Systems and methods for generating command indications, via a computing device, based on audio data including a keyword are described. The computing device receives and processes audio data to determine whether the audio data includes a keyword. The keyword may be a device user identifier, such as an individual's name. Once a keyword is detecting, audio data surrounding the keyword is processed to determine a command contained within the surrounding data, and the command is conveyed to the computing device's user either audibly or visually. Alternatively, a location of the device is determined, a command is determined based on the device's location, and the command is conveyed to a user of the device either audibly or visually.