An electronic device includes a display, a microphone, a communication circuit, a memory configured to store at least one application, and one or more processor(s), wherein the processor is configured to obtain voice data corresponding to the user's voice received through the microphone, transmit the voice data to an external electronic device through the communication circuit, receive a sequence of tasks for performing a first function of the at least one application, which is determined based on the voice data, from the external electronic device through the communication circuit; and while performing the tasks based on the sequence of tasks, when it is determined that execution of a first task in the sequence of tasks is not completed within a specified time, extending a time-out time of the first task and switching the execution of the first task to the execution in background.