I would love to add that... I have researched it before.
Implementing voice recognition would mean another significant dependency,
which needs to be cross-platform.
It's a big job; and speech recognition usually needs to sample how you speak.
That means some interface needs to be created for that analysis.
The bad news is that this probably won't be added anytime soon.
The good news is that Qt (which is what we use) might provide speech recognition in the future.
https://wiki.qt.io/QtSpeech