OpenAI’s gpt-realtime Enables Production-Ready Voice Agents with End-to-End Speech Processing

2025-09-10 23:00 GMT · 7 months ago aimagpro.com

OpenAI launched gpt-realtime and the Realtime API, enabling production-ready AI voice agents with end-to-end speech processing, lower latency, and natural speech delivery. New features include SIP phone support, image input, MCP server integration, and improved safeguards. Early adopters like Zillow and T-Mobile are testing real-time customer service and search use cases. By Hien Luu