Currently, SSML is only used in the original version of Voice, not yet in Voice 2.0. However, the feature is in the implementation process.
It is a standardized language that allows adding and controlling through tags attributes such as pronunciation, intonation, pauses, emotions, and speed of speech, among others. Said descriptive attribute tags will be inserted within the content of the AgentBot response and Voice will then take care of playing them at the time of giving the response.To learn more about it, you can enter here.
SSML Examples
1. Improved text identification with SSML
2. Add a Pause
3. Add emphasis to phrases or words
4. Volume, speech rate, and pitch control
5. Play audio from a URL
