> For the complete documentation index, see [llms.txt](https://docs.aimlapi.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aimlapi.com/api-references/realtime-models.md).

# Realtime Models

Overview of the available realtime (live) voice models.

## Overview

Realtime (live) models hold a continuous, two-way voice conversation over a single WebSocket connection. You stream microphone audio in, and the model streams spoken audio (and, where supported, text) back while the user is still in the conversation. Each model family keeps its provider's own WebSocket protocol, so the official OpenAI and Google GenAI SDKs work with only the base URL and the API key changed.

How sessions work, authentication and browser client secrets, billing, limits and errors are described in the [Realtime Sessions](/capabilities/realtime-sessions.md) guide.

{% hint style="info" %}
You can try realtime models in the [Playground](https://aimlapi.com/app/): open the model picker and choose the **Realtime** tab.
{% endhint %}

## All Available Realtime Models

<table data-header-hidden="false" data-header-sticky data-full-width="true"><thead><tr><th width="320">Model ID + API Reference link</th><th width="132">Developer</th><th>Protocol</th></tr></thead><tbody><tr><td><a href="/api-references/realtime-models/openai/gpt-realtime-2.1.md">openai/gpt-realtime-2.1</a></td><td>OpenAI</td><td>OpenAI Realtime</td></tr><tr><td><a href="/api-references/realtime-models/openai/gpt-realtime-2.1-mini.md">openai/gpt-realtime-2.1-mini</a></td><td>OpenAI</td><td>OpenAI Realtime</td></tr><tr><td><a href="/api-references/realtime-models/openai/gpt-live-1.md">openai/gpt-live-1</a></td><td>OpenAI</td><td>GPT-Live</td></tr><tr><td><a href="/api-references/realtime-models/xai/grok-voice-think-fast-2.0.md">x-ai/grok-voice-think-fast-2.0</a></td><td>xAI</td><td>OpenAI Realtime (xAI dialect)</td></tr><tr><td><a href="/api-references/realtime-models/google/gemini-3.8-live.md">google/gemini-3.8-live</a></td><td>Google</td><td>Gemini Live</td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.aimlapi.com/api-references/realtime-models.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.