Cody
en
ENESFRDEJAKOPT-BRPLAR
Log in · Assist
Start free
Agents
Cody Assist logoCody AssistKnowledge and supportCody Convert logoCody ConvertProactive website agentCody Clear logoCody ClearCompliance-gradeCody Live logoCody LiveAvatars and experiences
All agentsPricing
Resources
BlogUse casesPrompt librarySkill libraryModel library
Company
AboutContact
All models
Voice & realtimeLive
OpenAI

GPT-Live 1

OpenAI's full-duplex voice frontend for natural conversation that delegates deeper reasoning and actions to a separate backend agent.

Open provider docsSee key facts

Plain-English overview

What GPT-Live 1 actually is

GPT-Live 1 listens and speaks at the same time, so it can handle pauses, acknowledgements, interruptions, and background noise without forcing every exchange into rigid turns. It also provides transcripts and response text alongside the live audio.

The architecture separates conversation from deeper work. GPT-Live 1 manages the voice experience while a Responses model or an application-operated agent handles reasoning and approved tools. The published voice price therefore excludes backend model usage, tools, telephony, and application infrastructure.

Good fit for

  • Natural customer-service and scheduling calls
  • Voice interfaces that must keep talking while work runs
  • Teams that want to choose or operate the backend agent

Category comparison

The facts that matter for voice models

These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.

Price basis
$0.05 / voice minute + backend usageToken-, character-, or minute-based price for the listed access route.
Interaction mode
Full-duplex voice frontend with delegated backendSpeech-to-speech, audio-to-audio, or streamed text-to-speech behavior.
Published latency
Not publishedProvider-published measurement with its stated exclusions; not a Cody test.
Languages
Multiple accents, dialects, and languages; exact list not publishedProvider-documented language coverage or a clear unpublished marker.
Tools & control
Responses or client delegation to backend agents and toolsNative function calling, reasoning, or speech-control features.
Context or input limit
Not publishedDocumented token or character limit where it is meaningful.

API and provider access

Where to get GPT-Live 1

OpenAIGPT-Live 1 model docsCurrent price, model ID, modalities, features, and rate limits.OpenAIGPT-Live getting startedWebRTC, WebSocket, sideband, and telephony integration guidance.

Availability

Regions and access stage

Available through OpenAI's Live API for browser, server, and telephony voice applications.

Direct access follows OpenAI's live supported-country list; the Free API tier is not supported for this model.

Check live availability

Data and training

The route matters.

OpenAI says API content is not used for training by default. Default abuse-monitoring logs may be retained up to 30 days, with additional controls available to qualifying organizations.

This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.

Read the provider policy

Frequently asked questions

GPT-Live 1 FAQ

What is GPT-Live 1?

OpenAI's full-duplex voice frontend for natural conversation that delegates deeper reasoning and actions to a separate backend agent. GPT-Live 1 listens and speaks at the same time, so it can handle pauses, acknowledgements, interruptions, and background noise without forcing every exchange into rigid turns. It also provides transcripts and response text alongside the live audio.

When was GPT-Live 1 released?

GPT-Live 1 was released on September 10, 2026 according to the cited provider materials.

Where can I access GPT-Live 1?

Available through OpenAI's Live API for browser, server, and telephony voice applications. The access routes listed in this guide are OpenAI.

How much does GPT-Live 1 cost?

$0.05 / voice minute. Voice sessions are billed per second without whole-minute rounding. Backend model and tool usage is billed separately, as are telephony and application infrastructure.

Where is GPT-Live 1 available?

Available through OpenAI's Live API for browser, server, and telephony voice applications. Direct access follows OpenAI's live supported-country list; the Free API tier is not supported for this model.

Is my GPT-Live 1 API data used for training?

OpenAI says API content is not used for training by default. Default abuse-monitoring logs may be retained up to 30 days, with additional controls available to qualifying organizations. The policy belongs to the provider route and account terms, so verify it again before production use.

Related comparisons

Head-to-head comparisons

View category →

  1. GPT-Live 1 vs GPT-Realtime-2.1

    OpenAI's realtime speech-to-speech reasoning model for tool-using voice agents that also need text and image context.

    Open full comparison

  2. GPT-Live 1 vs Gemini 3.1 Flash Live Preview

    Google's preview audio-to-audio model for low-latency dialogue with multimodal awareness, thinking, search grounding, and function calling.

    Open full comparison

  3. GPT-Live 1 vs Eleven v3 Conversational

    ElevenLabs' expressive realtime text-to-speech model for natural dialogue, emotional delivery, audio tags, and more than 70 languages.

    Open full comparison

  4. GPT-Live 1 vs Inworld Realtime TTS-2

    Inworld's newest expressive realtime text-to-speech model, designed to remember conversational delivery and speak in more than 100 languages.

    Open full comparison

  5. GPT-Live 1 vs Grok Voice Think Fast 2.0

    SpaceXAI's current realtime speech-to-speech model for sub-second conversational agents with tool access.

    Open full comparison