gpt-realtime

gpt-realtime is OpenAI's new speech-to-speech model for production voice agents, delivering low latency and natural, expressive speech. The Realtime API is now GA, adding key features for developers like remote MCP support, image input, and SIP phone calling.

gpt-realtime is OpenAI’s speech-to-speech model designed for creating production-ready voice agents. It offers low latency and expressive, natural speech output. The Realtime API is now generally available, featuring developer tools such as remote MCP support, image input capability, and SIP phone calling integration.