Audio search results in a multi-content source environment

Described herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for processing voices searches over multiple content sources. Some embodiments operate by receiving audio input corresponding to a voice search from a user; performing automatic speech recognition of the audio input to obtain search parameters; executing a search having the search parameters over the multiple content sources to obtain search results; and displaying search results in categories in a manner customized to the user. The multiple content sources may include a principal content source, an active partner content source, and at least one non-active partner content source, where the active partner content source represents an active context. In some embodiments, the media device performs the receiving, performing, executing and displaying without exiting the active content.