Appendix B: Limitations - AI Powered Speech Analytics for Amazon Connect

Appendix B: Limitations

AI Powered Speech Analytics for Amazon Connect has the following limitations that should be considered before using this solution in a production environment.

  • When a new AWS Lambda container is used for a call, it is considered a cold start and has a latency of approximately ten seconds. When using this solution in a production environment and latency needs to be at zero seconds, we recommend increasing the memory of the Lambda function so new containers are used less often. Or, you can use a different AWS service such as AWS Fargate. Note that Lambda has a 15 minute limitation and will stop transcribing if a call is longer than 15 minutes.

  • The first call using the Amazon Kinesis video stream streaming block, may fail. If this happens wait 10 seconds and try again. Also, the number of concurrent calls cannot exceed the number of KVS streams, so you must manually increase this number of streams based on your estimated traffic.

  • The first few seconds of a call may not be transcribed. If this happens and impacts your transcriptions, we recommend changing the START_SELECTOR_TYPE Lambda function value to FRAGMENT_NUMBER.