OpenAI Realtime WebRTC Transport

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();

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;
}