Note: This release is in preview. Features described here don’t become generally available until the latest general availability date that Salesforce announces for this release. Before then, and where features are noted as beta, pilot, or developer preview, we can’t guarantee general availability within any particular time frame or at all. Make your purchase decisions only on the basis of generally available products and features.

kvsTranscriber Lambda Function

This Lambda function does the actual real-time transcription work. This function is not directly invoked from a contact flow. It is triggered by the kvsConsumerTrigger Lambda function. You do not need to call this function manually.

Configuration: This function is available to Salesforce Voice with Amazon Connect and Salesforce Voice with Partner Telephony from Amazon Connect customers who are using an Amazon Connect instance that’s provided by Salesforce. No additional configuration is necessary. See a sample version of the invokeTelephonyIntegrationApi Lambda function in GitHub.

Usage: The kvsConsumerTrigger Lambda function automatically calls this function. You do not need to call this function manually.

This Lambda function performs the following steps:

  1. Generates the JWT token that is required to authenticate into the Salesforce Telephony Integration API.
  2. Starts Amazon real-time transcription and hooks the audio stream (between rep and end user) to the transcription service.
  3. Parses the generated transcripts and invokes the CreateMessage API on the telephony Integration Service to stream the transcripts into Salesforce.
  4. Stops the transcription when the call ends.

To learn how to use Amazon Transcribe’s custom vocabulary and vocabulary filtering, see Improve Amazon Transcribe's Transcription Accuracy with Custom Vocabulary and Filters.