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:
pnpmadd ai@latest @ai-sdk/openai@latest ws
pnpmadd-D @types/ws @types/node
Delegate work and keep talking
This starts openai/gpt-live-1 without calling another model. Wait for session-started before sending audio.
3
const live =createOpenAI({
1
import{ createOpenAI }from'@ai-sdk/openai';
8 send(live.serializeClientEvent({
6
}).experimental_realtime('openai/gpt-live-1',{ api:'live'});
7
11 }));
9
type:'session-start',
10
config:{ instructions:'You are a helpful voice assistant.'},
4 apiKey: process.env.AI_GATEWAY_API_KEY,
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:
Our Services
8
model:'openai/gpt-5.6-sol',// Any text model
4 );
17
providerOptions:{ openai:{ channel:'commentary'}},
1 const voice = openai.experimental_realtime(
5
6
asyncfunctionhandleDelegation({ delegationId }){
7
const{ text }=awaitgenerateText({
9 prompt: conversationContext,
10
maxOutputTokens:200,
3
{ api:'live'},
13
send(voice.serializeClientEvent({
16 content: text,
18
}));
19 }
2
'openai/gpt-live-1',
14
type:'context-append',
15 delegationId,
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.