Explain to me this concept of “emotion capture” that you used.

We didn’t now what else to call it because it’s not motion capture, which is when your actors’ physical performance is driving the computer. We were just recording their sound only, so we jokingly called it emotion capture because we had all the actors in this one space at one time wearing flip flops and hats and side arms, jumping off apple boxes. It gave it a theater of the absurd feeling. We were just trying to get a really lively soundtrack, get any sort of anomalies we could hold onto and cherish.

Everything that we were trying to do was to make it feel like there actually is a lizard talking to a tortoise. We’re trying to fabricate this sense that it happened. It wasn’t manufactured. The term “emotion capture” was just a poke at motion capture to say, “Look, we’re doing something different.” The actors were all saying this isn’t how you do animation. A lot of them worked on animated films and they never wore hats and jumped around and shot guns and running around while doing them.

What’s an example of something you were able to change because all the actors were together in the same room?

I would say when Rango and Beans (Isla Fisher) are together, when she freezes for the first time, and he’s got her arm around her, and he’s doing, “What are you doing?” “I was not,” that sort of thing. If you had one person in the room and then a few months later another person in the room, and you were cutting the different audio together you would never get that sort of awkwardness.

– Read the full Q&A with Gore Verbinski at VanityFair.com