A hub-dialogue system includes a speech processor configured to determine a user intention that is included in inputted user dialogue. A communicator is configured to connect a local speaker corresponding to an external dialogue system through wireless communication. A controller is configured to determine the external dialogue system corresponding to the user intention from among a plurality of external dialogue systems, to generate a command sentence indicating the user intention, to convert the command sentence to a voice signal, and to control the communicator to transmit the voice signal to the local speaker corresponding to the determined external dialogue system.