March 20, 2025

  • The Press or Say Next Gen Voice toggle is now available. Use this toggle to enable Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) streaming, improve latency within your flow, and access greater customization for audio messages within your flows.

    • When you enable the Next Gen Voice toggle:

      • The Advanced Configuration check box appears.

        Note: At this time we recommend only using the Advanced Configuration option for the most comprehensive experience.

        • If you select this check box, the App and mrcp_model text box appear. Select the appropriate TTS or ASR app and use the model text box to send raw XML data.

        • Some of the other input fields will disappear (Vendor, Language, etc.) when this check box is selected.

    • There is a known Next Gen Voice defect related to intermittent Deepgram duplication of digit strings that will be fixed in our next release.