Feature Overview
Virtual Agent–Voice (VAV) feature, which was referred to as Customer Virtual Assistant (CVA) in 12.5(1) release, enables the IVR platform to integrate with cloud-based speech services. This feature supports human-like interactions that enable customers to resolve issues quickly and more efficiently within the IVR, thereby, reducing the calls directed towards agents.
Note |
The Dialogflow ES GCP project trial version should not be used in a production environment. |
In a traditional IVR, customers can interact with the IVR in the following ways:
-
VVB Media Services-Based Interaction: Prompts are played locally by VVB by downloading WAV files. User inputs are captured using DTMF grammar.
-
ASR-Based and TTS-Based Interactions: Prompts are played by the external media server over MRCP Synthesis command for Text-to-Speech (TTS) functionality. The responses are recognized by external media server based on predefined grammar provided by Asynchronous Speech Recognition (ASR).
VAV-based IVR enables a new mechanism to leverage cloud-based-AI-enabled speech services. VAV provides the following speech services:
-
Text-to-Speech: Integration with cloud-based TTS services in your application for Speech Synthesis operations. VAV currently supports Google Text to Speech service.
-
Speech-to-Text: Integration with cloud-based ASR services in your application for Speech Recognition operations. VAV currently supports Google Speech to Text service.
-
Speech-to-Intent: VAV provides capability of identifying the intent of customer utterances by processing the text received from Speech-to-Text operations. VAV offers this service by using cloud-based Natural Language Understanding (NLU) services. VAV currently supports Google Dialogflow service.