How to configure webkitSpeechRecognition with Virtual Agent

Surya Prakash · 2 hours ago

Hi Community,

I was looking for some features that can be useful when integrated with Virtual Agent and found this "webkitSpeechRecognition". It would be a great help if anyone can share the process to build this feature and integrate the Virtual Agent with webkitSpeechRecognition.

Since this was feature was new to me, it would be great help if anyone can share step by step procedure to build it or please share if you have any detailed documentation to build this.

Thanks in Advance!!!

M Iftikhar · an hour ago

Hi @Surya Prakash ,

Integrating the webkitSpeechRecognition API with ServiceNow Virtual Agent is possible, but it requires some client-side development. The general process is to capture the user’s speech, convert it to text, and then pass that text to the Virtual Agent’s input.

Integration Approach

You can achieve this by creating a Service Portal Widget or a custom UI Script that handles:

Initializing webkitSpeechRecognition – starting the speech recognition service in the browser (Chrome recommended).
Capturing and transcribing speech – converting the user’s voice into a text string.
Sending text to Virtual Agent – injecting the transcript into the Virtual Agent chat input programmatically.
Handling events – managing start/stop actions and errors for smooth user interaction.

Here are some community examples and demos you can follow:

Thanks & Regards,
Muhammad Iftikhar

If my response helped, please mark it as the accepted solution so others can benefit as well.

Surya Prakash · an hour ago

Hi @M Iftikhar,

Thanks for the reply. Will go through the links shared. Also, do you have any idea of using this feature to enable for Catalog Items or Incidents as well? Example: Opening a Catalog Form in portal using voice command, Filling the fields on the catalog form using voice command etc..

Thanks,

Surya