- OpenAI has released three new voice models—GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper—that can now reason in real time, translate across 70+ languages, and transcribe live speech. Notably, GPT-Realtime-2 is claimed to match the reasoning capabilities of GPT-5.
- These advancements bring AI closer to achieving human-like conversational intelligence by enabling more sophisticated responses in real-time conversations, translating between multiple languages seamlessly, and accurately transcribing spoken words.
- The introduction of these models signifies a significant leap forward in AI’s ability to handle complex tasks such as reasoning and translation during voice interactions, potentially revolutionizing fields like customer service, education, and personal assistants.
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.