- OpenAI has released three new voice models—GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper—that can reason in real time, translate across 70+ languages, and transcribe live speech. Notably, the GPT-Realtime-2 model is said to bring reasoning capabilities that match GPT-5.
- This advancement positions OpenAI’s voice models at a level previously thought only achievable by more advanced AI systems like GPT-5, enhancing their utility in real-time applications such as live translation and intelligent responses during conversations.
- The release of these new models underscores OpenAI’s commitment to advancing the capabilities of its AI technology, particularly in natural language processing for voice interactions, which could have significant implications for various sectors including communication services, customer support, and more.
Originally published at the-decoder.com. Curated by AI Maestro.
Stay ahead of AI. Get the most important stories delivered to your inbox — no spam, no noise.