A system for user interaction with a building automation system (BAS). The system includes a user device configured to accept vocal inputs and produce audio outputs, and a server in communication with the user device and a BAS controller. The server is configured to translate a vocal input to input text, and determine and store a conversation context based on the input text. The server is further configured to determine a desired output corresponding to the input text. Additionally, the server is configured to receive, from the BAS controller, BAS data corresponding to the desired output, and generate at least one audio output from the BAS data. The user device outputs the at least one audio output, and the server is configured to apply the conversation context to a subsequent vocal input.