- OpenAI has released three new voice models, GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper, which can reason in real time, translate across 70+ languages, and transcribe live speech.
- The GPT-Realtime-2 model is said to match the reasoning capabilities of GPT-5, marking a significant advancement in AI’s ability to engage in complex conversations.
- These models demonstrate OpenAI’s continued focus on enhancing natural language processing for real-time applications, pushing the boundaries of what AI can achieve in voice and text interactions.
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.