OpenAI’s new voice model brings GPT-5-level reasoning to real-time conversations

• OpenAI has unveiled three new voice models, GPT-Realtime-2, GPT-Realtime-Translate, and GPT-Realtime-Whisper, capable of real-time reasoning that matches GPT-5.
• The models can now translate across 70+ languages in real time and transcribe live speech accurately.
• This advancement significantly enhances the utility of AI voice assistants by providing them with advanced language understanding and translation capabilities.

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.

Please enable JavaScript in your browser to complete this form.

Name *

First

Last

Name Email

Email *

Submit