Disclosed herein are system, method, and computer program product embodiments for a text-to-speech system. An embodiment operates by identifying a portion of content of the document, that is to be replaced with a summary associated with the content responsive to a request for an audible version of the document. A first request for the audible version of the document is received. A first summary of the content at a first level of detail is generated. The first summary is audibly output. A second request for additional information is received. A second summary of the content at different level of detail is generated. The second summary of the content at the second level of detail is audibly output.