Hi,
You need something like this: https://developer.mozilla.org/en-US/docs/Web/API/Web_Speech_API/Using_the_Web_Speech_API
This component on Forge says they are using this API to control volume on an HTML video. You may be able to adapt this for your needs: https://www.outsystems.com/forge/component-overview/5292/html5-video-voice-control
Maybe there are other components at Forge that uses this API (didn't find any on a first search).
Cheers