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

OpenAI has introduced the GPT-Realtime-2.1 and GPT-Realtime-2.1-mini models to its API, focusing on improved performance for voice-based applications. By utilizing enhanced caching techniques, the company has reduced p95 latency by at least 25%, allowing developers to build more responsive interactive agents.