> ## Documentation Index
> Fetch the complete documentation index at: https://daily-main.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI Realtime WebRTC Transport

> OpenAIRealTimeWebRTCTransport for the JavaScript SDK: connect directly to the OpenAI Realtime API over WebRTC.

<Warning>
  **Deprecated:** This transport connects directly from the browser to a
  third-party LLM API rather than through a Pipecat server, so it can't use
  most Pipecat server-side features and drifts out of sync with that API over
  time. It is no longer supported and will not receive further updates.
  Published npm versions will remain installable, but since this transport
  depends directly on a third-party API that changes over time, it may stop
  working correctly as that API evolves.

  For production applications, use a server-friendly transport like the
  [DailyTransport](./daily) with a Pipecat server component to securely handle
  API keys and access the full Pipecat feature set.
</Warning>

## Overview

The `OpenAIRealTimeWebRTCTransport` is a fully functional [Pipecat `Transport`](/api-reference/client/js/transports/transport). It provides a framework for implementing real-time communication directly with the [OpenAI Realtime API using WebRTC](https://platform.openai.com/docs/guides/realtime-webrtc) voice-to-voice service. It handles media device management, audio/video streams, and state management for the connection.

## Usage

### Basic Setup

```javascript theme={null}
import { OpenAIRealTimeWebRTCTransport, OpenAIServiceOptions } from '@pipecat-ai/openai-realtime-webrtc-transport';
import { PipecatClient } from '@pipecat-ai/client-js';

const options: OpenAIServiceOptions = {
  api_key: 'YOUR_API_KEY',
  settings: {
    instructions: 'You are a confused jellyfish.',
  },
  initial_messages: [{ role: "user", content: "Blub blub!" }],
};

let pcClient = new PipecatClient({
  transport: new OpenAIRealTimeWebRTCTransport (options),
  ...
});
pcClient.connect();
```

## API Reference

### Constructor Options

Below is the transport's type definition for the OpenAI Session configuration you pass to the constructor. See the [OpenAI Realtime API documentation](https://platform.openai.com/docs/api-reference/realtime-client-events/session/update) for more details on each of the options and their defaults.

```typescript theme={null}
export type OpenAIFunctionTool = {
  type: "function";
  name: string;
  description: string;
  parameters: JSONSchema;
};

export type OpenAIServerVad = {
  type: "server_vad";
  create_response?: boolean;
  interrupt_response?: boolean;
  prefix_padding_ms?: number;
  silence_duration_ms?: number;
  threshold?: number;
};

export type OpenAISemanticVAD = {
  type: "semantic_vad";
  eagerness?: "low" | "medium" | "high" | "auto";
  create_response?: boolean; // defaults to true
  interrupt_response?: boolean; // defaults to true
};

export type OpenAISessionConfig = Partial<{
  modalities?: string;
  instructions?: string;
  voice?:
    | "alloy"
    | "ash"
    | "ballad"
    | "coral"
    | "echo"
    | "sage"
    | "shimmer"
    | "verse";
  input_audio_noise_reduction?: {
    type: "near_field" | "far_field";
  } | null; // defaults to null/off
  input_audio_transcription?: {
    model: "whisper-1" | "gpt-4o-transcribe" | "gpt-4o-mini-transcribe";
    language?: string;
    prompt?: string[] | string; // gpt-4o models take a string
  } | null; // we default this to gpt-4o-transcribe
  turn_detection?: OpenAIServerVad | OpenAISemanticVAD | null; // defaults to server_vad
  temperature?: number;
  max_tokens?: number | "inf";
  tools?: Array<OpenAIFunctionTool>;
}>;

export interface OpenAIServiceOptions {
  api_key: string;
  model?: string;
  initial_messages?: LLMContextMessage[];
  settings?: OpenAISessionConfig;
}
```

### TransportConnectionParams

The `OpenAIRealTimeWebRTCTransport` does not take connection parameters. It connects directly to the OpenAI Realtime API using the API key provided as part of the initial configuration.

### Events

The transport implements the various [`PipecatClient` event handlers](/api-reference/client/js/callbacks). Check out the docs or samples for more info.

## More Information

<CardGroup cols={2}>
  <Card horizontal title="Demo" icon="play" href="https://github.com/pipecat-ai/pipecat-client-web-transports/tree/main/examples/directToLLMTransports">
    OpenAI Realtime Basic Demo
  </Card>

  <Card horizontal title="Source" icon="github" href="https://github.com/pipecat-ai/pipecat-client-web-transports/tree/main/transports/openai-realtime-webrtc-transport">
    `OpenAIRealTimeWebRTCTransport`
  </Card>
</CardGroup>

<Card horizontal title="Package" icon="browser" href="https://www.npmjs.com/package/@pipecat-ai/openai-realtime-webrtc-transport">
  `@pipecat-ai/openai-realtime-webrtc-transport`
</Card>