Speaker detection is the ability to define who is speaking at any one point in time, and to attach that information to CaptionHub's output.
It's currently only available when the Speechmatics transcription engine is selected. To check that it is, navigate to the Team Settings / Transcription sub-menu.
Speaker detection in CaptionHub relies on three steps:
- Enabling speaker detection when you submit a job for transcription. Please see the Auto Transcribe section.
- Editing the speaker identification results on the Edit page. Please see the Caption Metadata section.
- Enabling speaker identification when exporting from CaptionHub