Disclosed is an electronic device which includes at least one camera module, at least one microphone, a communication module, a memory, and a processor operatively connected to the at least one camera module, the at least one microphone, the communication module, or the memory, the processor being configured to detect whether a user has taken a vehicle based on detection of the vehicle through the communication module, determine an existence or nonexistence of a passenger in the vehicle based on at least one of an external electronic device searched for through the communication module, a sound collected by the at least one microphone, or an image obtained from the at least one camera module, identify relationship information on the passenger, analyze an attribute of audio of which an output has been requested, and control an audio output through the vehicle based on the relationship information and the attribute of the audio.