Vanderbilt University Medical Center has developed a voice user interface prototype for the electronic health record (EHR). This interaction modality allows caregivers to naturally interact with the EHR through speech and easily surface information needed for patient care. Using artificial intelligence and natural language processing, the Vanderbilt EHR Voice Assistant (V-EVA) accepts voice request inputs, translates voice into text and then uses the natural language understanding engine to map the text to intents and synthesize results. V-EVA returns results to the user as voice replies, textual information and graphical data representations. These design principles support the busy caregiver workflow and decrease the EHR burden on providers.