GenAIWiki
Search
intermediate

Build a Voice Session with GPT-Live-1

Stand up an OpenAI GPT-Live-1 session: full-duplex voice, $0.05/min billing, backend delegation, and when to use ASR instead.
gpt-livevoiceopenairealtimeasr

11 min read

FeaturedUpdated todayVerified recentlyInformation score 92

Key insights

Concrete technical or product signals.

  • Live is the conversation front-end. Delegation is where tools and facts live.
  • Sessions are $0.05/min billed per second; backend tokens are extra.
  • GPT-Live-1 mini is ChatGPT-only. There is no mini API ID.

Use cases

Where this shines in production.

  • Replacing a chained STT to LLM to TTS stack
  • Voice agents that keep talking during a lookup
  • Deciding that you only needed ASR

Limitations & trade-offs

What to watch for.

  • This is not a WebRTC implementation dump. Follow the official quickstart.
  • Free API tier is not supported on the model card.
  • Do not use Live for batch transcription.

GPT-Live-1 is OpenAI's full-duplex voice model. The API ID is gpt-live-1. It listens and speaks at the same time, handles interruptions, and delegates reasoning and tool use to a backend agent.

This is not an ASR-only model. Muse Voice Transcribe and Gemini 3.5 Transcribe return text. GPT-Live-1 speaks.

1. Decide if you actually need Live

Use GPT-Live-1 when the product is a spoken conversation that should continue while a backend looks something up.

Use Muse Voice Transcribe or Gemini 3.5 Transcribe when the product is a transcript.

GPT-Live-1 mini is the ChatGPT free-tier voice default in the system card. There is no gpt-live-1-mini API model card. Do not invent one.

2. Split conversation from work

Official getting-started docs describe two parts:

  • GPT-Live handles conversation style and when to ask the backend for help. Keep that prompt short.
  • The backend holds tools, business rules, and longer tasks. Use Responses delegation for a managed backend, or client delegation when your app must control execution.

Interrupting speech does not automatically cancel delegated backend work.

3. Connect the first session

Start with the official GPT-Live WebRTC quickstart:

  1. Keep the API key on a trusted server. Serve the browser page over HTTPS or localhost.
  2. Create the Live session on the server and exchange the browser connection offer.
  3. Wait for session.started, then speak and listen.
  4. Ask a question that needs current information if you attached a web-search backend.
  5. Close the session to collect usage and release the connection.

Other official connection paths: WebSockets for server-side audio, sideband controls for an existing session, and telephony/SIP for phone integrations.

4. Price the session correctly

The official API card bills voice sessions at $0.05 per minute, per second. Session duration is not rounded up to the next whole minute. Backend model and tool usage is billed separately.

The live model has a small context window. Put tool schemas and procedures in the backend prompt.

Image and video are not supported on the API card. Structured outputs and fine-tuning are not supported.

5. Prompt only the handoff rules

Official prompting guidance: list backend capabilities the backend actually has, then write concrete delegate / do-not-delegate rules. The live model must not promise a booking, guess a price, or claim an action finished before the backend confirms it.

Official sources

Continue learning

Related models, implementation guides, comparisons, and concepts.