Prismix
Vercel — AI · · 2 min read

GPT-Live 1 now available on AI Gateway

#model-release #voice #partnership

Mirrored from Vercel — AI for archival readability. Support the source by reading on the original site.

Like Read original ↗

GPT-Live 1 from OpenAI is now available on AI Gateway.

GPT-Live 1 is a full-duplex voice model and can listen and speak at the same time. Many voice models use turn detection to respond. Full duplex removes that boundary, so a user can pause, interrupt, or add detail while GPT-Live is speaking.

GPT-Live 1 also supports client delegation. Client delegation lets you choose the background model independently from GPT-Live 1. A basic session runs only the voice model. When deeper work is needed, your application can handle delegation-created with any text model on AI Gateway while the conversation continues.

Install AI SDK 7, @ai-sdk/openai 4.0.67 or later, and a WebSocket client:

pnpm add ai@latest @ai-sdk/openai@latest ws
pnpm add -D @types/ws @types/node

Copy link to headingSimple example without delegation

This starts openai/gpt-live-1 without calling another model. Wait for session-started before sending audio.

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', { api: 'live' });


send(live.serializeClientEvent({
  type: 'session-start',
  config: { instructions: 'You are a helpful voice assistant.' },

Copy link to headingDelegate work and keep talking

You can call a text model for GPT Live to delegate to, then return the result on the commentary channel for it to speak. This example uses openai/gpt-5.6-sol, but you can substitute any text model available on AI Gateway:

const voice = openai.experimental_realtime(
  'openai/gpt-live-1',
  { api: 'live' },
async function handleDelegation({ delegationId }) {
const { text } = await generateText({
model: 'openai/gpt-5.6-sol', // Any text model
prompt: conversationContext,
maxOutputTokens: 200,
send(voice.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; voice-session usage continues while they run. These snippets omit WebSocket connection, event parsing, transcript assembly, audio streaming, and shutdown. See the GPT-Live guide in the AI Gateway docs for connection setup, audio streaming, and complete examples. For all audio models on AI Gateway, go to the model list.

Discussion (0)

Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.

Sign in →

No comments yet. Sign in and be the first to say something.

More from Vercel — AI