We introduce a method for predicting a control signal from another related signal, and apply it to voice puppetry: Generating full facial animation from expressive information in an audio track. The voice puppet learns a facial control model from computer vision of real facial behavior, automatically incorporating vocal and facial dynamics such as co-articulation. Animation is produced by using audio to drive the model, which induces a probability distribution over the manifold of possible facial motions. We present a linear-time closed-form solution for the most probable trajectory over this manifold. The output is a series of facial control parameters, suitable for driving many different kinds of animation ranging from video-realistic image warps to 3D cartoon characters.