Not now and Record meeting buttons

The signal is deliberately dumb: something is using your microphone. That catches every meeting app without Fokus needing to know they exist. Dictating a message or a quick sound check won't trigger it — the mic has to stay live for a while first. Ignoring the prompt is a valid answer, and Not now stays quiet for the next half hour rather than asking again during the same call.

macOS only, for now

Call detection is available on macOS. The floating recorder works on every desktop platform.

On mobile

The same two buttons sit at the top of Notes:

The Meeting Scribe card on mobile with Record meeting and Upload recording, above the notes list

Tap Record meeting and the recorder takes over the screen: a level meter, the elapsed time, and the transcript building underneath as each chunk comes back.

The mobile record screen: microphone button, level meter, timer, live transcript area, and Pause and Stop and transcribe buttons

Mobile chunks a little more patiently than the web — the first chunk closes after about 20 seconds, then 40, then a minute — which keeps the first line quick without spending your battery and data on rotation for a two-hour meeting.

A few things worth knowing:

  • Recording survives a locked screen and the app going to the background. Put the phone face-down on the table and it keeps going.
  • Link it to an event while you're recording, from the pill on the record screen — no need to decide up front.
  • Pause works the same as everywhere else. Splitting a recording in two is web and desktop only.
  • On newer phones the transcript also starts appearing straight away, recognised on the device itself. Older phones simply wait for the first chunk, and the record screen says so above the transcript rather than leaving you watching an empty panel. Either way the saved transcript comes from Fokus's own transcription.

Afterwards: the meeting note

When you stop, Scribe re-reads the whole recording in one pass, then writes the note: a summary organised into the topics that were actually discussed, the decisions, and the action items. It's the same meeting on every device — three tabs on mobile, one scrolling note on the web:

A finished meeting on mobile: speaker chips, Summary / Transcript / Actions tabs, and the summary organised into topics and key decisions

Why the final transcript looks better than the live one

The live transcript is assembled chunk by chunk, so each piece is analysed without knowing about the others. Once the meeting ends, Fokus transcribes the complete recording in a single pass and replaces the provisional text. That's what keeps speakers consistent from the first minute to the last on microphone-only recordings — and why a line can change slightly between what you saw live and what you keep.

Action items that actually get done

Here's where Scribe stops being a transcription tool and starts being a Fokus feature. Every commitment made in the meeting comes back as a structured action item — with the owner, the deadline they said out loud, and an Add task button:

Extracted action items with owners, due chips, and Add task buttons — above the speaker-labeled transcript

Click Add task and the item enters your real plan — TEA fills in the details, auto-scheduling finds it a slot. "Maria will update the script by Monday" goes from a sentence in a meeting to a scheduled block on Maria's Monday, in two clicks. Items that don't belong get an ✕.

The same list is on mobile, with the same two buttons:

The Actions tab on mobile showing an extracted action item with Add task and Dismiss

You don't even have to open the note: ask Captain Fokus "what were the action items from my last meeting?" and accept or dismiss them right in chat — "accept the second one" creates the task on the spot. The Captain can read full transcripts too, when a summary isn't enough.

The transcript underneath

The transcript tab on mobile with speaker-labeled, timestamped paragraphs
  • Timestamped and speaker-labeled — "Transcript · 3 min · 2 speakers", with each line attributed and clickable. Speaker labels are worked out when the recording finishes, so the live transcript shows timestamps and text only.
  • Name the voices once. Tap an unknown speaker and say who it is — a name from your people, or This is me — and the whole transcript updates:
The Who is Speaker 1? sheet with a This is me option and a people search field
  • It remembers. Name someone in a recurring meeting and Scribe reuses that the next time the same people are in the room. Desktop recordings of a one-to-one usually don't need naming at all — with the two sides on separate channels, Fokus can work out who's who by itself.
  • Listen from any line. Playback jumps the audio to the exact moment someone said the thing.
  • It's a note, so it's searchable from Spotlight, taggable, and editable like everything else. Pair it with the Meeting notes template for agendas on top, evidence below.

Getting it out of Fokus

The recording bar in the meeting note carries everything you can do with a finished meeting — on the web and in the desktop app:

The meeting player row with export to Markdown, export to PDF, share, email draft, and delete buttons

Markdown or PDF

Download the whole meeting — summary, decisions, action items, and full transcript — as a file. Markdown for anywhere that takes text; PDF for a laid-out document with a Fokus header and footer on every page.

A follow-up email, drafted

Connect Gmail or Outlook and Fokus writes the recap into a draft addressed to the attendees. It lands in your drafts, not in their inboxes — you read it before anyone else does.

Straight into Slack or Teams

Post the recap to a channel, the same way the daily briefing does. You get a preview of the exact message before anything is sent.

Who gets a follow-up draft, and when

The draft email button needs nothing but a connected Gmail or Outlook account — Meeting Scribe on its own is enough, and it works for a walk-up meeting with no invitees. Having Fokus draft one automatically after every meeting is a feature of the Email Assistant add-on, and needs invitees on the event.

With one mailbox connected, Fokus drafts straight away and tells you which address it used. With more than one, it asks first — so a follow-up never quietly lands in the wrong Drafts folder.

Either way, drafting has its own daily AI allowance — separate from Captain Fokus's, and shared with the Email Assistant when you have it. If it runs out, the button tells you so and comes back after the daily reset.

PDFs and non-Latin scripts

Arabic exports properly — the letters join and the text sits right-aligned. Two things to know: a line that mixes Arabic with Latin words or numbers keeps them in typed order rather than reading order, and Chinese, Japanese and Korean aren't covered yet and come out as empty boxes.

For either of those, use the Markdown export — it's plain UTF-8 and keeps everything exactly as it was.

Getting the words right

Two settings decide how accurate the transcript is, and both live under Meeting Scribe in Settings → AI Agents:

The Meeting Scribe section in settings, with the Meeting language dropdown and the Custom vocabulary field

Meeting language. The language people actually speak in your meetings, which is often not the language you use the app in. Pick it. Leaving it on Mixed languages lets Scribe switch mid-sentence, which is the right answer for genuinely multilingual teams — but if your meetings are always in German, saying so produces a noticeably cleaner transcript than auto-detection does.

Custom vocabulary. A comma-separated list of the names, products and jargon a general-purpose transcriber would mangle — internal project names, an unusual surname, the library nobody outside your team has heard of. It applies to everyone in the workspace.

The usage meter at the top of the same page shows how many of the workspace's monthly Scribe minutes are gone, and when it resets.

Mobile has the same meeting-language setting, plus a switch for whether the transcript appears while you record:

Mobile account settings showing Meeting language and the Live meeting transcript toggle

Turning Live meeting transcript off doesn't change what you keep — the saved transcript is identical either way. It just stops the phone fetching it during the meeting, which is the one to reach for on a metered connection.

What changes between web, desktop, and mobile

BrowserDesktop appMobile
What gets recordedYour microphoneSystem audio + your microphoneYour microphone
Best forIn-person meetingsOnline meetings (Zoom, Meet, Teams…)In-person, on the move
Speaker labelsWorked out when the recording finishesyou / them, separated by channelWorked out when the recording finishes
Names filled in for youYes, in one-to-one meetings
Start a recording
Upload an existing file
Live transcript while recording✓ (~30s chunks)✓ (~30s chunks)✓ (20s → 40s → 60s), switchable
Rough live captions✓ browser speech recognition✓ on-device, newer phones
Pause and resume
Split into two meetings
Auto-stop after 5 min of silence
Keeps recording when you look awayTab must stay open✓ including minimised✓ including a locked screen
Floating recorder window
"Are you in a meeting?" prompt✓ macOS
Link a recording to a calendar event
Assign and rename speakers
Export Markdown / PDF
Draft a follow-up email
Share to Slack / Teams
Delete a recording

The desktop app runs the same interface as the browser, so anything in the Browser column is there too — the Desktop column is what it adds on top.

Deleting a recording

One action removes everything: hit the trash icon on the recording bar inside the meeting note (or in the meeting screen header on mobile), confirm, and the recording, transcript, audio, and the meeting note are deleted together. Deleting the meeting note itself does the same cleanup — no orphaned recordings either way.

Practical notes

  • Scribe time is metered monthly per workspace — the Billing page shows what's left. Paused time isn't counted.
  • Recording is offline-tolerant: chunks upload as they're captured and retry on their own, so a flaky connection doesn't lose the meeting — and neither does a crash, since everything already uploaded is kept.
  • Keep-audio is optional — if you'd rather store only the transcript, the audio can be discarded after processing.
  • Everyone in the room should know they're being recorded. That's basic courtesy in most places and the law in some of them.

Where it runs

Once the add-on is on, recording and uploading both work everywhere — browser, desktop app, and mobile. Only the desktop app can capture system audio, so that's the one to use for online meetings; everywhere else records the microphone, which is what in-person meetings need.

How is this guide?

On this page