> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.vapi.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.vapi.ai/_mcp/server.

# GPT-Live

> Learn what GPT-Live changes for a Vapi assistant, how its speaker and reasoner work together, whether it fits your use case, and where to start.

GPT-Live is an OpenAI voice model that listens to the caller's audio and generates its own speech. It keeps listening while it speaks, so it can respond to an interruption or a new detail while it's talking.

In Vapi, a GPT-Live assistant pairs that voice model with a second model that does the task work, so the conversation can carry on while your tools run.

> **Note**
>
> **Beta.** If you already have a Vapi assistant or squad, see [Migrate to GPT-Live](/gpt-live/migrate).

## How it works

A GPT-Live assistant has two parts:

#### Speaker

The GPT-Live voice the caller hears. It listens throughout the call, responds to the caller, and decides when to ask the reasoner for help.

#### Reasoner

A separate model that does the task work. It follows your procedures, calls your tools, and returns what it found.

When the speaker needs something done, such as checking a calendar, it **delegates** the task to the reasoner. The reasoner works from the conversation so far and your instructions. Meanwhile the speaker can continue listening and responding to the caller. When the result comes back, the speaker fits it into the current conversation.

Because GPT-Live hears and speaks directly, you don't configure a separate transcriber or text-to-speech provider.

## What changes with GPT-Live

For the caller, the conversation can feel less like taking turns. They can speak over the assistant, add a detail while it's talking, or ask something else while it's checking.

For you, more of the design lives in the two prompts:

* **Decide what happens while work runs.** Which work to start early, what the assistant can usefully ask or answer while it waits, and how it brings the result back into the conversation.
* **Make delegation explicit.** The speaker only starts work when it delegates, so tell it which requests need the reasoner.
* **Plan for generated speech.** All speech, including the greeting, is generated, so exact wording isn't guaranteed.
* **Keep saying and doing separate.** The assistant saying something happened is different from your service confirming it.

[Design conversations](/gpt-live/design) works through these decisions with an appointment-booking example. As an assistant takes on more kinds of work, [reasoner skills](/gpt-live/skills) let you organize each procedure and its tools behind the same conversation.

## In this guide

#### [Make a first call](/gpt-live/quickstart)

Create an assistant and talk to it in a few minutes, with no server of your own.

#### [Design conversations](/gpt-live/design)

Shape a conversation that reaches the caller's goal while work runs alongside it.

#### [Migrate an assistant or squad](/gpt-live/migrate)

Move an existing assistant or squad, compare it with the original, and keep a way back.

#### [Check a feature](/gpt-live/configuration#compatibility)

See what's supported before you build or migrate.

## What Vapi provides

Vapi connects GPT-Live to your phone numbers and tools, and provides call records and observability according to your recording and data settings:

* Browser, Twilio, Vapi SIP, and WebSocket calls.
* Function, API request, and MCP tools, Google Calendar, Google Sheets, and Slack tools, plus built-in Hang Up, transfer, and DTMF tools.
* Speaker and reasoner prompts, reasoner skills, personality packs, and 22 voices.
* Idle-message hooks and HTTP live call control.
* Transcripts, recordings, structured outputs, scorecards, Boards, Monitoring, and Voice Simulations.

Before you commit, check whether your assistant depends on something GPT-Live doesn't support:

| If you need                                      | With GPT-Live                                              |
| ------------------------------------------------ | ---------------------------------------------------------- |
| Exact or prerecorded speech                      | Not available. All speech is generated                     |
| A voice from another provider, or a custom voice | Not available. Choose from 22 OpenAI voices                |
| A squad with handoffs                            | Not supported. Use one assistant, often with skills        |
| Knowledge bases or the Query tool                | Not available. Use a retrieval tool                        |
| Warm transfers, or transfers on browser calls    | Not supported. Blind transfers work on Twilio and Vapi SIP |
| Caller keypad input                              | Supported on native Twilio and Vapi SIP                    |
| Native Telnyx or Vonage numbers                  | Not supported                                              |

The full list is in [Settings and compatibility](/gpt-live/configuration#compatibility).

These pages describe Vapi's GPT-Live integration. OpenAI's API and ChatGPT offer some capabilities, such as web search, custom voices, and image input, that aren't available through Vapi. For background on the model itself, see OpenAI's [GPT-Live documentation](https://developers.openai.com/api/docs/guides/live).

## Cost

A GPT-Live call is billed for voice time by the second, including silence and waiting, plus Vapi's platform fee, the reasoner's token usage, and telephony. See [Cost](/gpt-live/testing#cost) for a worked example and how to check a real call.