What is Speaker Diarization?
It is the process of labeling speakers on the text by distinguishing who made the speeches in the audio recording.
Overview
Speaker Diarization, 'who spoke?' answers the question. If there is more than one person in a meeting recording, the system analyzes differences in voice tone and separates the conversations into 'Person 1', 'Person 2' etc.
How it works
AI learns the timbre and characteristics of the voice. It tracks these sound signatures throughout the recording, marking speaker transitions within the text.
Where it is used
Used in podcast analysis, court recordings, and multi-participant meeting summaries.
Commonly confused with
Not to be confused with Transcription, which simply transcribes audio; This process adds 'who' is speaking in addition to the text.
Frequently asked questions
Does the speaker come up with their own names?
No, it usually distinguishes between speakers (person A, person B). You must introduce the names into the system.
Related terms
Related tools
This explanation was written in plain language for TreScout and machine-translated from the Turkish original · the Turkish version prevails. If something looks wrong or missing, write to hello@trescout.com. Read in Turkish →