The present invention is a computer software product and method including an XML parsing module, a translation module communicatively coupled to the XML parsing module and an output module communicatively coupled to the translation module, the output module configurable by the end user to execute a predefined event responsive to the processing of an associated XML tag. The predefined event may be selected from a group consisting of audio output modification, visual output modification, and tactile output modification. These output modifications may include, but are not limited to, voice inflection, voice gender, voice volume, voice pitch, voice speed, visual display modification, visual display cues, tactile device output modification and the like.