- OpenAI has unveiled 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. Remarkably, the company claims that GPT-Realtime-2 matches the reasoning power of GPT-5.
- These innovations represent a significant leap forward for voice AI, promising more sophisticated interactions where understanding and context are crucial.
- The ability to translate across multiple languages without any delay could revolutionize communication in multilingual environments, making real-time translation accessible and seamless for users around the world.
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.