Dialog management with multiple modalities

A system comprising:

• computer-readable memory storing executable instructions;
• and
• one or more processors in communication with the computer-readable memory, wherein the one or more processors are programmed by the executable instructions to:
• receive audio data representing at least one utterance;
• generate, using natural language understanding (“NLU”) processing based at least partly on the audio data, command data that represents a subject of the at least one utterance;
• send the command data to a first application, wherein during a first period of time, the first application:
• causes presentation of first output content in a first modality in response to receiving the command data;
• and
• generates second output content in a second modality different from the first modality, wherein the second output content is associated with the first output content;
• receive the second output content from the first application;
• and
• send the second output content to a second application, wherein the second application causes presentation of the second output content in the second modality during a second period of time subsequent to the first period of time.