Speaker Detection
Label each speaker separately in your live transcript.
Speaker detection (also called diarization) automatically attributes speech to different speakers in your transcript, labelling each one separately (Speaker 1, Speaker 2, and so on) instead of producing a single undivided block of text.
Turn on diarization
- Open Settings.
- Toggle on Speaker detection.
- Start your session. Each speaker is now labelled separately.
Toggle speaker detection on before you start captioning. It can’t be changed once a session is running.