> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ag2.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# autogen.agentchat.realtime.experimental.clients.oai.OpenAIRealtimeWebRTCClient

<h2 id="autogen.agentchat.realtime.experimental.clients.oai.OpenAIRealtimeWebRTCClient" class="doc doc-heading">
  <code class="doc-symbol doc-symbol-heading doc-symbol-class" />

  <span class="doc doc-object-name doc-class-name">OpenAIRealtimeWebRTCClient</span>
</h2>

```python theme={null}
OpenAIRealtimeWebRTCClient(
    *,
    llm_config: LLMConfig | dict[str, Any],
    websocket: WebSocket,
    logger: Logger | None = None
)
```

(Experimental) Client for OpenAI Realtime API that uses WebRTC protocol.<br />(Experimental) Client for OpenAI Realtime API.<br />

<b>Parameters:</b>

| Name         | Description                                                                                       |
| ------------ | ------------------------------------------------------------------------------------------------- |
| `llm_config` | **Type:** [LLMConfig](/docs/api-reference/autogen/llm_config/LLMConfig) \| dict\[str, typing.Any] |
| `websocket`  | **Type:** WebSocket                                                                               |
| `logger`     | **Type:** logging.Logger \| None<br /><br />**Default:** None                                     |

### Static Methods

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### get\_factory

```python theme={null}
get_factory(
    llm_config: LLMConfig | dict[str, Any],
    logger: Logger,
    **kwargs: Any
) -> Callable[[], RealtimeClientProtocol] | None
```

Create a Realtime API client.<br />

<b>Parameters:</b>

| Name         | Description                                                                                                                             |
| ------------ | --------------------------------------------------------------------------------------------------------------------------------------- |
| `llm_config` | The config for the client.<br /><br />**Type:** [LLMConfig](/docs/api-reference/autogen/llm_config/LLMConfig) \| dict\[str, typing.Any] |
| `logger`     | The logger to use for logging events.<br /><br />**Type:** logging.Logger                                                               |
| `**kwargs`   | Additional arguments.<br /><br />**Type:** Any                                                                                          |

<b>Returns:</b>

| Type                                                                                                                                         | Description                                                                                  |
| -------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------- |
| Callable\[\[], [RealtimeClientProtocol](/docs/api-reference/autogen/agentchat/realtime/experimental/clients/RealtimeClientProtocol)] \| None | RealtimeClientProtocol: The Realtime API client is returned if the model matches the pattern |

<br />

### Instance Attributes

<code class="doc-symbol doc-symbol-heading doc-symbol-attribute" />

#### logger

<br />

Get the logger for the OpenAI Realtime API.

### Instance Methods

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### connect

```python theme={null}
connect(self) -> AsyncGenerator[None, None]
```

Connect to the OpenAI Realtime API.<br />In the case of WebRTC, we pass connection information over the
websocket, so that javascript on the other end of websocket open
actual connection to OpenAI

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### read\_events

```python theme={null}
read_events(self) -> AsyncGenerator[RealtimeEvent, None]
```

Read events from the OpenAI Realtime API.

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### send\_audio

```python theme={null}
send_audio(self, audio: str) -> None
```

Send audio to the OpenAI Realtime API.<br />in case of WebRTC, audio is already sent by js client, so we just queue it in order to be logged.<br />

<b>Parameters:</b>

| Name    | Description                                 |
| ------- | ------------------------------------------- |
| `audio` | The audio to send.<br /><br />**Type:** str |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### send\_function\_result

```python theme={null}
send_function_result(
    self,
    call_id: str,
    result: str
) -> None
```

Send the result of a function call to the OpenAI Realtime API.<br />

<b>Parameters:</b>

| Name      | Description                                               |
| --------- | --------------------------------------------------------- |
| `call_id` | The ID of the function call.<br /><br />**Type:** str     |
| `result`  | The result of the function call.<br /><br />**Type:** str |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### send\_text

```python theme={null}
send_text(
    self,
    *,
    role: Literal['user', 'assistant', 'system'],
    text: str
) -> None
```

Send a text message to the OpenAI Realtime API.<br />

<b>Parameters:</b>

| Name   | Description                                                                           |
| ------ | ------------------------------------------------------------------------------------- |
| `role` | The role of the message.<br /><br />**Type:** Literal\['user', 'assistant', 'system'] |
| `text` | The text of the message.<br /><br />**Type:** str                                     |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### session\_init\_data

```python theme={null}
session_init_data(self) -> list[dict[str, Any]]
```

Control initial session with OpenAI.

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### session\_update

```python theme={null}
session_update(self, session_options: dict[str, Any]) -> None
```

Send a session update to the OpenAI Realtime API.<br />In the case of WebRTC we can not send it directly, but we can send it
to the javascript over the websocket, and rely on it to send session
update to OpenAI

<b>Parameters:</b>

| Name              | Description                                                                |
| ----------------- | -------------------------------------------------------------------------- |
| `session_options` | The session options to update.<br /><br />**Type:** dict\[str, typing.Any] |

<br />

<code class="doc-symbol doc-symbol-heading doc-symbol-method" />

#### truncate\_audio

```python theme={null}
truncate_audio(
    self,
    audio_end_ms: int,
    content_index: int,
    item_id: str
) -> None
```

Truncate audio in the OpenAI Realtime API.<br />

<b>Parameters:</b>

| Name            | Description                                                    |
| --------------- | -------------------------------------------------------------- |
| `audio_end_ms`  | The end of the audio to truncate.<br /><br />**Type:** int     |
| `content_index` | The index of the content to truncate.<br /><br />**Type:** int |
| `item_id`       | The ID of the item to truncate.<br /><br />**Type:** str       |

<br />