A system and method for providing a message-based communications infrastructure for automated call center operation is described. A call from a user into a call center is accepted. The accepted call includes a stream of transcribed verbal speech utterances. Each transcribed verbal speech utterance is recorded as a user message. The accepted call is assigned to a session, which is then assigned to an agent. The call is progressively processed in the assigned session by presenting each user message to the assigned agent, executing commands responsive to the assigned agent, and sending an agent message to the user. The agent message includes a stream of synthesized audible speech utterances.