← Latest news 
OpenAI launches three real time audio models turning voice agents into multitaskers
Technology
Published on 7 May 2026
Interruptions and complex requests handled in real time
OpenAI has unveiled three new audio models for developers aimed at making voice agents faster, smarter, and more interactive in real time. GPT-Realtime-2 tackles complex requests even when users interrupt. GPT-Realtime-Translate delivers live multilingual translation, while GPT-Realtime-Whisper provides instant speech to text for captions and notes. Early adopters include companies like Zillow and Priceline.
- GPT-Realtime-2 is built for interruptions and complex requests
- GPT-Realtime-Translate enables live translation across many languages
- GPT-Realtime-Whisper offers near instant speech to text
- Zillow and Priceline are testing these voice tools
Read the full story at The Economic Times
This summarization was done by Beige for a story published on 
The Economic Times