| CPC G10L 15/22 (2013.01) [G10L 15/08 (2013.01); G10L 15/30 (2013.01); G10L 2015/088 (2013.01); G10L 2015/223 (2013.01)] | 16 Claims |

|
10. A system comprising:
at least one processor; and
at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
receive, from a user device, first audio data representing an utterance;
determine, based in part on a wakeword of the first audio data, that the utterance is directed to a first personality corresponding to a first speech-processing configuration;
process the first audio data to determine the utterance includes a command;
generate message data that:
indicates the command is associated with a second personality corresponding to a second speech-processing configuration, and comprises a request for permission to use the second speech-processing configuration to process the command;
perform speech synthesis using the message data to generate second audio data; send, to the user device, the second audio data;
receive third audio data comprising an indication of permission to use the second speech-processing configuration; and
based at least in part on the indication of permission, cause a component associated with the second speech-processing configuration to determine a response to the command.
|