OpenAI Releases GPT-Realtime-2.1 and GPT-Realtime-2.1-mini for Low-Latency Voice Agents in the API

OpenAI has released GPT-Realtime-2.1 and GPT-Realtime-2.1-mini models designed to support low-latency voice agents through its API. The new models enable developers to build voice-based applications with reduced response times. GPT-Realtime-2.1-mini offers a lighter variant for applications requiring smaller computational footprints, while the full GPT-Realtime-2.1 provides enhanced capabilities. These releases expand OpenAI's offerings for real-time voice interaction, allowing developers greater flexibility in integrating voice agent functionality into their applications.