What version of Windows are you running?
I am not familiar with the functionality of Windows 8, but in Vista and 7, there is a built-in speech recognition system with decent accuracy. Now, out of the box, it is NOT really something with SIRI-like functionality. It's more of an alternative to Dragon NaturallySpeaking, primarily used for dictating text and/or interacting with GUIs.
However, there is a surprisingly-little-known download available from Microsoft called Windows Speech Recognition Macros (available here: http://www.microsoft.com/en-us/download/details.aspx?id=13045) that sounds like it might be up your alley. It's not the most user-friendly and requires you to write simple scripts, since it was released basically as a tech preview. Personally, I have a feeling that a good chunk of this is going to be under the hood of the new Windows 10 Cortana.
Anyways, the key benefit is that it will let you do all of the custom command creation that you want to be able to do. And since it's just an add-on for WSR, the whole thing would be free. Depending on how much time you're willing to spend setting things up, you could even get your computer to speak back to you in response to prompts. You would just need to use a text-to-speech program (FYI, those have nothing to do with whether or not you can type) that can run from the commandline, and then you could script custom responses for your commands.