gpt-realtime - For reliable, production-ready voice agents
gpt-realtime is OpenAI's new speech-to-speech model for production voice agents, delivering low latency and natural, expressive speech. The Realtime API is now GA, adding key features for developers like remote MCP support, image input, and SIP phone calling.
Replies
Last update seems promising!
I still feels like the API version is weaker than the chatGPT one — can’t wait for the next checkpoints!