Speaker analytics

Conversation analytics identify the parts of a conversation that help you find a specific place in a transcript or trigger an action based on an insight.

Analytics by speaker include individual metrics such as pace and talk time, and comparative data for silence, speaker overlap, and speaker ratio.

Use cases

A new salesperson consistently speaks over potential customers, alienating them and losing sales. Speaking over other people can indicate that the salesperson is not listening to the customer, or pushing an agenda other people don’t want to hear. To uncover this problem without listening to all conversations, check speaker analytics for a high level of speaker overlap during sales calls.
Analyze business meetings to find levels of attendee involvement, without listening to the entire meeting. View speaker ratio and talk time to find out if everyone is participating.
Call center support calls that fail to resolve customer issues might have a number of problems. For example, if an agent speaks rapidly followed by long periods of silence, the customer might be confused. Use speaker analytics to quickly find this problem by looking for a combination of rapid pace and extended silence time.

Features

Speaker analytics features:

Pace – The speed at which the person spoke, in words per minute (WPM). Also called speaker speech speed.
Silence time – The time during which none of the speakers said anything.
Speaker overlap – Shows if a speaker spoke over another speaker, provided as a percentage of total conversation and overlap time in seconds.
Speaker ratio – The total ratio of talk time for one speaker compared to others in the same conversation.
Talk time – The amount of time each person spoke during the conversation.

Feature availability

Speaker analytics are available for al recorded (async) and real-time (streaming and telephony) conversations:

Feature	Async	Streaming	Telephony
Pace	✓	✓	✓
Silence time	✓	✓	✓
Speaker overlap	✓	✓	✓
Speaker ratio	✓	✓	✓
Talk time	✓	✓	✓

Conversation analytics

You can get speaker analytics from any saved conversation as described in Conversation analytics.

You can also view speaker analytics during a conversation as described in the Streaming API and Telephony API guides. Interim results only apply to the part of the conversation that has completed processing.

For async, streaming, and telephony conversations, use the API reference Get analytics operation.

Next steps

If you're new to Symbl.ai, see the Get started guide.
To start processing async, streaming, or telephony conversations, see the Process a conversation overview.
For more information about using Symbl.ai features, see Conversation intelligence.