Reference architectures
Voice agent architecture
Speech-to-text, an agent with tools, and text-to-speech in one low-latency loop.
A voice agent is a pipeline that has to finish in well under a second. Audio from the phone line is streamed to a speech-to-text model. The agent receives the transcript, calls the LLM and, if needed, tools such as a booking system. The reply is streamed through a text-to-speech model back to the caller. Call context is held in short-term memory. The diagram marks the two streaming edges where latency matters most.
