A method and structure for the invention forwards a request for voice instructions from the XML browser to a call control protocol to CCXML/Voice XML converter. The invention converts the request for voice instructions to the call control protocol using the converter and forwards the request for voice instructions from the converter to the control point. The control point returns voice instructions to the converter, and the converter, in turn, converts the voice instructions from the call control protocol to CCXML/Voice XML. This process next returns voice instructions from the converter to the CCXML/Voice XML browser and the XML browser executes the voice instructions using the XML browser. Then, the invention runs an application on a CCXML application server connected to said CCXML/Voice XML browser.