Since I feel really bad about being so snide earlier, I'll give you a bit of production advice re voice editing -
There's two ways of changing the apparent pitch of a voice in digital post production - pitch shifting, which decreases/increases the actual, physical pitch of the signal, and formant shifting, which is a little cleverer. I don't want to get into a big technical description into what formants are, but it's to do with the shape and length of the object causing the sound - in this case, a throat. Higher formants make the voice sound high and squeaky despite being at the same pitch in pure musical terms, and lower formants make the voice deep and boomy. This is why it sounds different when a man (low formant), a woman (higher formant) and a child (high formant) all sing the same note.
The reason I'm bringing up formant shifting is because, even when done to extremes, it leads to a more comprehensible result than pitch shifting. For speech to be easily understandable, we have to have high frequency 's' and 't' sounds, which are lost when a signal is pitch shifted downwards more than a little.
Since verbal comedy is only funny if you can hear the words, you might want to think about using formant shifting instead of pitch shifting, especially if you're shifting your voice down. You should also get as close as you can to the voice of one of the characters, and then use post production to nudge that signal a few semitones down/up, rather than using your normal speaking voice range and making pitch shifting do all the work, because it can't and won't.
Oh yeah, to do formant shifting, there's a ton of free VST plugins out there which you can use with Audacity or anything more upmarket than that. Or, if you have Auto-Tune, it has a Formant knob - turn off all the pitch correction settings first, though, or Bosco will sound like T-Pain.