Accelerated task performance

A method, comprising:

• at an electronic device with a display and an audio input device:
• displaying a plurality of suggested candidate task affordances including a candidate task affordance associated with a task, wherein a first suggested candidate task affordance from the plurality of suggested candidate task affordances is suggested based on a first contextual characteristic associated with the electronic device and a second suggested candidate task affordance from the plurality of suggested candidate task affordances is suggested based on a second contextual characteristic associated with the electronic device, wherein the first contextual characteristic and the second contextual characteristic are different contextual characteristics;
• detecting a set of inputs including a first user input corresponding to a selection of the candidate task affordance associated with the task;
• in response to detecting the set of user inputs, displaying a first interface for generating a voice shortcut associated with the task;
• while displaying the first interface:
• receiving, by the audio input device, a natural-language speech input;
• and
• displaying, in the first interface, a candidate phrase, wherein the candidate phrase is based on the natural-language speech input;
• after displaying the candidate phrase, detecting a second user input;
• and
• in response to detecting the second user input, associating the candidate phrase with the task.

A non-transitory computer-readable storage medium storing one or more programs configured to be executed by one or more processors of an electronic device with a display and an audio input device, the one or more programs including instructions for:

• displaying a plurality of suggested candidate task affordances including a candidate task affordance associated with a task, wherein a first suggested candidate task affordance from the plurality of suggested candidate task affordances is suggested based on a first contextual characteristic associated with the electronic device and a second suggested candidate task affordance from the plurality of suggested candidate task affordances is suggested based on a second contextual characteristic associated with the electronic device, wherein the first contextual characteristic and the second contextual characteristic are different contextual characteristics;
• detecting a set of inputs including a first user input corresponding to a selection of the candidate task affordance associated with the task;
• in response to detecting the set of user inputs, displaying a first interface for generating a voice shortcut associated with the task;
• while displaying the first interface:
• receiving, by an audio input device, a natural-language speech input;
• and
• displaying, in the first interface, a candidate phrase, wherein the candidate phrase is based on the natural-language speech input;
• after displaying the candidate phrase, detecting a second user input;
• and
• in response to detecting the second user input, associating the candidate phrase with the task.