Models

GPT Live 1

Model id: gpt-live-1

  • Audio
  • Tools

OpenAI’s live voice. You speak; it answers in voice and text. Tools run on a delegated model.

Best for

a voice call that also needs tools.

Provider
OpenAI
Context window
Not published
Release date
2026-09-10

Pricing

Session
$0.0013 / s

Amounts in Canadian dollars, converted at the Bank of Canada indicative rate (2026-09-21).

Performance

Reading

Last 7 days

Not enough data to display the chart.

Activity

Tokens

Top 5 tools · last 7 days

Tool activity appears only when at least 2 workspaces have used this model recently.

Availability

Availability (%)

Last 7 days

Operational probes
99.98% over 7 days
Samples
9,210

View service status

Quick start

Open a Live session with a tonia_ key and the exact model id below.

wscat

wscat -c "wss://pass.tonia.ca:8443/v1/realtime?provider=openai&model=gpt-live-1&mode=native&transcripts=1" \
  -H "Authorization: Bearer $TONIA_API_KEY"

Python — Live session

import os
import struct

from tonia import Tonia

pcm = struct.pack("<2400h", *([0] * 2400))
with Tonia(api_key=os.environ["TONIA_API_KEY"]) as client:
    with client.realtime.connect(
        provider="openai",
        model="gpt-live-1",
        mode="native",
        transcripts=True,
    ) as session:
        session.send_audio_append(pcm, mime="audio/pcm")
        print(session.recv(timeout=60.0))

TypeScript — Live session

import { Tonia } from "@tonia-router/sdk";

const pcm = new Uint8Array(4800);
const client = new Tonia({
  apiKey: process.env.TONIA_API_KEY,
});
const session = await client.realtime.connect({
  provider: "openai",
  model: "gpt-live-1",
  mode: "native",
  transcripts: true,
});
session.sendAudioAppend(pcm, "audio/pcm");
console.log(await session.recv(60_000));
session.close();

Create a key in the portal