API Voice Recognition Integration

In a time now where Siri, Alexa, Google, and various other AI's have been created to analyze voice commands DSP could utilize the Google API for vocal recognition such as "Navigate to Customer targets" or "Process customer master object" or "Show my governance reports" or "Show Compose Requests for Review". This would save many clicks as well as add the wow factor. After watching the demo on the Google API widgets integration for maps and address lookup, it appears the framework is already there. Maybe on the main DSP taskbar next to the status light and quick link and design icons, a microphone button could enable a listening mode in the browser. Using the API to convert text to speech, return the string and parse it against a list of editable key commands listed in a webpage with certain desired actions when a command is given. If security does not permit this action or is not understood, a message could be displayed for a denial of reason why. 

Additional idea: have a text box similar to Cortana on Microsoft allowing you to type your question/command rather than speaking into a microphone.

If the framework of the "listen, recognize, return text string, perform action" is folded into the platform, I'm sure the consultant development is endless for certain commands relevant for our clients or consultants using this in the field.

  • Brad Helman
  • Jun 11 2018
  • Unlikely to Implement
  • Jan 4, 2019

    Admin response

    We are unlikely to implement this at this time.  This could change with real customer demand and market problem solves.

  • Attach files