People and speaker names

Overview

MeetingDebrief labels your microphone as Me and the other side of a call as Other. Assign a speaker to a person, and their name replaces the label everywhere that meeting appears, including the summary and chat. People in the sidebar lists everyone you have named.

The first time you name a speaker, MeetingDebrief asks What's your name? Your answer is used for Me in every meeting.

Name the speakers in a meeting

1. Open a meeting and find People in this meeting above the transcript. Each voice has a chip showing its share of the talking.
2. Click a chip marked who is this?
3. Type a name or pick someone you have already named. When the audio is available, you can play that speaker's longest line to check who it is.

The name updates every line that speaker said in the transcript. Naming a speaker also marks that meeting's summary as out of date, so you can regenerate it with the right names.

Tell remote speakers apart (preview)

Everyone on the far end of a call is Other by default. Turn on Tell remote speakers apart in Settings → Transcription and they become Speaker 1, Speaker 2, and so on, for up to four remote speakers. You can then assign each one to a person.

• It runs on your computer and works with both Parakeet and Whisper.
• It needs a one-time model download and Detect speakers in Settings → Recording.
• It works best in English and applies to new transcriptions.
• If it fails, the transcript falls back to Me and Other.

The People page

Click People in the sidebar to see everyone named in your meetings, with how often and how recently you met. Use Find someone… to filter the list. Open a person to see every meeting they were in and how long they talked. People also appear in global search (Cmd+K on macOS, Ctrl+K on Windows).

Renaming someone to a name that already exists offers a merge instead of creating a duplicate. You can also start a merge from the person's page with Merge….

Names follow voices

When you re-transcribe a meeting, assignments carry over when the match is unambiguous. If it isn't, MeetingDebrief keeps the assignment as it was rather than guess.

When speakers can't be told apart

The transcript says why, and what to do about it. Common reasons:

• Your microphone recorded silence: check the microphone permission and input device.
• No audio from other apps: the system audio track is silent. That is expected in person. For calls, turn on Include system audio in Settings → Recording.
• A single audio track: an imported file, for example, has no separate microphone and system audio tracks to compare.
• The speaker model is missing: download it in Settings → Transcription.

Privacy

Speaker separation and naming run on your computer. If you connect your own AI server, it receives transcripts with those names. Integrations include speaker names in the details they send.