OpenAI Releases GPT-Realtime: AI Enters Hyper-Realistic Chat Era
OpenAI launches GPT-RealTime: AI's most advanced voice model with natural conversations, multilingual support, and new API features for developers.
"AI Disruption" Publication 7500 Subscriptions 20% Discount Offer Link.
Today, OpenAI released the voice-to-voice model GPT-RealTime designed for developers, and simultaneously updated API functionality, including remote MCP server support, image input, and SIP (Session Initiation Protocol) phone call support.
OpenAI claims this is its most advanced voice synthesis model to date. GPT-RealTime has improvements in following complex instructions, precise tool calling, and generating more natural, expressive speech.
The model can naturally read repeated letters and numbers, seamlessly switch languages, and even capture non-verbal signals like laughter.
New Voice Options
Today, OpenAI also released two new voices, Cedar and Marin, which will be exclusively available in the Realtime API.