Creating call analytics configurations

The steps in this section explain how to create a call analytics configuration.

Note

To use call analytics with Amazon Transcribe, Amazon Transcribe Analytics, or Amazon Chime SDK voice analytics, you must have the following items:

• An Amazon Chime SDK Voice Connector. If not, see Creating an Amazon Chime SDK Voice Connector.

• Amazon EventBridge targets. If not, see Automating the Amazon Chime SDK with EventBridge.

• A service-linked role that allows the Voice Connector to access actions on the EventBridge targets. For more information, see Using the Amazon Chime SDK Voice Connector service linked role policy.

• An Amazon Kinesis Data Stream. If not, see Create a Kinesis Video Stream in the Amazon Kinesis Video Stream Developer Guide. Voice analytics and transcription require a Kinesis stream.

• To analyze calls offline, you must create an Amazon Chime SDK data lake. To do that, see Creating the Amazon Chime SDK data lake in the Amazon Chime SDK Developer Guide.

To create a configuration

1. Open the Amazon Chime SDK console at https://console.aws.amazon.com/chime-sdk/home.

2. In the navigation pane, under Call Analytics, choose Configurations, then choose Create configuration.

3. Under Basic information, enter a name for the configuration.

4. (Optional) Under Tags, choose Add new tag, then enter your tag keys and optional values. When finished, choose Next.

5. (Optional) Under Analytics service details, choose any combination of voice analytics and Transcribe services, then do the following, depending on the option that you select:

   If you choose voice analytics

   1. Under Output details, choose your Kinesis Data Stream from the list.

   2. (Optional) To store data in an Amazon S3 bucket for post-call analysis, choose Data warehouse to perform historical analysis, then select your Amazon S3 bucket from the list.

   3. Under Voice analytics destinations, select one or more targets from the lists.

   4. Under Consent Acknowledgement, select the Yes, I agree to the Consent Acknowledgement for Amazon Chime Speaker Search checkbox, then select any combination of Speaker Search and Voice Tone Analysis.

   5. Choose Next, then choose Next again to skip the Recording page.

   If you choose Amazon Transcribe services

   1. Choose Amazon Transcribe if you only want call transcripts.

      —OR—

      Choose Amazon Transcribe Call Analytics to generate insights in addition to call transcripts.

   2. Under Output details, select a Kinesis data stream from the list.

   3. (Optional) Choose Data warehouse to perform historical analysis, then choose your Amazon S3 bucket from the list.

   4. Under Language, choose your language from the list.

   5. (Optional) Expand Content removal settings, select one or more options, then choose one or more of the additional options that appear. Helper text explains each option.

   6. (Optional) Expand Additional settings, select one or more options, then choose one or more of the additional options that appear. Helper text explains each option.

   7. Choose Next, then choose Next again to skip the Recording page.

6. Under Service access, choose one of the following options:

   • Create and use a new service role to automatically create a role with the minimum required permissions for the resources currently specified by your configuration.

   • Use an existing service role to use one of your current roles. Make sure that the role contains the correct permissions for the resources specified by your configuration.

   When finished, choose Next.

7. (Optional) Under Real-time alerts, choose Active real-time alerts, then choose the radio button for the rule or rules that you want to use. You can select three rules per alert. When finished, choose Next.

8. Under Review and create, edit your settings as needed, then choose Create configuration.