Generating additional synthesized voice output based on prior utterance and synthesized voice output provided in response to the prior utterance

A system comprising:

• a first computing device comprising one or more storage devices storing instructions, and one or more processors that are operable to execute the instructions to cause the one or more processors to perform operations comprising:
• determining that a second computing device is providing audible synthesized voice output in response to a prior utterance, spoken by a user, that was processed by the second computing device to generate the audible synthesized voice output;
• and
• in response to determining that the second computing device is providing the audible synthesized voice output in response to the prior utterance spoken by the user:
• generating additional synthesized voice output based on both:
• the prior utterance spoken by the user, and
• a transcription of the audible synthesized voice output provided in response to the prior utterance,
• wherein content of the additional synthesized voice output varies from that of the audible synthesized voice output;
• and
• providing, by the first computing device and for audible presentation, the additional synthesized voice output generated based on the prior utterance spoken by the user and the transcription of the audible user interface output provided in response to the prior utterance.