Hey Teleman,
If you're working on a Mac, there is a work around for this that I've been using. If you go to System Preferences>Accessibility>Dictation>Open Dictation Preferences you can turn dictation on. Then, go back to the Dictation section in Accessibility and make sure you check Enable the dictation keyword phrase.
Then use a wireless mouse to click the button to make sure the plugin is receiving data, move the point off the button and go back into a T-Pose and say "Computer, press Return key". Sometimes it takes a few tries for the speech recognition to work, but once it does you should get out of calibrating and into being able to capture poses on the model.
Not sure if there's a similar option for Windows.