OpenAI Brings GPT-5 Reasoning to Real-Time Voice

OpenAI has released three new voice models: GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper. Each handles a distinct function, separating conversational reasoning, translation, and transcription into specialized orchestration components rather than bundling them into one product. GPT-Realtime-2 is OpenAI's first voice model with GPT-5 class reasoning, designed to handle complex requests while maintaining natural conversation flow. The move aims to reduce the costly workarounds enterprises currently build to manage context limits in voice agent deployments.