reference deployment

Quantiphi Real-Time Call Analytics on the AWS Cloud

Live call transcription, metadata extraction, and postcall data analytics on AWS

This Quick Start sets up an Amazon Web Services (AWS) architecture that deploys real-time call analytics on the AWS Cloud. Quantiphi's real-time call analytics uses machine learning to transcribe and run live and postcall data analytics, freeing support agents from manual note taking. Agents receive call transcriptions, keywords, and caller identification on a dashboard during a call and can replay and download call data afterward.

UiPath logo

This Quick Start was developed by Quantiphi in collaboration with AWS. Quantiphi is an AWS Partner.

  •  What you'll build
  •  How to deploy
  •  Cost and licenses
  •  What you'll build
  • This Quick Start sets up the following:

    • Amazon Chime Voice Connector to receive calls from user private branch exchange (PBX) software.
    • Amazon Kinesis Video Streams to store call streams.
    • Amazon EventBridge to write messages to Amazon Simple Queue Service (Amazon SQS) queues when a call begins and ends.
    • Amazon SQS queues to store messages that are read by AWS Lambda functions.
    • In the transcription queue:
      • AWS Lambda function to read audio streams from Kinesis Video Streams and initiate transcription.
      • Amazon Transcribe to transcribe call streams.
      • Amazon DynamoDB table to store transcriptions.
      • Amazon Simple Storage Service (Amazon S3) bucket to store MP3 files of call streams.
    • In the keyword-extraction queue:
      • AWS Lambda function to extract keywords and publish them to the Quantiphi web application.
      • DynamoDB table to store keywords.
      • API Gateway to manage access to the Quantiphi web application.
    • In the postcall metadata-extraction queue:
      • AWS Lambda function to extract metadata and publish it to the Quantiphi web application.
      • Amazon Comprehend to extract metadata.
      • DynamoDB table to store metadata.
      • API Gateway to manage access to the Quantiphi web application.
    • In the virtual private cloud (VPC):*
      • An Application Load Balancer to route traffic between Quantiphi web application nodes.*
      • 1-4 Amazon Elastic Compute Cloud (Amazon EC2) instances to host Quantiphi web application nodes. You choose the number of hosts during deployment.
    • AWS Identity and Access Management (IAM) to manage IAM roles and policies.

     

    * The template that deploys the Quick Start into an existing VPC skips the components marked by asterisks and prompts you for your existing VPC configuration.

  •  How to deploy
  • To deploy Quantiphi real-time call analytics, follow the instructions in the deployment guide. The deployment process takes about 40 minutes and includes these steps:

    1. If you don't already have an AWS account, sign up at https://aws.amazon.com, and sign in to your account.

    2. Launch the Quick Start by choosing from the following options. Before you create the stack, choose the AWS Region from the top toolbar.

    3. Test the deployment.

    Amazon may share user-deployment information with the AWS Partner that collaborated with AWS on the Quick Start.  

  •  Cost and licenses
  • You are responsible for the cost of the AWS services and any third-party licenses used while running this Quick Start reference deployment. There is no additional cost for using the Quick Start.

    The AWS CloudFormation templates for this Quick Start include configuration parameters that you can customize. Some of these settings, such as instance type, affect the cost of deployment. For cost estimates, see the pricing pages for each AWS service you use. Prices are subject to change.

    Tip: After you deploy the Quick Start, create AWS Cost and Usage Reports to track costs associated with the Quick Start. These reports deliver billing metrics to an Amazon Simple Storage Service (Amazon S3) bucket in your account. They provide cost estimates based on usage throughout each month and aggregates the data at the end of the month. For more information about the report, see What are AWS Cost and Usage Reports?