Qwen-Audio-ASR-Streaming WebSocket 接続ガイド

# pip install websocket-client
import os
import json
import time
import uuid
import threading
from urllib.parse import urlsplit
import websocket

api_key = os.environ.get('DASHSCOPE_API_KEY')
url = f"wss://{urlsplit(os.environ['DASHSCOPE_BASE_URL']).netloc}/api-ws/v1/inference"  # WebSocket server address
audio_file = 'asr_example.wav'  # Replace with the path to your audio file

# Generate a 32-character random ID
TASK_ID = uuid.uuid4().hex[:32]

task_started = False  # Flag indicating whether the task has started

# Send the run-task instruction
def send_run_task(ws):
    run_task_message = {
        'header': {
            'action': 'run-task',
            'task_id': TASK_ID,
            'streaming': 'duplex'
        },
        'payload': {
            'task_group': 'audio',
            'task': 'asr',
            'function': 'recognition',
            'model': 'qwen-audio-3.1-asr-flash-streaming',
            'parameters': {
                'sample_rate': 16000,
                'format': 'wav'
            },
            'input': {}
        }
    }
    ws.send(json.dumps(run_task_message))

# Send the finish-task instruction
def send_finish_task(ws):
    finish_task_message = {
        'header': {
            'action': 'finish-task',
            'task_id': TASK_ID,
            'streaming': 'duplex'
        },
        'payload': {
            'input': {}
        }
    }
    ws.send(json.dumps(finish_task_message))

# Send the audio stream (send one binary chunk every 100ms)
def send_audio_stream(ws):
    chunk_size = 3200  # 100ms @ 16kHz 16bit mono
    try:
        with open(audio_file, 'rb') as f:
            while True:
                chunk = f.read(chunk_size)
                if not chunk:
                    break
                ws.send(chunk, opcode=websocket.ABNF.OPCODE_BINARY)
                time.sleep(0.1)
        print('Audio stream ended')
        send_finish_task(ws)
    except Exception as e:
        print('Error reading audio file:', e)
        ws.close()

# Send the run-task instruction when the connection opens
def on_open(ws):
    print('Connected to server')
    send_run_task(ws)

# Handle received messages
def on_message(ws, data):
    global task_started
    message = json.loads(data)
    event = message['header']['event']
    if event == 'task-started':
        print('Task started')
        task_started = True
        threading.Thread(target=send_audio_stream, args=(ws,), daemon=True).start()
    elif event == 'result-generated':
        print('Recognition result:', message['payload']['output']['sentence']['text'])
        if message['payload'].get('usage'):
            print('Audio duration (seconds):', message['payload']['usage']['duration'])
    elif event == 'task-finished':
        print('Task finished')
        ws.close()
    elif event == 'task-failed':
        print('Task failed:', message['header'].get('error_message'))
        ws.close()
    else:
        print('Unknown event:', event)

# Close the connection if the task-started event is not received
def on_close(ws, close_status_code, close_msg):
    if not task_started:
        print('Task not started, closing connection')

# Error handling
def on_error(ws, error):
    print('WebSocket error:', error)

if __name__ == '__main__':
    ws = websocket.WebSocketApp(
        url,
        header={'Authorization': f'bearer {api_key}'},
        on_open=on_open,
        on_message=on_message,
        on_error=on_error,
        on_close=on_close
    )
    ws.run_forever()

package main

import (
	"encoding/json"
	"fmt"
	"io"
	"log"
	"net/http"
	neturl "net/url"
	"os"
	"time"

	"github.com/google/uuid"
	"github.com/gorilla/websocket"
)

const (
	audioFile = "asr_example.wav"                                   // Replace with the path to your audio file
)

var dialer = websocket.DefaultDialer

func main() {
	apiKey := os.Getenv("DASHSCOPE_API_KEY")

	// Connect to the WebSocket service
	conn, err := connectWebSocket(apiKey)
	if err != nil {
		log.Fatal("Failed to connect to WebSocket: ", err)
	}
	defer closeConnection(conn)

	// Start a goroutine to receive results
	taskStarted := make(chan bool)
	taskDone := make(chan bool)
	startResultReceiver(conn, taskStarted, taskDone)

	// Send the run-task instruction
	taskID, err := sendRunTaskCmd(conn)
	if err != nil {
		log.Fatal("Failed to send the run-task instruction: ", err)
	}

	// Wait for the task-started event
	waitForTaskStarted(taskStarted)

	// Send the audio file stream to be recognized
	if err := sendAudioData(conn); err != nil {
		log.Fatal("Failed to send audio: ", err)
	}

	// Send the finish-task instruction
	if err := sendFinishTaskCmd(conn, taskID); err != nil {
		log.Fatal("Failed to send the finish-task instruction: ", err)
	}

	// Wait for the task to finish or fail
	<-taskDone
}

// Define structs to represent the JSON data
type Header struct {
	Action       string                 `json:"action"`
	TaskID       string                 `json:"task_id"`
	Streaming    string                 `json:"streaming"`
	Event        string                 `json:"event"`
	ErrorCode    string                 `json:"error_code,omitempty"`
	ErrorMessage string                 `json:"error_message,omitempty"`
	Attributes   map[string]interface{} `json:"attributes"`
}

type Output struct {
	Sentence struct {
		BeginTime int64  `json:"begin_time"`
		EndTime   *int64 `json:"end_time"`
		Text      string `json:"text"`
		Words     []struct {
			BeginTime   int64  `json:"begin_time"`
			EndTime     *int64 `json:"end_time"`
			Text        string `json:"text"`
			Punctuation string `json:"punctuation"`
		} `json:"words"`
	} `json:"sentence"`
}

type Payload struct {
	TaskGroup  string `json:"task_group"`
	Task       string `json:"task"`
	Function   string `json:"function"`
	Model      string `json:"model"`
	Parameters Params `json:"parameters"`
	Input      Input  `json:"input"`
	Output     Output `json:"output,omitempty"`
	Usage      *struct {
		Duration int `json:"duration"`
	} `json:"usage,omitempty"`
}

type Params struct {
	Format                   string `json:"format"`
	SampleRate               int    `json:"sample_rate"`
	DisfluencyRemovalEnabled bool   `json:"disfluency_removal_enabled"`
}

type Input struct {
}

type Event struct {
	Header  Header  `json:"header"`
	Payload Payload `json:"payload"`
}

// Connect to the WebSocket service
func connectWebSocket(apiKey string) (*websocket.Conn, error) {
	base, err := neturl.Parse(os.Getenv("DASHSCOPE_BASE_URL"))
	if err != nil {
		return nil, err
	}
	wsURL := "wss://" + base.Host + "/api-ws/v1/inference"
	header := make(http.Header)
	header.Add("Authorization", fmt.Sprintf("bearer %s", apiKey))
	conn, _, err := dialer.Dial(wsURL, header)
	return conn, err
}

// Start a goroutine to receive WebSocket messages asynchronously
func startResultReceiver(conn *websocket.Conn, taskStarted chan<- bool, taskDone chan<- bool) {
	go func() {
		for {
			_, message, err := conn.ReadMessage()
			if err != nil {
				log.Println("Failed to parse server message: ", err)
				return
			}
			var event Event
			err = json.Unmarshal(message, &event)
			if err != nil {
				log.Println("Failed to parse event: ", err)
				continue
			}
			if handleEvent(conn, event, taskStarted, taskDone) {
				return
			}
		}
	}()
}

// Send the run-task instruction
func sendRunTaskCmd(conn *websocket.Conn) (string, error) {
	runTaskCmd, taskID, err := generateRunTaskCmd()
	if err != nil {
		return "", err
	}
	err = conn.WriteMessage(websocket.TextMessage, []byte(runTaskCmd))
	return taskID, err
}

// Generate the run-task instruction
func generateRunTaskCmd() (string, string, error) {
	taskID := uuid.New().String()
	runTaskCmd := Event{
		Header: Header{
			Action:    "run-task",
			TaskID:    taskID,
			Streaming: "duplex",
		},
		Payload: Payload{
			TaskGroup: "audio",
			Task:      "asr",
			Function:  "recognition",
			Model:     "qwen-audio-3.1-asr-flash-streaming",
			Parameters: Params{
				Format:     "wav",
				SampleRate: 16000,
			},
			Input: Input{},
		},
	}
	runTaskCmdJSON, err := json.Marshal(runTaskCmd)
	return string(runTaskCmdJSON), taskID, err
}

// Wait for the task-started event
func waitForTaskStarted(taskStarted chan bool) {
	select {
	case <-taskStarted:
		fmt.Println("Task started successfully")
	case <-time.After(10 * time.Second):
		log.Fatal("Timed out waiting for task-started; failed to start the task")
	}
}

// Send audio data
func sendAudioData(conn *websocket.Conn) error {
	file, err := os.Open(audioFile)
	if err != nil {
		return err
	}
	defer file.Close()

	buf := make([]byte, 3200)
	for {
		n, err := file.Read(buf)
		if n == 0 {
			break
		}
		if err != nil && err != io.EOF {
			return err
		}
		err = conn.WriteMessage(websocket.BinaryMessage, buf[:n])
		if err != nil {
			return err
		}
		time.Sleep(100 * time.Millisecond)
	}
	return nil
}

// Send the finish-task instruction
func sendFinishTaskCmd(conn *websocket.Conn, taskID string) error {
	finishTaskCmd, err := generateFinishTaskCmd(taskID)
	if err != nil {
		return err
	}
	err = conn.WriteMessage(websocket.TextMessage, []byte(finishTaskCmd))
	return err
}

// Generate the finish-task instruction
func generateFinishTaskCmd(taskID string) (string, error) {
	finishTaskCmd := Event{
		Header: Header{
			Action:    "finish-task",
			TaskID:    taskID,
			Streaming: "duplex",
		},
		Payload: Payload{
			Input: Input{},
		},
	}
	finishTaskCmdJSON, err := json.Marshal(finishTaskCmd)
	return string(finishTaskCmdJSON), err
}

// Handle events
func handleEvent(conn *websocket.Conn, event Event, taskStarted chan<- bool, taskDone chan<- bool) bool {
	switch event.Header.Event {
	case "task-started":
		fmt.Println("Received the task-started event")
		taskStarted <- true
	case "result-generated":
		if event.Payload.Output.Sentence.Text != "" {
			fmt.Println("Recognition result: ", event.Payload.Output.Sentence.Text)
		}
		if event.Payload.Usage != nil {
			fmt.Println("Audio duration (seconds): ", event.Payload.Usage.Duration)
		}
	case "task-finished":
		fmt.Println("Task finished")
		taskDone <- true
		return true
	case "task-failed":
		handleTaskFailed(event, conn)
		taskDone <- true
		return true
	default:
		log.Printf("Unexpected event: %v", event)
	}
	return false
}

// Handle the task-failed event
func handleTaskFailed(event Event, conn *websocket.Conn) {
	if event.Header.ErrorMessage != "" {
		log.Fatalf("Task failed: %s", event.Header.ErrorMessage)
	} else {
		log.Fatal("The task failed for an unknown reason")
	}
}

// Close the connection
func closeConnection(conn *websocket.Conn) {
	if conn != nil {
		conn.Close()
	}
}

const fs = require('fs');
const WebSocket = require('ws');
const { v4: uuidv4 } = require('uuid'); // Used to generate a UUID

const apiKey = process.env.DASHSCOPE_API_KEY;
const url = `wss://${new URL(process.env.DASHSCOPE_BASE_URL).host}/api-ws/v1/inference`; // WebSocket server address
const audioFile = 'asr_example.wav'; // Replace with the path to your audio file

// Generate a 32-character random ID
const TASK_ID = uuidv4().replace(/-/g, '').slice(0, 32);

// Create the WebSocket client
const ws = new WebSocket(url, {
  headers: {
    Authorization: `bearer ${apiKey}`
  }
});

let taskStarted = false; // Flag indicating whether the task has started

// Send the run-task instruction when the connection opens
ws.on('open', () => {
  console.log('Connected to server');
  sendRunTask();
});

// Handle received messages
ws.on('message', (data) => {
  const message = JSON.parse(data);
  switch (message.header.event) {
    case 'task-started':
      console.log('Task started');
      taskStarted = true;
      sendAudioStream();
      break;
    case 'result-generated':
      console.log('Recognition result:', message.payload.output.sentence.text);
      if (message.payload.usage) {
        console.log('Audio duration (seconds):', message.payload.usage.duration);
      }
      break;
    case 'task-finished':
      console.log('Task finished');
      ws.close();
      break;
    case 'task-failed':
      console.error('Task failed:', message.header.error_message);
      ws.close();
      break;
    default:
      console.log('Unknown event:', message.header.event);
  }
});

// Close the connection if the task-started event is not received
ws.on('close', () => {
  if (!taskStarted) {
    console.error('Task not started, closing connection');
  }
});

// Send the run-task instruction
function sendRunTask() {
  const runTaskMessage = {
    header: {
      action: 'run-task',
      task_id: TASK_ID,
      streaming: 'duplex'
    },
    payload: {
      task_group: 'audio',
      task: 'asr',
      function: 'recognition',
      model: 'qwen-audio-3.1-asr-flash-streaming',
      parameters: {
        sample_rate: 16000,
        format: 'wav'
      },
      input: {}
    }
  };
  ws.send(JSON.stringify(runTaskMessage));
}

// Send the audio stream
function sendAudioStream() {
  const audioStream = fs.createReadStream(audioFile);
  let chunkCount = 0;

  function sendNextChunk() {
    const chunk = audioStream.read();
    if (chunk) {
      ws.send(chunk);
      chunkCount++;
      setTimeout(sendNextChunk, 100); // Send once every 100ms
    }
  }

  audioStream.on('readable', () => {
    sendNextChunk();
  });

  audioStream.on('end', () => {
    console.log('Audio stream ended');
    sendFinishTask();
  });

  audioStream.on('error', (err) => {
    console.error('Error reading audio file:', err);
    ws.close();
  });
}

// Send the finish-task instruction
function sendFinishTask() {
  const finishTaskMessage = {
    header: {
      action: 'finish-task',
      task_id: TASK_ID,
      streaming: 'duplex'
    },
    payload: {
      input: {}
    }
  };
  ws.send(JSON.stringify(finishTaskMessage));
}

// Error handling
ws.on('error', (error) => {
  console.error('WebSocket error:', error);
});

using System.Net.WebSockets;
using System.Text;
using System.Text.Json;
using System.Text.Json.Nodes;

class Program {
    private static ClientWebSocket _webSocket = new ClientWebSocket();
    private static CancellationTokenSource _cancellationTokenSource = new CancellationTokenSource();
    private static bool _taskStartedReceived = false;
    private static bool _taskFinishedReceived = false;
    private static readonly string ApiKey = Environment.GetEnvironmentVariable("DASHSCOPE_API_KEY") ?? throw new InvalidOperationException("DASHSCOPE_API_KEY environment variable is not set.");

    private static readonly string WebSocketUrl = "wss://" + new Uri(Environment.GetEnvironmentVariable("DASHSCOPE_BASE_URL")!).Authority + "/api-ws/v1/inference";
    // Replace with the path to your audio file
    private const string AudioFilePath = "asr_example.wav";

    static async Task Main(string[] args) {
        // Establish the WebSocket connection and configure headers for authentication
        _webSocket.Options.SetRequestHeader("Authorization", $"bearer {ApiKey}");

        await _webSocket.ConnectAsync(new Uri(WebSocketUrl), _cancellationTokenSource.Token);

        // Start a thread to receive WebSocket messages asynchronously
        var receiveTask = ReceiveMessagesAsync();

        // Send the run-task instruction
        string _taskId = Guid.NewGuid().ToString("N"); // Generate a 32-character random ID
        var runTaskJson = GenerateRunTaskJson(_taskId);
        await SendAsync(runTaskJson);

        // Wait for the task-started event
        while (!_taskStartedReceived) {
            await Task.Delay(100, _cancellationTokenSource.Token);
        }

        // Read the local file and send the audio stream to be recognized to the server
        await SendAudioStreamAsync(AudioFilePath);

        // Send the finish-task instruction to end the task
        var finishTaskJson = GenerateFinishTaskJson(_taskId);
        await SendAsync(finishTaskJson);

        // Wait for the task-finished event
        while (!_taskFinishedReceived && !_cancellationTokenSource.IsCancellationRequested) {
            try {
                await Task.Delay(100, _cancellationTokenSource.Token);
            } catch (OperationCanceledException) {
                // The task has been canceled, exit the loop
                break;
            }
        }

        // Close the connection
        if (!_cancellationTokenSource.IsCancellationRequested) {
            await _webSocket.CloseAsync(WebSocketCloseStatus.NormalClosure, "Closing", _cancellationTokenSource.Token);
        }

        _cancellationTokenSource.Cancel();
        try {
            await receiveTask;
        } catch (OperationCanceledException) {
            // Ignore the operation canceled exception
        }
    }

    private static async Task ReceiveMessagesAsync() {
        try {
            while (_webSocket.State == WebSocketState.Open && !_cancellationTokenSource.IsCancellationRequested) {
                var message = await ReceiveMessageAsync(_cancellationTokenSource.Token);
                if (message != null) {
                    var eventValue = message["header"]?["event"]?.GetValue<string>();
                    switch (eventValue) {
                        case "task-started":
                            Console.WriteLine("Task started successfully");
                            _taskStartedReceived = true;
                            break;
                        case "result-generated":
                            Console.WriteLine($"Recognition result: {message["payload"]?["output"]?["sentence"]?["text"]?.GetValue<string>()}");
                            if (message["payload"]?["usage"] != null && message["payload"]?["usage"]?["duration"] != null) {
                                Console.WriteLine($"Audio duration (seconds): {message["payload"]?["usage"]?["duration"]?.GetValue<int>()}");
                            }
                            break;
                        case "task-finished":
                            Console.WriteLine("Task finished");
                            _taskFinishedReceived = true;
                            _cancellationTokenSource.Cancel();
                            break;
                        case "task-failed":
                            Console.WriteLine($"Task failed: {message["header"]?["error_message"]?.GetValue<string>()}");
                            _cancellationTokenSource.Cancel();
                            break;
                    }
                }
            }
        } catch (OperationCanceledException) {
            // Ignore the operation canceled exception
        }
    }

    private static async Task<JsonNode?> ReceiveMessageAsync(CancellationToken cancellationToken) {
        var buffer = new byte[1024 * 4];
        var segment = new ArraySegment<byte>(buffer);
        var sb = new StringBuilder();
        WebSocketReceiveResult result;
        // Receive and concatenate fragments until EndOfMessage to avoid JSON parsing failures on long messages
        do {
            result = await _webSocket.ReceiveAsync(segment, cancellationToken);
            if (result.MessageType == WebSocketMessageType.Close) {
                await _webSocket.CloseAsync(WebSocketCloseStatus.NormalClosure, "Closing", cancellationToken);
                return null;
            }
            sb.Append(Encoding.UTF8.GetString(buffer, 0, result.Count));
        } while (!result.EndOfMessage);

        return JsonNode.Parse(sb.ToString());
    }

    private static async Task SendAsync(string message) {
        var buffer = Encoding.UTF8.GetBytes(message);
        var segment = new ArraySegment<byte>(buffer);
        await _webSocket.SendAsync(segment, WebSocketMessageType.Text, true, _cancellationTokenSource.Token);
    }

    private static async Task SendAudioStreamAsync(string filePath) {
        using (var audioStream = File.OpenRead(filePath)) {
            var buffer = new byte[3200]; // Send 100ms of audio data each time
            int bytesRead;

            while ((bytesRead = await audioStream.ReadAsync(buffer, 0, buffer.Length)) > 0) {
                var segment = new ArraySegment<byte>(buffer, 0, bytesRead);
                await _webSocket.SendAsync(segment, WebSocketMessageType.Binary, true, _cancellationTokenSource.Token);
                await Task.Delay(100); // 100ms interval
            }
        }
    }

    private static string GenerateRunTaskJson(string taskId) {
        var runTask = new JsonObject {
            ["header"] = new JsonObject {
                ["action"] = "run-task",
                ["task_id"] = taskId,
                ["streaming"] = "duplex"
            },
            ["payload"] = new JsonObject {
                ["task_group"] = "audio",
                ["task"] = "asr",
                ["function"] = "recognition",
                ["model"] = "qwen-audio-3.1-asr-flash-streaming",
                ["parameters"] = new JsonObject {
                    ["format"] = "wav",
                    ["sample_rate"] = 16000,
                },
                ["input"] = new JsonObject()
            }
        };
        return JsonSerializer.Serialize(runTask);
    }

    private static string GenerateFinishTaskJson(string taskId) {
        var finishTask = new JsonObject {
            ["header"] = new JsonObject {
                ["action"] = "finish-task",
                ["task_id"] = taskId,
                ["streaming"] = "duplex"
            },
            ["payload"] = new JsonObject {
                ["input"] = new JsonObject()
            }
        };
        return JsonSerializer.Serialize(finishTask);
    }
}

<?php

require __DIR__ . '/vendor/autoload.php';

use Ratchet\Client\Connector;
use React\EventLoop\Loop;
use React\Socket\Connector as SocketConnector;
use Ratchet\rfc6455\Messaging\Frame;

$api_key = getenv("DASHSCOPE_API_KEY");
$websocket_url = 'wss://' . parse_url(getenv('DASHSCOPE_BASE_URL'), PHP_URL_HOST) . '/api-ws/v1/inference';
$audio_file_path = 'asr_example.wav'; // Replace with the path to your audio file

$loop = Loop::get();

// Create a custom connector
$socketConnector = new SocketConnector($loop, [
    'tcp' => [
        'bindto' => '0.0.0.0:0',
    ],
    'tls' => [
        'verify_peer' => true,
        'verify_peer_name' => true,
    ],
]);

$connector = new Connector($loop, $socketConnector);

$headers = [
    'Authorization' => 'bearer ' . $api_key
];

$connector($websocket_url, [], $headers)->then(function ($conn) use ($loop, $audio_file_path) {
    echo "Connected to WebSocket server\n";

    // Start a thread to receive WebSocket messages asynchronously
    $taskId = generateTaskId();
    $conn->on('message', function($msg) use ($conn, $loop, $audio_file_path, $taskId) {
        $response = json_decode($msg, true);

        if (isset($response['header']['event'])) {
            handleEvent($conn, $response, $loop, $audio_file_path, $taskId);
        } else {
            echo "Unknown message format\n";
        }
    });

    // Listen for the connection close
    $conn->on('close', function($code = null, $reason = null) {
        echo "Connection closed\n";
        if ($code !== null) {
            echo "Close code: " . $code . "\n";
        }
        if ($reason !== null) {
            echo "Close reason: " . $reason . "\n";
        }
    });

    // Generate the task ID

    // Send the run-task instruction
    sendRunTaskMessage($conn, $taskId);

}, function ($e) {
    echo "Unable to connect: {$e->getMessage()}\n";
});

$loop->run();

/**
 * Generate the task ID
 * @return string
 */
function generateTaskId(): string {
    return bin2hex(random_bytes(16));
}

/**
 * Send the run-task instruction
 * @param $conn
 * @param $taskId
 */
function sendRunTaskMessage($conn, $taskId) {
    $runTaskMessage = json_encode([
        "header" => [
            "action" => "run-task",
            "task_id" => $taskId,
            "streaming" => "duplex"
        ],
        "payload" => [
            "task_group" => "audio",
            "task" => "asr",
            "function" => "recognition",
            "model" => "qwen-audio-3.1-asr-flash-streaming",
            "parameters" => [
                "format" => "wav",
                "sample_rate" => 16000
            ],
            "input" => new stdClass()
        ]
    ]);
    echo "Preparing to send the run-task instruction: " . $runTaskMessage . "\n";
    $conn->send($runTaskMessage);
    echo "run-task instruction sent\n";
}

/**
 * Read the audio file
 * @param string $filePath
 * @return bool|string
 */
function readAudioFile(string $filePath) {
    $voiceData = file_get_contents($filePath);
    if ($voiceData === false) {
        echo "Unable to read the audio file\n";
    }
    return $voiceData;
}

/**
 * Split the audio data
 * @param string $data
 * @param int $chunkSize
 * @return array
 */
function splitAudioData(string $data, int $chunkSize): array {
    return str_split($data, $chunkSize);
}

/**
 * Send the finish-task instruction
 * @param $conn
 * @param $taskId
 */
function sendFinishTaskMessage($conn, $taskId) {
    $finishTaskMessage = json_encode([
        "header" => [
            "action" => "finish-task",
            "task_id" => $taskId,
            "streaming" => "duplex"
        ],
        "payload" => [
            "input" => new stdClass()
        ]
    ]);
    echo "Preparing to send the finish-task instruction: " . $finishTaskMessage . "\n";
    $conn->send($finishTaskMessage);
    echo "finish-task instruction sent\n";
}

/**
 * Handle events
 * @param $conn
 * @param $response
 * @param $loop
 * @param $audio_file_path
 */
function handleEvent($conn, $response, $loop, $audio_file_path, $taskId) {
    static $chunks;
    static $allChunksSent = false;


    switch ($response['header']['event']) {
        case 'task-started':
            echo "Task started, sending audio data...\n";
            // Read the audio file
            $voiceData = readAudioFile($audio_file_path);
            if ($voiceData === false) {
                echo "Unable to read the audio file\n";
                $conn->close();
                return;
            }

            // Split the audio data
            $chunks = splitAudioData($voiceData, 3200);

            // Define the send function
            $sendChunk = function() use ($conn, &$chunks, $loop, &$sendChunk, &$allChunksSent, $taskId) {
                if (!empty($chunks)) {
                    $chunk = array_shift($chunks);
                    $binaryMsg = new Frame($chunk, true, Frame::OP_BINARY);
                    $conn->send($binaryMsg);
                    // Send the next chunk after 100ms
                    $loop->addTimer(0.1, $sendChunk);
                } else {
                    echo "All data chunks sent\n";
                    $allChunksSent = true;

                    // Send the finish-task instruction
                    sendFinishTaskMessage($conn, $taskId);
                }
            };

            // Start sending audio data
            $sendChunk();
            break;
        case 'result-generated':
            $result = $response['payload']['output']['sentence'];
            echo "Recognition result: " . $result['text'] . "\n";
            if (isset($response['payload']['usage']['duration'])) {
                echo "Audio duration (seconds): " . $response['payload']['usage']['duration'] . "\n";
            }
            break;
        case 'task-finished':
            echo "Task finished\n";
            $conn->close();
            break;
        case 'task-failed':
            echo "Task failed\n";
            echo "Error code: " . $response['header']['error_code'] . "\n";
            echo "Error message: " . $response['header']['error_message'] . "\n";
            $conn->close();
            break;
        case 'error':
            echo "Error: " . $response['payload']['message'] . "\n";
            break;
        default:
            echo "Unknown event: " . $response['header']['event'] . "\n";
            break;
    }

    // If all data has been sent and the task has finished, close the connection
    if ($allChunksSent && $response['header']['event'] == 'task-finished') {
        // Wait 1 second to ensure all data has been transmitted
        $loop->addTimer(1, function() use ($conn) {
            $conn->close();
            echo "Client closed the connection\n";
        });
    }
}