Genesys PureCloud : Criteria to get the transcripts of a long conversation in realtime

[shamss]

Hi Team,

What will be the criteria Genesys PureCloud consider to split the transcripts of a long conversation.

Suppose, A customer starts talking to an Agent, and without any pauses, their conversation continues. To get the transcript of this conversation in realtime, what are the criteria Genesys consider for splitting the conversation or transcript to push to a web socket connection in a single transcript event.

Is it based on any pause time or time intervals ?
Is this criteria configurable?

Environment - [https://apps.usw2.pure.cloud/ ]

Please help

[jacobshaw]

Hi @shamss
My understanding is that phrases are terminated by pauses, but the transcription notifications are grouped periodically, generally with a window of about 35 seconds.

Sources:

Genesys Cloud Developer Center

Call transcript phrases

When downloading call transcripts with /api/v2/speechandtextanalytics/conversations/, each conversation has a list of phrases. How does the transcription service define a phrase? ie where is the boundary between one phrase and the next? If I join all the phrases together, will that give me the entire conversation, or just the phrases that met a certain confidence level?