GPT-Live 1.1 from OpenAI is now available on AI Gateway.
GPT-Live 1.1 is a full-duplex voice model, so it listens while it speaks and a caller can pause, interrupt, or add detail mid-reply. Compared with the previous GPT-Live model, it transcribes speech more accurately and keeps a more consistent accent and voice across languages. It uses the same Live endpoint and client delegation, so an existing GPT-Live integration only needs the new model ID.
Copy link to headingSimple example without delegation
Run openai/gpt-live-1.1 by itself:
import { createOpenAI } from '@ai-sdk/openai';
const live = createOpenAI({ apiKey: process.env.AI_GATEWAY_API_KEY, baseURL: 'https://ai-gateway.vercel.sh/v1',}).experimental_realtime('openai/gpt-live-1.1', { api: 'live' });
const { url, headers } = await live.getServerWebSocketConfig();
send(live.serializeClientEvent({ type: 'session-start', config: { instructions: 'You are a helpful voice assistant.' },}));
Copy link to headingDelegate work and keep talking
Turn on client delegation, and use the session instructions to tell GPT-Live 1.1 when to ask for help. It asks by sending delegation-created. Answer with any text model on AI Gateway and return the result on the commentary channel for GPT-Live to speak. This example uses openai/gpt-6.2-sol and builds on the session above:
send(live.serializeClientEvent({ type: 'session-start', config: { instructions: 'Ask the application for help with order questions.', providerOptions: { openai: { delegation: { type: 'client' } } }, },}));
async function handleDelegation({ delegationId }) { const { text } = await generateText({ model: 'openai/gpt-6.2-sol', // Any text model prompt: conversationContext, });
send(live.serializeClientEvent({ type: 'context-append', delegationId, content: text, providerOptions: { openai: { channel: 'commentary' } }, }));}
Your application controls delegated work and its permissions, confirmations, and cancellation. Delegated model requests are billed separately through AI Gateway, and voice-session usage continues while they run. These snippets omit the WebSocket connection, event parsing, transcript assembly, audio streaming, and shutdown. See the GPT-Live guide for connection setup, audio streaming, and complete examples.
Try GPT-Live 1.1 in the model playground.
AI Gateway provides a unified API for calling models, tracking usage and cost, and configuring retries, failover, and performance optimizations for higher-than-provider uptime. It includes built-in custom reporting, Zero Data Retention support, budgets for API keys, routing rules, and more.
AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.
You can view all models available on AI Gateway.