OpenAI gives its voice agent superpowers to developers - look for more apps soon

OpenAI has upgraded its Realtime API, making it generally available with enhanced capabilities for voice agents. The update includes support for remote Model Context Protocol servers, image inputs, and phone calling through SIP. OpenAI also launched gpt-realtime, its most advanced speech-to-speech model, featuring improved intelligence, complex instruction following, and multilingual capabilities. Two new voices, Cedar and Marin, are now exclusively available in the API. These developments will enable more sophisticated AI voice applications with better user experiences.