Understanding XML voice response

If you have used an interactive voice response system then you have used an voice xml application, without knowing what technology is used behind that application. Voicexml is an xml application that has special xml grammar meant for handling the voice of the user.

The speech to text engine and the text to speech engine plays an important role in such applications. Support for multiple languages is available in a good voice xml server.

Know the simple voice xml grammar would help you understand what is going behind the scenes. For example the tag <prompt> under the <menu> tag would prompt the user with some audio message that is defined in the <audio> tag.

The text to speech engine converts the text message in the <audio> tag to audio message and the user hears that message. If you respond to that audio message with some voice, it is converted back to text and compared and the <choice> tag is used to divert the user to other part of the application where you will get related voice prompts according to your response. The <form> and the <block> tags are used in the voice xml grammar to present some information to the user.