Abstract: A device determines at least one search result that is responsive to a textual representation of a voice query. The at least one search result includes a reference to a first document related to the voice query, a first set of text from a content of the first document, and a second set of text that is responsive to the voice query. The second set of text is in a complete sentence form. The device converts the second set of text into information corresponding to an audible version of the second set of text, and generates a second document that includes the reference to the first document, the first set of text, the second set of text, and the information corresponding to the audible version of the second set of text. The device provides the second document to a client device for presentation on a display.