A system is described which includes a content retriever to retrieve and format data and a media file playlist generated by the content retriever from the data. The media file playlist includes a playlist entry title identifying a title for a media file, a file name identifying the media file, and a metadata tag containing data for performing an action associated with the file. Examples of the actions that may be performed are calling a phone number or sending an email. The system also includes a text file playlist generated by the content retriever from the text data in XML (extensible markup language). The text file play list includes text-to-speech markup tags indentifying the XML-formatted text file as a text-to-speech conversion file. The system further includes a text-to-speech converter configured to generate at least one audio file playlist from the text file playlist and a configuration module associated with the content retriever configured to accept user input instruction that identify the data.