According to an embodiment, an electronic device comprises: a communication module comprising communication circuitry, a memory, and at least one processor. The memory stores instructions which, when executed, cause the at least one processor to control the electronic device to: transmit, to a first electronic device through the communication module, first response data obtained by processing a first speech input corresponding to a first utterance received from the first electronic device, identify a second electronic device including circuitry configured to detect a second utterance associated with the first response data within a designated time after the first utterance, transmit a wake-up signal to the second electronic device, receive, from the second electronic device, a speech input corresponding to an utterance obtained by a microphone turned on based on the wake-up signal, identify whether the received speech input corresponding to the utterance is a second speech input corresponding to the second utterance, obtain second response data obtained by processing the second speech input based on the first speech input and the first response data in response to identifying that the received speech input corresponding to the utterance is the second speech input corresponding to the second utterance, and transmit the second response data to at least one of the first electronic device or the second electronic device through the communication module.