Accessory for a voice-controlled device

A method comprising:

• receiving first audio data from a first device, the first device residing in an environment that includes the first device and a second device, the first audio data representing speech of a user in the environment;
• determining, based at least in part on the first audio data, to instruct the second device to output content in the environment;
• generating second audio data representing first audio and second audio, wherein:
• the first audio has a frequency below 20 kHz;
• and
• the second audio has a frequency of at least 20 kHz and represents one or more instructions for causing the second device to output the content in the environment;
• and
• sending the second audio data to the first device for output on one or more speakers of the first device.

A device comprising:

• one or more microphones;
• one or more speakers;
• one or more processors;
• and
• one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform acts comprising:
• generating first audio data based at least in part on speech of a user in an environment, the speech captured by the one or more microphones;
• sending the first audio data to one or more remote computing devices;
• receiving, from the one or more remote computing devices, second audio data for output by the one or more speakers, the second audio data including:
• first audio representing audio that is below 20 kHz, and
• second audio representing audio that is above 20 kHz, the second audio comprising one or more instructions for instructing an accessory device in the environment to acquire supplemental content;
• and
• outputting the second audio data by the one or more speakers, the second audio data including the first audio for the user to hear and the second audio for instructing the accessory device.