GPT-Live 1 now available on AI Gateway
By Steven Van ·
OpenAI's full-duplex voice model reaches AI Gateway, letting apps delegate background work to any text model mid-conversation.
GPT-Live 1 from OpenAI is now available through Vercel's AI Gateway. The model is full-duplex, meaning it can listen and speak at the same time rather than relying on turn detection, so a user can pause, interrupt, or add detail while GPT-Live is speaking.
GPT-Live 1 also supports client delegation: an application can choose a background model to handle deeper work independently of GPT-Live 1 while the conversation continues. A basic session runs only the voice model. Using it requires AI SDK 7, @ai-sdk/openai 4.0.67 or later, and a WebSocket client.
Vercel
The platform for frontend developers — deploy, preview, and scale web apps and AI agents with zero config.
View Vercel →