A vehicle is detected at a drive thru terminal and an automated voice-based dialogue is established with a user in the vehicle and the terminal. An order is placed for a transaction using natural-language speech. The automated voice-based dialogue identifies commands, nouns associated with menu items, adjectives associated with modifying the menu items, prepositions associated with modifying the menu items, and exclamations associated with confirming the order and associated menu items. The automated speech is identified and processed based on a specific lexicon associated with a specific type of restaurant. The speech is translated into actions processed through an ordering system/interface as text-based instructions. Feedback for the order and guidance during the order are provided to the user through: speech played over a speaker associated with the terminal, text displayed on a display, and/or images associated with the ordered items.