The Agents Framework is designed for building realtime, programmable participants that run on servers. Use it to create conversational, multi-modal voice agents that can see, hear, and understand.
This package contains the OpenAI plugin, which allows for TTS, STT, LLM, as well as using the Realtime API. Refer to the documentation for information on how to use it, or browse the API reference. See the repository for more information about the framework as a whole.