Transcribing interactive voice response menu options to generate visualizations during a call
A method includes connecting a call from a client device to a destination having an interactive voice response service; transcribing audio from the destination during the call to identify menu options of the interactive voice response service; generating visualizations representing the menu options; and outputting the visualizations to a display associated with the client device. A system includes a telephony system, an automatic speech recognition processing tool, and a visualization output generation tool. The telephony system connects a call from a client device to a destination having an interactive voice response service. The automatic speech recognition processing tool transcribes audio from the destination during the call to identify menu options of the interactive voice response service. The visualization output generation tool generates visualizations representing the menu options. The telephony system outputs the visualizations to a display associated with the client device.
1 . A method, comprising:
determining, during a call associated with an interactive voice response service, a first menu option of a current menu of the interactive voice response service;
outputting, for display at a device during the call, a first visualization generated to represent the first menu option;
determining, during the call and based on the current menu including one or more other menu options, a second menu option of the current menu; and
outputting, for display at the device during the call, a second visualization generated to represent the second menu option.
2 . The method of claim 1 , wherein determining the second menu option of the current menu comprises:
determining the second menu option after the first visualization is output.
3 . The method of claim 1 , wherein determining a menu option of the current menu of the interactive voice response service comprises:
transcribing audio of the call.
4 . The method of claim 3 , wherein the menu options are determined using a telephony system of a software platform and the audio of the call is transcribed using a transcription service of the software platform.
5 . The method of claim 3 , wherein the menu options are determined using a telephony system of a software platform and the audio of the call is transcribed using a transcription service external to the software platform.
6 . The method of claim 1 , comprising:
determining a selection of one of the first visualization or the second visualization at the device; and
indicating the selection to the interactive voice response service.
7 . The method of claim 1 , comprising:
determining whether the device is video-enabled.
8 . The method of claim 1 , comprising:
routing the call through an external telephony system.
9 . The method of claim 1 , comprising:
generating the first visualization during the call; and
generating the second visualization during the call.
10 . A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations comprising:
determining, during a call associated with an interactive voice response service, a first menu option of a current menu of the interactive voice response service;
outputting, for display at a device during the call, a first visualization generated to represent the first menu option;
determining, during the call and based on the current menu including one or more other menu options, a second menu option of the current menu; and
outputting, for display at the device during the call, a second visualization generated to represent the second menu option.
11 . The non-transitory computer readable medium of claim 10 , wherein the first visualization is output before the second visualization is output.
12 . The non-transitory computer readable medium of claim 10 , the operations comprising:
performing a real-time transcription process against audio of the call to determine the first menu option and the second menu option.
13 . The non-transitory computer readable medium of claim 10 , wherein the device is a secondary device in communication with a calling device used to initiate the call.
14 . The non-transitory computer readable medium of claim 10 , wherein one or more of the first visualization or the second visualization includes one or more of image content or video content.
15 . A system, comprising:
one or more memories; and
one or more processors configured to execute instructions stored in the one or more memories to:
determine, during a call associated with an interactive voice response service, a first menu option of a current menu of the interactive voice response service;
output, for display at a device during the call, a first visualization generated to represent the first menu option;
determine, during the call and based on the current menu including one or more other menu options, a second menu option of the current menu; and
output, for display at the device during the call, a second visualization generated to represent the second menu option.
16 . The system of claim 15 , wherein the first visualization is output before the second menu option is determined.
17 . The system of claim 15 , wherein the first menu option and the second menu option are separately determined based on a real-time transcription process performed against audio of the call.
18 . The system of claim 15 , wherein the device is one of a calling device used to initiate the call or a secondary device in communication with the calling device.
19 . The system of claim 15 , wherein the call is routed to a destination through an external telephony system.
20 . The system of claim 15 , wherein the menu options are determined and the visualizations are output using one or more services of a unified communications as a service software platform.