The live transcript in Notetaker
Last updated: November 5, 2026
Available on: Mac and Windows, where Notetaker is enabled for your account. Account and organization restrictions, including HIPAA restrictions, apply. Mac system audio requires macOS Ventura or later.
Use the Transcript tab to follow meeting speech, find earlier words and copy the conversation. Live text and speaker labels can change after the meeting.
Read the live transcript
Live Transcript is on by default in Settings → Notetaker → Transcription. Starting with it off still saves audio for post-meeting processing, and live transcription can be unavailable for a recording even when the setting is on. Turning it off mid-meeting hides the tab; turning it back on does not start live transcription for a meeting that began with it off, and Flow shows a message that the change applies to the next meeting.
In-progress text: Words still being transcribed appear in lighter gray under the speaker who said them and stay there once confirmed, keeping the name of a speaker Flow has already identified. A very brief switch stays in the current group until the text is confirmed. Your microphone and the meeting's audio each keep their own in-progress line, shown in the order speech started.
Follow: New speech scrolls into view while you are at the bottom and not searching. Scrolling up or selecting text pauses following, so a selection is not lost; Jump to bottom resumes it.
Labels: Live views can group your microphone and other audio as You/Others, or show numbered speakers. Names replace numbered labels when available, usually within a few seconds of someone speaking, and names already in use carry over when you Resume a recording. Each line is labelled from its own evidence, so grouping, colors, badges and copied text follow that line's own speaker; an identified voice keeps its name after a quiet stretch, and a continuous run stays under one speaker header.
If a voice loses its name: After someone briefly speaks over a voice, the live view names it after the participant who has said most of what that voice has spoken. A voice with no speaking history, or one where two participants are tied, keeps the label it already has, and a silent microphone voice is never given a new name.
Markers: Sleep, offline gaps, pause/resume, Dictated and audio events can appear. Dictated means the microphone is being used for Flow dictation; system audio continues recording.
Stop: Trailing lines are saved above a pause divider timestamped when you pressed Stop, and remain when you reopen the meeting from the hub or quit Flow.
Translate what others are saying
When someone else speaks a supported language other than English, a tip appears on the Flow bar: Looks like someone is speaking [Language] — Notetaker can translate what others are saying to your preferred language. Choose Translate live transcript to open the Notepad on the Transcript tab with the live-translation language picker open, or Not now to dismiss it. The tip appears at most once per meeting, never while the Notepad is already open, and not again for a language you have already seen it for.
Search the transcript
Search and copy are disabled until the transcript has content. Search shortcuts work only with the Transcript tab active and focus outside text fields.
Open search with Cmd+F on Mac, Ctrl+F on Windows, or /.
Enter at least two characters. The match count appears in the search box.
Navigate with Enter/↓ for next or Shift+Enter/↑ for previous, or the ▲/▼ chevrons; matches wrap around and the current (orange) match scrolls into view.
Adding to a query — "not" to "not just", for example — moves you to its first match. Search ignores case, matches partial words and treats punctuation literally, with no case-sensitive or whole-word setting. It searches speech, not markers; translated rows use the displayed translation, not the original speech.
During recording, search uses the text present when the search started — clear and rerun the query to include newer speech or corrections. Escape clears and closes search, allowing following again when you are at the bottom. After recording stops, search uses the current transcript.
Understand speaker names
Automatic naming requires the attribute names setting, on by default, and naming availability for the recording; turning it off leaves numbered labels. The supported meeting app must be using your microphone, and on Mac, Wispr Flow also needs Accessibility permission. Names are not immediate — Flow can detect the call and begin naming later — and unsupported layouts can leave numbered speakers.
Meeting app | Naming requirements |
Google Meet | Chrome (including Beta/Dev/Canary), Edge or Brave; Chromium or Arc on Mac; Safari unsupported. |
Zoom | Native app; on Mac, Accessibility permission for Zoom and any Zoom interface language; on Windows, readable meeting windows and an English interface. |
Microsoft Teams | Native app on Mac and Windows; Chrome, Edge or Brave on Mac also support naming. |
Slack huddles | Desktop app on Mac or Windows. |
Webex and Discord | No automatic naming; speakers remain numbered. |
Keeping meeting windows readable
Names come only from visible participant tiles, so keep a meeting window on screen — the main window or, for Google Meet, the picture-in-picture window. A window that is hidden, minimized, on another macOS Space or fully covered by other applications cannot be read; Flow's own floating panels do not block it. With no readable window, speech stays unnamed until you uncover or restore one, and a brief unnamed interval can remain.
Flow follows the call itself rather than one particular tab or window, so a call keeps its speaker names when you switch tabs or windows, share your screen, present, or when the window Flow was reading closes and another window of the same call is open. You can start recording before you join — from Meet's waiting room, for example — and names appear once participant tiles are on screen.
Arc on Mac: naming covers only meet.google.com calls that Arc is using your microphone for; Teams, Zoom and Slack calls in Arc stay numbered, and Arc on Windows is unsupported.
Microsoft Teams: the native app also supports a compact call window (on Windows, Meeting compact view); browser-hosted Teams has none. On Mac, Flow can use the compact window when the main window is covered, but not when it is hidden or minimized, and a Teams window parked in the Stage Manager side strip still supplies names when a speaker is highlighted there. Names come from participant tiles, the participant list and gallery pages in any Teams interface language, with no need to open the People panel. The highlighted speaking tile gets the line; with no tile highlighted, an incomplete participant list or an empty gallery, other people's speech stays numbered. Teams never highlights your own tile, so your speech is named from your microphone instead.
Check and correct a name
Click a speaker name to open or close its picker; reopening clears the search box. Speaker header rows show Play audio for a short clip of that voice, so you can recognize who it is before renaming them. Numbered speakers such as Speaker 1 always show it; a named speaker shows it while their picker is open or their clip is playing, and You/Others and the meeting owner do not. Playing a clip does not close the picker.
Your own name and the "(You)" label
Your speech can be labelled with your name even when your meeting tile is not marked as you, and a single voice in a microphone-only recording appears as You or Name (You). When it is unclear which voice said a line, Flow keeps your microphone's claim on your own speech, so your words stay labelled with you rather than left unnamed. Flow uses a saved speaker rename before your profile name, and a later transcript improvement preserves that rename. First-name-only profiles can remain numbered, and if another participant uses exactly your name, neither is resolved automatically.
The (You) label is shown only on speakers linked to your own contact, so renaming a speaker to someone else never marks that person as you. If no speaker in a meeting is linked to your contact, speech from your microphone is still labelled as you. A meeting that synced before this behaviour applied updates the next time you change it, or when you use Settings → Data → Hard refresh all notes.
Matching speakers to meeting attendees
Flow matches the participants it sees to the people invited, so labels use the attendee's name as you know it. A tile can match by full name, a short or first name, a joined form of the name, the exact address on the invitation, or the part of that address before the @ sign. Names from your own contacts can match as well, including attendees with no name on the calendar invite. When a tile could belong to more than one attendee — two people named Alex, for example — or when two separate voices appear to claim the same name, Flow leaves one speaker as a numbered Speaker N instead of guessing; rename it yourself if you recognize the voice.
When every other voice has been identified and exactly one invitee is still unaccounted for, Flow gives the remaining voice that person's name — this commonly completes in-person, microphone-only one-on-ones that would otherwise end with a Speaker 2 label. Flow keeps the numbered label instead when the evidence disagrees, the invitee list is incomplete, a meeting room or a declined invitee is on the invite, or the leftover audio looks like echo or media playback. Because of this, a stray sound such as a notification chime can occasionally pick up a real name. Names you saved yourself and manual speaker assignments are kept if the meeting is processed again.
Note: Private names that only exist in your own contacts are used to match speakers for you, and are never shown or saved as the shared speaker label others see.
Warning: Speaker names are not a guarantee of identity. Speech containing more than one voice can sometimes carry your name, and when two people's voices are not told apart, a line can briefly show the other person's name. Review names before relying on or sharing the transcript; final post-meeting labels are produced separately.
When live text stops
Audio records locally during reconnection, and live text resumes when connectivity returns. Hovering the Flow bar's meeting pill can show Still listening · Reconnecting… when the Notetaker window is unfocused and the meeting is not wrapping up. Short interruptions catch up; longer outages can leave an Offline for <duration> — audio was captured and will be transcribed after the meeting marker, and post-meeting processing recovers missing words when saved audio is available. Signing out or a revoked session ends reconnection attempts; signing out saves the audio on this device.
If Flow offers Live transcript unavailable because you are offline at the start, recording has not begun.
Choose Record offline to record audio on this device for later transcription, or Cancel.
Select Generate summary after recording, once online, if offered.
The offline offer works once and expires after a newer start attempt. Failed-start cards say whether audio was saved; dismissing, ignoring or letting the card expire does not delete saved audio. See Offline meeting recording for recovery.
When no audio is coming in
If your microphone or the meeting's audio stops sending any sound — at the start or part-way through — Flow restarts that source for you and recording continues if it comes back. If no audio returns after about half a minute, a card appears on the Flow bar: Notetaker isn't getting any audio. Choose Restart Flow so capture can start cleanly, or Dismiss to close the card for this recording. The card stays until audio returns, you stop the meeting or you dismiss it; if dictation or another notification covers it, it comes back shortly afterwards.
Windows: other people's speech is missing
A recorder banner can show Could not capture system audio, System audio capture stopped or System audio permission denied. A concurrent capture can show A meeting is already recording.
If capture of other people's audio stops part-way through, Flow restarts it for you and the far end comes back on its own, usually within a few seconds. While no speaker or other output device is connected, Flow keeps retrying until one is available. The gap is kept in the recording, so the saved audio and the transcript times after recovery still line up with the meeting.
Warning: Your microphone keeps recording throughout. Speech from others during the gap itself is not recovered, and if restarts do not succeed, System audio capture stopped appears and other people's speech is missing for the rest of that recording; start a new recording to capture system audio again.
Mac: permissions or an unexpected stop
If macOS asks for Screen Recording permission, restart Flow after granting it; System Audio Recording Only requires no restart. If that permission request remains unanswered, Turn on becomes available again after 30 seconds, and choosing Don't Allow ends the wait immediately. A device another app is using exclusively cannot be captured.
Leaving a native Zoom or Teams call on Mac stops the recording within a few seconds, so anything said after you click Leave usually does not appear; if system audio such as a video starts playing right after, the stop can take around 20–25 seconds. Meetings on Windows are unaffected by this native auto-stop. Browser meetings such as Google Meet use a separate stop check; Zoom web is an exception.
Use Resume if a recording stops earlier than expected; it requires usable, unexpired audio and remaining recording time. After resuming, Flow allows settling time before another automatic stop, and Keep recording prevents another prompt for the same interruption.
If your Mac sleeps, capture and live transcription stop at that moment, so the saved audio and transcript match the recorded end time. Waking finishes processing the recording; it does not resume it.
Full storage or another saving error
Flow warns you once during a recording when your drive is nearly full with a Storage almost full — About N min of recording left alert, shown even if other tips are muted. A write failure stops an offline recording or one started without live transcription, keeping audio already saved; full storage shows Storage Full, and other saving errors show a different error notification.
Warning: A recording started with live transcription online can continue with only its live transcript after a saving failure. Post-meeting improvement is skipped, and speech saved only in audio — including offline gaps — can be lost.
Press Stop and the meeting finishes promptly with a storage or processing failure, keeping the audio recorded up to that point. Free up space and restart Flow, and Flow re-processes that audio on its own. This recovery applies to the retained audio from an offline recording, not audio discarded after a live-transcribed recording's saving failure. If there is not enough free space to finish a stopped meeting, its hub row and note card show Storage full with a Retry button; make space, then click Retry.
After the meeting
Keep Flow online for processing. Waiting for a connection appears in the floating recorder or the note opened inside the hub while you are fully offline; the meeting stays listed, and a meeting recorded offline finishes on its own once you reconnect. For a stuck upload, use a notice's Retry control and wait 15 seconds between attempts; Retry needs cloud sync on and the recording finished preparing, and nudges the existing upload rather than creating a duplicate. With Notetaker cloud sync off, meetings stay local on your computer and are picked up for processing once you turn sync on.
Transcript corrections and speaker reassignment become available once the recording has ended on every device. Silent or very short recordings can show The meeting was too short to summarize. Missing or empty audio cannot be recovered. See transcript and summary troubleshooting for uploads blocked by a VPN or slow network.
Warning: Deleting a meeting permanently removes its note, transcript and audio after you confirm Delete meeting?. If deletion fails, the meeting reappears with an error. Local audio remains on your computer after transcript processing — see meeting-data retention.
Copy or share a transcript
Click Copy transcript, or press Cmd+C on Mac or Ctrl+C on Windows with the Transcript tab active, nothing selected and focus outside text fields. The whole transcript copies as Speaker: text lines using displayed labels and translations, excluding markers and deleted lines, as plain text that takes on the styling of wherever you paste it.
To copy part of the conversation, drag across the lines you want — your selection stays intact as you scroll, and only the selection copies. Cmd+A on Mac or Ctrl+A on Windows selects the whole transcript; it does nothing while the chat drawer or a dialog is open, or when focus is in another control.
My thoughts stays private. Shared summaries can still contain transcript-derived content and speaker names.
Warning: Check copied content before sending it. Invitation emails can include a summary preview — not raw notes or transcripts — and revoking access cannot retract an email already sent.
Sharing restrictions and access changes
The owner's organization policy applies even to recipients in other organizations, and changes apply without restarting. An invitation cannot override an organization-policy denial, and organizations can disable sharing entirely; ask the owner's administrator about access under the current policy. A shared note's disabled Transcript tab explains whether an invitation or organization policy blocks access, and on the shared-note website even recipients with transcript access must open the note in the Wispr Flow desktop app.
If access is missing, check the account in the web header and use Switch account; access-denied screens offer Sign in or Retry, and there is no Request access button. Tightening link visibility does not remove explicit invitees, and if the owner leaves their organization, organization-based access ends while the owner and explicit invitees keep access.
Still need help?
If text is still missing after the relevant recovery steps, contact support with your platform, meeting app and the steps you tried.