Embodiments disclosed herein generally relate to a system and method for transacting at an ATM. A computing system receives a request from the ATM to provide audio commands for an input having one or more components. The computing system generates an audio message for a component of the one or more components. The computing system receives an indication from the user to select an entry from the set of candidate entries as the component. The indication from the user does not include a recitation of the first entry. The computing system maps the indication to a respective candidate in the set of candidate entries. The computing system generates a verification audio message for the user to audibly verify a correct mapping between the indication and the respective candidate in the set of candidate entries. The computing system receives an audible verification from the user.