OpenAI Realtime API

OpenAI Realtime API

Low‑latency speech‑to‑speech API for building real‑time voice experiences

Website
AI Tools
AI Voice & Audio
OpenAI Realtime API screenshot

The OpenAI Realtime API lets developers add fast, low‑latency speech‑to‑speech interactions to apps via a persistent WebSocket connection. Powered by GPT‑4o, it streams audio input and output, supports function calling, multiple preset voices, and integrates with popular audio SDKs. Ideal for conversational agents, language learning, customer support, and any real‑time audio‑driven experience.