Speaker Clustering

Speaker clustering segments an audio recording into different speakers. Speaker clustering does not need training, but cannot identify the speakers. If you want to identify the speakers in a recording, use Speaker Identification instead.

Configuration Parameter Description
FixTime A fixed time duration for speaker clustering, to assist with processing large files.
Input The audio track to process.
LanguagePack The language pack to use.
MaxSpeakers The maximum number of people who speak in the audio or video file.
MinSpeakers The minimum number of people who speak in the audio or video file.
PrioritizeSpeed Specifies whether to prioritize speed over accuracy.
Type The analysis engine to use. Set this parameter to ClusterSpeech.

Output Tracks

Output track Description
Result Contains a record for each segment of speech or silence. Media Server begins a new segment when the speaker changes.

For more information see Speaker Clustering Results or use the action GetExampleRecord.