The Text-to-Speech (TTS) technology enables an Interactive Voice Response (IVR) system to render text content into synthesized speech output, according to algorithms within the TTS software. Avaya Experience Portal integrates with third-party TTS servers to provide this capability in speech applications.
When the Experience PortalMedia Processing Platform (MPP) software receives a call, MPP starts the associated speech application that controls the call flow. If the speech application uses TTS resources, MPP also starts a session with a TTS server that is configured to use all the language and voice combinations defined in the speech application.
Note:
You can switch languages within a single speech application, provided all the required languages are configured on the same TTS server. If a speech application is configured to use more language/voice combinations than are configured for any single TTS server, Experience Portal sends a No TTS Resource exception to the application. What happens then depends on the event handler that the application uses.
As the call progresses, MPP directs any requests for speech synthesis from the application to the designated TTS server. The TTS server then renders the text content as audible speech output.
Note:
You need one TTS license for each call that requires TTS resources. The license is unavailable until the call is complete and becomes available to other calls after the current call ends.
