- 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, GPT-Realtime-2 matches the reasoning capabilities of GPT-5.
- This development elevates AI’s ability to understand and respond to complex conversations in real-time, potentially transforming how we interact with digital assistants and virtual agents.
- The introduction of these models signifies a significant step forward for OpenAI’s voice technology, positioning them at the forefront of developing AI that can engage in sophisticated, context-aware dialogue.
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.