Configurable output data formats

1. A computer-implemented method, comprising:

receiving, from a device, first audio data corresponding to an utterance;

performing speech on the audio data to determine a command;

determining a category of content associated with the command;

determining a default content type associated with the category;

identifying a user profile associated with the first audio data;

determining, using the user profile, a non-default content type associated with the category;

generating an output data format including a first portion to be populated with the default content type and a second portion to be populated with the non-default content type;

receiving, from a first content source, first text data associated with the default content type;

populating the first portion with the first text data;

receiving, from a second content source, second text data associated with the non-default content type;

populating the second portion with the second text data;

performing text-to-speech (TTS) processing on the output data format, populated with the first text data and the second text data, to generate second audio data; and

causing the device to output audio corresponding to the second audio data.

2. The computer-implemented method of claim 1 ,

further comprising:

storing, in the user profile, the output data format;

receiving, from the device, third audio data corresponding to a second utterance;

performing speech processing on the third audio data to determine a second command;

determining the category is associated with the second command;

based at least in part on the category being associated with the second command, identifying the output data format in the user profile;

receiving, from the first content source, third text data associated with the default content type;

populating the first portion with the third text data;

receiving, from the second content source, fourth text data associated with the non-default content type;

populating the second portion with the fourth text data; and

performing TTS processing on the data format, populated with the third text data and the fourth text data, to generate fourth audio data; and

causing the device to output the data format populated with the third data and the fourth data.

3. The computer-implemented method of claim 1 , further comprising:

determining, in the user profile and associated with the category, a first indicator representing a first type of information; and

determining, in the user profile and associated with the category, a second indicator representing a second type of information, the first indicator and the second indicator being used by the first content source to determine the first text data.

4. The computer-implemented method of claim 1 , further comprising:

determining the category is absent from the user profile;

determining a second output data format including the first portion but not including the second portion;

performing, using the second output data format, TTS processing on the first text data to generate third audio data; and

causing the device to output second audio corresponding to the third audio data.

5. A system, comprising:

at least one processor; and

at least one memory including instructions that, when executed by the at least one processor, cause the system to:

receive text data representing a command;

determine, based at least in part on the text data, a first content source associated with the command, the first content source configured to provide a first type of content;

identify a user profile associated with the text data;

determine, based at least in part on the user profile, a second content source associated with the command, the second content source configured to provide a second type of content different from the first type of content;

generate an output data format including a first data field to be populated with data received from the first content source and a second data field to be populated with data received from the second content source;

receive first data from the first content source;

associate the first data with the first data field;

receive second data from the second content source;

associate the second data with the second data field; and

cause a device to output data corresponding to the output data format, the output data including the first data and the second data.

6. The system of claim 5 , wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the system to:

perform natural language understanding (NLU) processing on the text data to generate NLU results; and

determine the command based at least in part on the NLU results.

7. The system of claim 5 , wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the system to:

receive second text data representing a second command; and

determine, in the user profile, a second output data format associated with the second command, the second output data format including a third data field configured based at least in part on system preferences and a fourth data field configured based at least in part on user preferences.

8. The system of claim 5 , wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the system to:

send, to the second content source, an indicator representing the second type of content, the second content source using the indicator to determine the second data.

9. The system of claim 8 , wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the system to:

identify the indicator in the user profile.

10. The system of claim 5 , wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the system to:

store the output data format in the user profile;

associate, in the user profile, the first data field with the first content source; and

associate, in the user profile, the second data field with the second content source.

11. The system of claim 5 , wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the system to:

determine a change in a user location; and

generate the text data based at least in part on determining the change.

12. The system of claim 11 , wherein the at least one memory further includes instructions that, when executed by the at least one processor, further cause the system to:

determine the change has occurred in conjunction with the command a number of times over a period of time;

determine the number of times satisfies a threshold number of times; and

associate, in the user profile, the change with the command.

13. A computer-implemented method, comprising:

receiving text data representing a command;

determining, based at least in part on the text data, a first content source associated with the command the first content source configured to provide a first type of content;

identifying a user profile associated with the text data;

determining, based at least in part on the user profile, a second content source associated with the command, the second content source configured to provide a second type of content different from the first type of content;

generating an output data format including a first data field to be populated with data received from the first content source and a second data field to be populated with data received from the second content source;

receiving first data from the first content source;

associating the first data with the first data field;

receiving second data from the second content source;

associating the second data with the second data field; and

causing a device to output data corresponding to the output data format, the output data including the first data and the second data.

14. The computer-implemented method of claim 13 , further comprising:

performing natural language understanding (NLU) on the text data to generate NLU results; and

determining the command based at least in part on the NLU results.

15. The computer-implemented method of claim 13 , further comprising:

receiving second text data representing a second command; and

determining, in the user profile, a second output data format associated with the second command, the second output data format including a third data field configured based at least in part on system preferences and a fourth data field configured based at least in part on user preferences.

16. The computer-implemented method of claim 13 , further comprising:

sending, to the second content source, an indicator representing the second type of content, the second content source using the indicator to determine the second data.

17. The computer-implemented method of claim 16 , further comprising:

identifying the indicator in the user profile.

18. The computer-implemented method of claim 13 , further comprising:

storing the output data format in the user profile;

associating, in the user profile, the first data field with the first content source; and

associating, in the user profile, the second data field with the second content source.

19. The computer-implemented method of claim 13 , further comprising:

determining a change in a user location; and

generating the text data based at least in part on determining the change.

20. The computer-implemented method of claim 19 , further comprising:

determining the change has occurred in conjunction with the command a number of times over a period of time;

determining the number of times satisfies a threshold number of times; and

associating, in the user profile, the change with the command.