Hi ServiceNow Community,
I'm exploring ways to enhance the user experience of ServiceNow's Virtual Agent by adding voice interaction capabilities. Currently, I'm focusing on enabling users to interact with the Virtual Agent via voice, both on web browsers and mobile devices.
My initial research focuses on using the Web Speech API to convert user speech to text. I've reviewed the capabilities of the API (e.g., link to Google Chrome demo), and it appears to offer the functionality I need to capture and transcribe user voice input within a browser.
My current approach involves triggering a Javascript function utilizing the Web Speech API after the Virtual Agent is invoked. Is it feasible to execute Javascript code within the Virtual Agent context after a user interaction? Would this be a viable method for integrating voice recognition?
Alternatively, are there any other recommended approaches or best practices for integrating voice recognition into the Virtual Agent? Any insights or suggestions would be greatly appreciated.
Thanks in advance for your help!
