An electronic device includes a speaker, a microphone, a communication circuit, a processor operatively connected to the speaker, the microphone, and the communication circuit, and a memory operatively connected to the processor. The memory stores instructions that, when executed, cause the processor to receive a user input to activate an intelligent system, to determine at least part of a duration to receive a user utterance via the microphone, based at least partly on a state of the electronic device, to receive a first user utterance via the microphone after receiving the user input, to transmit first data associated with the first user utterance to an external server via the communication circuit, and to receive a first response from the external server via the communication circuit. The first response is generated based at least partly on the first data.