An example process includes: at an electronic device with one or more processors, a memory, and a display: receiving a natural language input; initiating the digital assistant; in accordance with initiating the digital assistant, obtaining a response package responsive to the natural language input; after receiving the natural language input, selecting, based on context information associated with the electronic device, a first response mode of the digital assistant from a plurality of digital assistant response modes; and in response to selecting the first response mode, presenting, by the digital assistant, the response package according to the first response mode.