Most people are familiar with the idea of using a keyboard to type up a document, send and e-mail or play games on a computer. Automatic speech recognition (“you talk, it types”) can also be used to do these tasks. The authors investigate what happens when the user has dysarthria, examining the capability of the software to adapt to the characteristics of the individual’s dysarthric speech, and to tolerate increased variability. They outline ways to help people with more marked dysarthria access the programs. They conclude that current commercially available automatic speech recognition products can be viable for mild or moderate dysarthric users.