Have been experimenting with Dragon NaturallySpeaking voice-recognition, in a few weeks and today I was able to complete all of my progress notes with a combination of which recognition and templating using electronic medical record.
It certainly easier than just typing the rhythm is something that will take some getting used to. Certainly, I can't do the voice-recognition in the office with my patients.
I bought an array microphone to experiment with that in the office. It seems to work OK the headset works a little bit better I think.
The most recent investment was in a good medical dictionary. It certainly does make a difference.
For example, I'm using a right now (and have been using it for all of this post). Here's a fake patient dictation: