Using SSML to control speech synthesis

AgentX supports Speech Synthesis Markup Language (SSML), providing additional control over the speech generation for your response. To use this feature, populate the SSML Answer field in content designer.

For a complete list of supported SSML tags, see https://docs.aws.amazon.com/polly/latest/dg/supportedtags.html

1. From content designer, create an item namde SSML-Demo, and set the utterance to “What is AgentX?”

2. Expand the Advanced section and enter the following text in the SSML Answer field:

   <speak>
   <sub alias="Agent X">AgentX</sub> is <amazon:effect name="drc">great</amazon:effect>.
   
   <sub alias="Agent X">AgentX</sub> supports <sub alias="Speech Synthesis Markup Language">SSML</sub> for speech synthesis.
   
   <prosody rate="150%">I can speak very fast</prosody>, 
   <prosody rate="75%">or very slowly</prosody>.
   
   <prosody volume="-16dB">I can speak quietly</prosody>,
   <amazon:effect name="drc">or speak loud and clear</amazon:effect>.
   
   I can say tomato or <phoneme alphabet="ipa" ph="təˈmɑːtəʊ">tomato</phoneme>. 
   </speak>
   

3. Click Save.

4. Call in to the system and ask: “What is AgentX?” to hear how SSML controls the synthesized voice response.