GET
/
v1
/
realtime
原生OpenAI格式
curl --request GET \
  --url https://api.applerouter.ai/v1/realtime \
  --header 'Authorization: Bearer <token>'
{
  "error": {
    "message": "<string>",
    "type": "<string>",
    "param": "<string>",
    "code": "<string>"
  }
}

​
Overview

Establish a WebSocket connection for realtime voice conversation. This enables bidirectional audio streaming for interactive voice applications.
​
model
string
The model to use (e.g. gpt-4o-realtime-preview)
This is a WebSocket endpoint. Use the WebSocket protocol (wss://) to connect.

​
Connecting

Connect using the WebSocket protocol: 
wss://api.applerouter.ai/v1/realtime?model=gpt-4o-realtime-preview
Include your API Key in the connection:
JavaScript
const ws = new WebSocket(
  "wss://api.applerouter.ai/v1/realtime?model=gpt-4o-realtime-preview",
  {
    headers: {
      Authorization: "Bearer sk-your-api-key",
    },
  }
);

ws.onopen = () => {
  console.log("Connected to realtime API");

  // Send session configuration
  ws.send(
    JSON.stringify({
      type: "session.update",
      session: {
        modalities: ["text", "audio"],
        instructions: "You are a helpful assistant.",
        voice: "alloy",
        input_audio_format: "pcm16",
        output_audio_format: "pcm16",
      },
    })
  );
};

ws.onmessage = (event) => {
  const data = JSON.parse(event.data);
  console.log("Received:", data.type);

  if (data.type === "response.audio.delta") {
    // Handle audio chunk
    playAudio(data.delta);
  }
};

// Send audio input
function sendAudio(audioData) {
  ws.send(
    JSON.stringify({
      type: "input_audio_buffer.append",
      audio: audioData, // base64 encoded PCM16 audio
    })
  );
}
Python
import asyncio
import websockets
import json

async def realtime_session():
    uri = "wss://api.applerouter.ai/v1/realtime?model=gpt-4o-realtime-preview"
    headers = {"Authorization": "Bearer sk-your-api-key"}

    async with websockets.connect(uri, extra_headers=headers) as ws:
        # Configure session
        await ws.send(json.dumps({
            "type": "session.update",
            "session": {
                "modalities": ["text", "audio"],
                "instructions": "You are a helpful assistant.",
                "voice": "alloy"
            }
        }))

        # Listen for responses
        async for message in ws:
            data = json.loads(message)
            print(f"Received: {data['type']}")

asyncio.run(realtime_session())

​
Message Types

​
Client Messages

TypeDescription
session.updateUpdate Session Config
input_audio_buffer.appendAppend Audio Data
input_audio_buffer.commitCommit Audio Buffer
conversation.item.createCreate Conversation Item
response.createRequest Response

​
Server Messages

TypeDescription
session.createdSession Created
response.audio.deltaAudio Delta
response.text.deltaText Delta
response.doneResponse Done
errorError occurred
Rate limits for realtime connections differ from REST API calls. Please monitor your usage accordingly.

Authorizations

​
Authorization
string
header
required

使用 Bearer Token 认证。格式: Authorization: Bearer sk-xxxxxx

Query Parameters

​
model
string

要使用的模型

Example:

"gpt-4o-realtime-preview"

Response

WebSocket 协议切换