Realtime API
Build low-latency, multimodal LLM applications with the Realtime API.
The OpenAI Realtime API enables low-latency communication with models that natively support speech-to-speech interactions as well as multimodal inputs (audio, images, and text) and outputs (audio and text). These APIs can also be used for realtime audio transcription.
With this library, you can connect to OpenAI Realtime API and interact with conversational models in a multi-channel way (audio-to-audio, text-to-audio).
Integrate this component in your application with 3 steps:
1. Drag the RealtimeAgent block to the application screen
2. Configure the agent and give him the desired tools
3. Start the session
Documentation:
https://platform.openai.com/docs/guides/realtime
https://platform.openai.com/docs/api-reference/realtime