US 11,810,556 B2
Interactive content output
Mark Conrad Kockerbeck, Laguna Beach, CA (US); Srikanth Nori, Arlington, MA (US); Jilani Zeribi, Seattle, WA (US); Ryan Summers, Tustin, CA (US); and Volkan Aginlar, Rancho Mission Viejo, CA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Jun. 24, 2021, as Appl. No. 17/356,877.
Prior Publication US 2022/0415307 A1, Dec. 29, 2022
Int. Cl. G10L 15/183 (2013.01); G10L 13/08 (2013.01); G10L 15/22 (2006.01)
CPC G10L 15/183 (2013.01) [G10L 13/08 (2013.01); G10L 15/22 (2013.01); G10L 2015/223 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving, from a device, first audio data representing a first spoken input;
determining that the first spoken input requests output of first content;
determining a first skill capable of outputting the first content;
sending, to the first skill, first data corresponding to the first spoken input to enable the first skill to output at least a first portion of the first content at the device;
determining, by the first skill, that second content is to be output at the device after the at least the first portion of the first content is outputted, the second content representing information for an item;
determining first output data including:
a first portion including second audio data corresponding to first synthesized speech indicating interactive content is going to be outputted, and
a second portion including third audio data corresponding to the second content;
sending the first output data to the device;
receiving, from the device and after sending the first output data, fourth audio data representing a second spoken input;
determining that the second spoken input requests performance of a first action associated with the item;
determining a second skill capable of performing the first action; and
sending, to the second skill, a first command to perform the first action with respect to the item.