Skip to main content

         This documentation site is for previous versions. Visit our new documentation site for current releases.      

Introducing Voice AI

Updated on May 20, 2021

This feature is added in Pega Customer Service 8.6.1 patch release.


Pega Voice AI is available as an add-on to Pega Customer Service. It requires a separate license. For pricing information, contact your Pega representative.

Pega Customer Service Release Notes

Voice AI uses proprietary speech-to-text transcription and natural language processing capabilities to analyze conversations and provide contextually relevant, real-time suggestions to CSRs during voice interactions. By providing useful suggestions to CSRs, Voice AI helps improve agent and customer experience and mitigate compliance risk for organizations.

Voice AI includes the following features:

Script adherence
Voice AI indicates to CSRs whether they are adhering to the script prescribed for the call type that is in progress.
Case suggestions
Based on the context of the conversation, Voice AI recommends one or more case types to CSRs to help handle the customer inquiry.
Form autofill
Voice AI detects entities from the conversation and automatically populates the corresponding form fields.
Knowledge suggestions
Based on the context of the conversation, Voice AI recommends relevant Pega Knowledge articles to CSRs.

You configure Voice AI suggestions in a dedicated channel interface available in the Pega Platform. You can train your Voice AI model to provide insights that are relevant for your company, industry, use cases, and dialects.

The following figure illustrates how various components in the Voice AI architecture work together to deliver suggestions to CSRs:

Voice AI architecture
An architecture diagram showing the interaction between various components of Voice AI.

For more information, see Voice AI.

Have a question? Get answers now.

Visit the Support Center to ask questions, engage in discussions, share ideas, and help others.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best. is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us