@FinanceYF5: 1/ Voice Agent Upgraded: OpenAI Launches GPT-Realtime-2, Bringing GPT-5-Level Reasoning to Real-Time Voice API. Voice assistants no longer just "understand and respond" — they can think while listening, and problem-solve while chatting.
Summary
OpenAI has launched GPT-Realtime-2, integrating GPT-5-level reasoning into the real-time voice API, enabling voice assistants to think and solve problems in real time during conversations.
View Cached Full Text
Cached at: 05/08/26, 09:54 AM
1/🚀 Voice Agent Upgraded
OpenAI launches GPT-Realtime-2, bringing GPT-5-level reasoning into the real-time speech API.
Voice assistants are no longer just “understand and respond” — they can now think while listening, chat while solving problems. 👇 https://t.co/zzQdH0kAV3
Similar Articles
@seclink: OpenAI Launches GPT-Realtime-2, Its Most Intelligent Voice Model to Date. The model features GPT-5-level reasoning, a 128,000 token context window, and supports adjusting 'effort level' for more natural conversation. It can pair with GPT-R…
OpenAI released the GPT-Realtime-2 voice model, featuring GPT-5-level reasoning capabilities and a 128,000 token context window. It supports real-time translation from over 70 input languages to 13 output languages, achieving 96.6% accuracy on the Big Bench Audio Intelligence benchmark. Greg Brockman called it a milestone in voice translation.
This is the new ChatGPT Voice, powered by GPT-Live
OpenAI has released the new generation ChatGPT voice feature powered by GPT-Live, enabling full-duplex real-time conversations, supporting interruption, intelligent reasoning, web search, and real-time translation, making interactions more natural and intelligent.
@FinanceYF5: OpenAI's new voice model Bidi 1 first test exposure - Bidirectional voice design: while you speak, it listens; you can interrupt mid-way to switch tasks immediately, no longer grabbing the conversation when you pause. It also supports real-time translation, and context memory is much stronger than the current Advanced Voice. It's now being pushed to a small group, ChatGPT …
OpenAI's new voice model Bidi 1 first test exposure, supports bidirectional voice design, real-time translation, and stronger context memory, currently being pushed to a small group on ChatGPT.
Build Hour: GPT-Realtime-2
OpenAI released GPT Realtime-2 and two accompanying models during Build Hour, enhancing the intelligence and naturalness of voice interaction. It supports 128k context, parallel tool calls, and dynamic voice cloning, demonstrating production-grade applications such as voice-driven shopping assistants and analytics dashboards.
We’re introducing three audio models in the API
OpenAI has launched three real-time audio models in the API, including a real-time translation model GPT Realtime Translate that supports 70 languages and a voice agent GPT Realtime 2 with reasoning capabilities, enabling developers to build more natural voice interaction interfaces.