How to Click Element when Voice heard? - Voice-to Text then Trigger click on an element 'activity'

Dear Community;

I need the robot to click on an element when it sees or hears what’s being pronounced. Details below;

  1. Voice to Text conversion activity (Data Source, Video file)
  2. Above text stored as an Output DataTable
  3. Split text stored in above dataTable into words not exceeding (10 Characters)
  4. Ability for the robot to use above DataTable as an ear / listening to what is being said in the video file in Step1, and perform a click element when it hears the words being repeated
  5. Above steps repeated till all data in our Output DataTable is complete.

Step 3 above has me scratching my head, am going bald. Your kind assistance will be greatly appreciated.

Thanks.