Provided is an improved direct store delivery (DSD) system for providing customized information to a user. The DSD system includes a device that receives a first voice command from the user and determines a current location of the user. The first voice command is then transformed into a first text request based on a conversion of the points in speech to points in data. Further, the first text request is processed to determine a first set of information, based on a current location of the device, to be provided audibly to the user. The first set of information is transmitted to the user through speech. The device further receives a second voice command from the user to interact with the first set of information. The second voice command is processed to determine a final set of information, and the final set of information is visually displayed to the user in an instance in which the user has arrived at a desired location.