Alibaba Cloud Model Studio:Real-time speech recognition - Qwen

Python

Before you run the example, install the dependencies with the following commands:

pip uninstall websocket-client
pip uninstall websocket
pip install websocket-client

Do not name the example file websocket.py. This name conflicts with the websocket library and causes the following error: AttributeError: module 'websocket' has no attribute 'WebSocketApp'. Did you mean: 'WebSocket'?.

# pip install websocket-client
import os
import json
import time
import uuid
import threading
import websocket

# The API Key differs between the Singapore and Beijing regions. Get your API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: api_key = "sk-xxx"
api_key = os.environ.get('DASHSCOPE_API_KEY')
# The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ by region.
url = 'wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference'  # WebSocket server address
audio_file = '{YOUR_AUDIO_FILE}'  # 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-3.0-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('Task billing 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()

Java

Before you run the example, install the Java-WebSocket dependency:

<dependency>
    <groupId>org.java-websocket</groupId>
    <artifactId>Java-WebSocket</artifactId>
    <version>1.5.6</version>
</dependency>
<dependency>
    <groupId>org.json</groupId>
    <artifactId>json</artifactId>
    <version>20240303</version>
</dependency>

implementation 'org.java-websocket:Java-WebSocket:1.5.6'
implementation 'org.json:json:20240303'

import org.java_websocket.client.WebSocketClient;
import org.java_websocket.handshake.ServerHandshake;
import org.json.JSONObject;

import java.net.URI;
import java.nio.ByteBuffer;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.UUID;
import java.util.concurrent.atomic.AtomicBoolean;

public class FunASRRealtimeClient {

    // The API Key differs between the Singapore and Beijing regions. Get your API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    // If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: private static final String API_KEY = "sk-xxx";
    private static final String API_KEY = System.getenv().getOrDefault("DASHSCOPE_API_KEY", "sk-xxx");
    // The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ by region.
    private static final String URL = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference";
    private static final String AUDIO_FILE = "{YOUR_AUDIO_FILE}"; // Replace with the path to your audio file
    private static final String MODEL = "qwen-audio-3.0-asr-flash-streaming";

    // Generate a 32-character random ID
    private static final String TASK_ID = UUID.randomUUID().toString().replace("-", "").substring(0, 32);

    private static final AtomicBoolean taskStarted = new AtomicBoolean(false);
    private static WebSocketClient client;

    public static void main(String[] args) throws Exception {
        client = new WebSocketClient(new URI(URL)) {
            @Override
            public void onOpen(ServerHandshake handshake) {
                System.out.println("Connected to server");
                sendRunTask();
            }

            @Override
            public void onMessage(String data) {
                JSONObject message = new JSONObject(data);
                String event = message.getJSONObject("header").getString("event");
                switch (event) {
                    case "task-started":
                        System.out.println("Task started");
                        taskStarted.set(true);
                        new Thread(FunASRRealtimeClient::sendAudioStream).start();
                        break;
                    case "result-generated":
                        JSONObject payload = message.getJSONObject("payload");
                        String text = payload.getJSONObject("output").getJSONObject("sentence").getString("text");
                        System.out.println("Recognition result: " + text);
                        if (payload.has("usage")) {
                            System.out.println("Task billing duration (seconds): " + payload.getJSONObject("usage").get("duration"));
                        }
                        break;
                    case "task-finished":
                        System.out.println("Task finished");
                        close();
                        break;
                    case "task-failed":
                        String errMsg = message.getJSONObject("header").optString("error_message");
                        System.err.println("Task failed: " + errMsg);
                        close();
                        break;
                    default:
                        System.out.println("Unknown event: " + event);
                }
            }

            @Override
            public void onClose(int code, String reason, boolean remote) {
                if (!taskStarted.get()) {
                    System.err.println("Task not started, closing connection");
                }
            }

            @Override
            public void onError(Exception ex) {
                System.err.println("WebSocket error: " + ex.getMessage());
            }
        };
        client.addHeader("Authorization", "bearer " + API_KEY);
        client.connectBlocking();
    }

    // Send the run-task instruction
    private static void sendRunTask() {
        JSONObject runTask = new JSONObject()
                .put("header", new JSONObject()
                        .put("action", "run-task")
                        .put("task_id", TASK_ID)
                        .put("streaming", "duplex"))
                .put("payload", new JSONObject()
                        .put("task_group", "audio")
                        .put("task", "asr")
                        .put("function", "recognition")
                        .put("model", MODEL)
                        .put("parameters", new JSONObject()
                                .put("sample_rate", 16000)
                                .put("format", "wav"))
                        .put("input", new JSONObject()));
        client.send(runTask.toString());
    }

    // Send the audio stream (send one binary chunk every 100ms)
    private static void sendAudioStream() {
        int chunkSize = 3200; // 100ms @ 16kHz 16bit mono
        try {
            byte[] audio = Files.readAllBytes(Paths.get(AUDIO_FILE));
            int offset = 0;
            while (offset < audio.length) {
                int end = Math.min(offset + chunkSize, audio.length);
                byte[] chunk = new byte[end - offset];
                System.arraycopy(audio, offset, chunk, 0, end - offset);
                client.send(ByteBuffer.wrap(chunk));
                offset = end;
                Thread.sleep(100);
            }
            System.out.println("Audio stream ended");
            sendFinishTask();
        } catch (Exception e) {
            System.err.println("Error reading audio file: " + e.getMessage());
            client.close();
        }
    }

    // Send the finish-task instruction
    private static void sendFinishTask() {
        JSONObject finishTask = new JSONObject()
                .put("header", new JSONObject()
                        .put("action", "finish-task")
                        .put("task_id", TASK_ID)
                        .put("streaming", "duplex"))
                .put("payload", new JSONObject()
                        .put("input", new JSONObject()));
        client.send(finishTask.toString());
    }
}

Node.js

Install the required dependencies:

npm install ws
npm install uuid

The example code is as follows:

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

// The API Key differs between the Singapore and Beijing regions. Get your API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
// If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: const apiKey = "sk-xxx"
const apiKey = process.env.DASHSCOPE_API_KEY;
// The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ by region.
const url = 'wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference'; // WebSocket server address
const audioFile = '{YOUR_AUDIO_FILE}'; // 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('Task billing 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-3.0-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);
});

C#

The example code is as follows:

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;
    // The API Key differs between the Singapore and Beijing regions. Get your API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    // If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: private static readonly string ApiKey = "sk-xxx"
    private static readonly string ApiKey = Environment.GetEnvironmentVariable("DASHSCOPE_API_KEY") ?? throw new InvalidOperationException("DASHSCOPE_API_KEY environment variable is not set.");

    // The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ by region.
    private const string WebSocketUrl = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference";
    // Replace with the path to your audio file
    private const string AudioFilePath = "{YOUR_AUDIO_FILE}";

    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($"Recognition result: {message["payload"]?["output"]?["sentence"]?["text"]?.GetValue<string>()}");
                            if (message["payload"]?["usage"] != null && message["payload"]?["usage"]?["duration"] != null) {
                                Console.WriteLine($"Task billing 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 result = await _webSocket.ReceiveAsync(segment, cancellationToken);

        if (result.MessageType == WebSocketMessageType.Close) {
            await _webSocket.CloseAsync(WebSocketCloseStatus.NormalClosure, "Closing", cancellationToken);
            return null;
        }

        var message = Encoding.UTF8.GetString(buffer, 0, result.Count);
        return JsonNode.Parse(message);
    }

    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[1024]; // 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-3.0-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

The example project has the following directory structure:

my-php-project/

├── composer.json

├── vendor/

└── index.php

The contents of composer.json are as follows. Adjust the dependency versions as needed:

{
    "require": {
        "react/event-loop": "^1.3",
        "react/socket": "^1.11",
        "react/stream": "^1.2",
        "react/http": "^1.1",
        "ratchet/pawl": "^0.4"
    },
    "autoload": {
        "psr-4": {
            "App\\": "src/"
        }
    }
}

The contents of index.php are as follows:

<?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;

// The API Key differs between the Singapore and Beijing regions. Get your API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
// If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: $api_key = "sk-xxx"
$api_key = getenv("DASHSCOPE_API_KEY");
// The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ by region.
$websocket_url = 'wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference';
$audio_file_path = '{YOUR_AUDIO_FILE}'; // 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' => false,
        'verify_peer_name' => false,
    ],
]);

$connector = new Connector($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
    $conn->on('message', function($msg) use ($conn, $loop, $audio_file_path) {
        $response = json_decode($msg, true);

        if (isset($response['header']['event'])) {
            handleEvent($conn, $response, $loop, $audio_file_path);
        } 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
    $taskId = generateTaskId();

    // 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-3.0-asr-flash-streaming",
            "parameters" => [
                "format" => "wav",
                "sample_rate" => 16000
            ],
            "input" => []
        ]
    ]);
    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" => []
        ]
    ]);
    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) {
    static $taskId;
    static $chunks;
    static $allChunksSent = false;

    if (is_null($taskId)) {
        $taskId = generateTaskId();
    }

    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, 1024);

            // 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 "Task billing 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";
        });
    }
}

Go

package main

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

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

const (
	// The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ by region.
	wsURL     = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/inference" // WebSocket server address
	audioFile = "{YOUR_AUDIO_FILE}"                                   // Replace with the path to your audio file
)

var dialer = websocket.DefaultDialer

func main() {
	// The API Key differs between the Singapore and Beijing regions. Get your API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    // If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: apiKey := "sk-xxx"
	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) {
	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-3.0-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, 1024)
	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("Task billing 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()
	}
}

Python

Before you run the example, install the dependencies with the following commands:

pip uninstall websocket-client
pip uninstall websocket
pip install websocket-client

Do not name the example file websocket.py. This name conflicts with the websocket library and causes the following error: AttributeError: module 'websocket' has no attribute 'WebSocketApp'. Did you mean: 'WebSocket'?.

# pip install websocket-client
import os
import time
import json
import threading
import base64
import websocket
import logging
import logging.handlers
from datetime import datetime

logger = logging.getLogger(__name__)
logger.setLevel(logging.DEBUG)

# The API Key differs between the Singapore and Beijing regions. Get your API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: API_KEY="sk-xxx"
API_KEY = os.environ.get("DASHSCOPE_API_KEY", "sk-xxx")
QWEN_MODEL = "qwen3-asr-flash-realtime"
# The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ by region.
baseUrl = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime"
url = f"{baseUrl}?model={QWEN_MODEL}"
print(f"Connecting to server: {url}")

# Note: In non-VAD mode, it is recommended that the cumulative duration of continuously sent audio does not exceed 60s
enableServerVad = True
is_running = True  # Add a running flag

headers = [
    "Authorization: Bearer " + API_KEY,
    "OpenAI-Beta: realtime=v1"
]

def init_logger():
    formatter = logging.Formatter('%(asctime)s|%(levelname)s|%(message)s')
    f_handler = logging.handlers.RotatingFileHandler(
        "omni_tester.log", maxBytes=100 * 1024 * 1024, backupCount=3
    )
    f_handler.setLevel(logging.DEBUG)
    f_handler.setFormatter(formatter)

    console = logging.StreamHandler()
    console.setLevel(logging.DEBUG)
    console.setFormatter(formatter)

    logger.addHandler(f_handler)
    logger.addHandler(console)

def on_open(ws):
    logger.info("Connected to server.")

    # Session update event
    event_manual = {
        "event_id": "event_123",
        "type": "session.update",
        "session": {
            "modalities": ["text"],
            "input_audio_format": "pcm",
            "sample_rate": 16000,
            # "input_audio_transcription": {
            #     # Language identifier, optional; recommended to set it if the language is known
            #     "language": "zh"
            # },
            "turn_detection": None
        }
    }
    event_vad = {
        "event_id": "event_123",
        "type": "session.update",
        "session": {
            "modalities": ["text"],
            "input_audio_format": "pcm",
            "sample_rate": 16000,
            # "input_audio_transcription": {
            #     "language": "zh"
            # },
            "turn_detection": {
                "type": "server_vad",
                "threshold": 0.0,
                "silence_duration_ms": 400
            }
        }
    }
    if enableServerVad:
        logger.info(f"Sending event: {json.dumps(event_vad, indent=2)}")
        ws.send(json.dumps(event_vad))
    else:
        logger.info(f"Sending event: {json.dumps(event_manual, indent=2)}")
        ws.send(json.dumps(event_manual))

def on_message(ws, message):
    global is_running
    try:
        data = json.loads(message)
        logger.info(f"Received event: {json.dumps(data, ensure_ascii=False, indent=2)}")
        if data.get("type") == "conversation.item.input_audio_transcription.completed":
            logger.info(f"Final transcript: {data.get('transcript')}")
        elif data.get("type") == "session.finished":
            logger.info("Closing WebSocket connection after session finished...")
            is_running = False  # Stop the audio sending thread
            ws.close()
    except json.JSONDecodeError:
        logger.error(f"Failed to parse message: {message}")

def on_error(ws, error):
    logger.error(f"Error: {error}")

def on_close(ws, close_status_code, close_msg):
    logger.info(f"Connection closed: {close_status_code} - {close_msg}")

def send_audio(ws, local_audio_path):
    time.sleep(3)  # Wait for the session update to complete
    global is_running

    with open(local_audio_path, 'rb') as audio_file:
        logger.info(f"File reading started: {datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]}")
        while is_running:
            audio_data = audio_file.read(3200)  # ~0.1s PCM16/16kHz
            if not audio_data:
                logger.info(f"File reading finished: {datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]}")
                if ws.sock and ws.sock.connected:
                    if not enableServerVad:
                        commit_event = {
                            "event_id": "event_789",
                            "type": "input_audio_buffer.commit"
                        }
                        ws.send(json.dumps(commit_event))
                    finish_event = {
                        "event_id": "event_987",
                        "type": "session.finish"
                    }
                    ws.send(json.dumps(finish_event))
                break

            if not ws.sock or not ws.sock.connected:
                logger.info("WebSocket is closed, stopping audio sending.")
                break

            encoded_data = base64.b64encode(audio_data).decode('utf-8')
            eventd = {
                "event_id": f"event_{int(time.time() * 1000)}",
                "type": "input_audio_buffer.append",
                "audio": encoded_data
            }
            ws.send(json.dumps(eventd))
            logger.info(f"Sending audio event: {eventd['event_id']}")
            time.sleep(0.1)  # Simulate real-time capture

# Initialize logging
init_logger()
logger.info(f"Connecting to WebSocket server at {url}...")

local_audio_path = "your_audio_file.pcm"
ws = websocket.WebSocketApp(
    url,
    header=headers,
    on_open=on_open,
    on_message=on_message,
    on_error=on_error,
    on_close=on_close
)

thread = threading.Thread(target=send_audio, args=(ws, local_audio_path))
thread.start()
ws.run_forever()

Java

Before you run the example, install the Java-WebSocket dependency:

<dependency>
    <groupId>org.java-websocket</groupId>
    <artifactId>Java-WebSocket</artifactId>
    <version>1.5.6</version>
</dependency>

implementation 'org.java-websocket:Java-WebSocket:1.5.6'

import org.java_websocket.client.WebSocketClient;
import org.java_websocket.handshake.ServerHandshake;
import org.json.JSONObject;

import java.net.URI;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.Base64;
import java.util.concurrent.atomic.AtomicBoolean;
import java.util.logging.*;

public class QwenASRRealtimeClient {

    private static final Logger logger = Logger.getLogger(QwenASRRealtimeClient.class.getName());
    // The API Key differs between the Singapore and Beijing regions. Get your API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    // If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: private static final String API_KEY = "sk-xxx"
    private static final String API_KEY = System.getenv().getOrDefault("DASHSCOPE_API_KEY", "sk-xxx");
    private static final String MODEL = "qwen3-asr-flash-realtime";

    // Controls whether to use VAD mode
    private static final boolean enableServerVad = true;

    private static final AtomicBoolean isRunning = new AtomicBoolean(true);
    private static WebSocketClient client;

    public static void main(String[] args) throws Exception {
        initLogger();

        // The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ by region.
        String baseUrl = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime";
        String url = baseUrl + "?model=" + MODEL;
        logger.info("Connecting to server: " + url);

        client = new WebSocketClient(new URI(url)) {
            @Override
            public void onOpen(ServerHandshake handshake) {
                logger.info("Connected to server.");
                sendSessionUpdate();
            }

            @Override
            public void onMessage(String message) {
                try {
                    JSONObject data = new JSONObject(message);
                    String eventType = data.optString("type");

                    logger.info("Received event: " + data.toString(2));

                    // The final recognition result is in the transcription.completed event
                    if ("conversation.item.input_audio_transcription.completed".equals(eventType)) {
                        logger.info("Final transcript: " + data.optString("transcript"));
                    }

                    // On receiving the finished event -> stop the sending thread and close the connection
                    if ("session.finished".equals(eventType)) {
                        logger.info("Closing WebSocket connection after session finished...");

                        isRunning.set(false); // Stop the audio sending thread
                        if (this.isOpen()) {
                            this.close(1000, "ASR finished");
                        }
                    }
                } catch (Exception e) {
                    logger.severe("Failed to parse message: " + message);
                }
            }

            @Override
            public void onClose(int code, String reason, boolean remote) {
                logger.info("Connection closed: " + code + " - " + reason);
            }

            @Override
            public void onError(Exception ex) {
                logger.severe("Error: " + ex.getMessage());
            }
        };

        // Add request headers
        client.addHeader("Authorization", "Bearer " + API_KEY);
        client.addHeader("OpenAI-Beta", "realtime=v1");

        client.connectBlocking(); // Block until the connection is established

        // Replace with the path to the audio file to be recognized
        String localAudioPath = "your_audio_file.pcm";
        Thread audioThread = new Thread(() -> {
            try {
                sendAudio(localAudioPath);
            } catch (Exception e) {
                logger.severe("Audio sending thread error: " + e.getMessage());
            }
        });
        audioThread.start();
    }

    /** Session update event (enable/disable VAD) */
    private static void sendSessionUpdate() {
        JSONObject eventNoVad = new JSONObject()
                .put("event_id", "event_123")
                .put("type", "session.update")
                .put("session", new JSONObject()
                        .put("modalities", new String[]{"text"})
                        .put("input_audio_format", "pcm")
                        .put("sample_rate", 16000)
                        // .put("input_audio_transcription", new JSONObject()
                        //         .put("language", "zh"))
                        .put("turn_detection", JSONObject.NULL) // Manual mode
                );

        JSONObject eventVad = new JSONObject()
                .put("event_id", "event_123")
                .put("type", "session.update")
                .put("session", new JSONObject()
                        .put("modalities", new String[]{"text"})
                        .put("input_audio_format", "pcm")
                        .put("sample_rate", 16000)
                        // .put("input_audio_transcription", new JSONObject()
                        //         .put("language", "zh"))
                        .put("turn_detection", new JSONObject()
                                .put("type", "server_vad")
                                .put("threshold", 0.0)
                                .put("silence_duration_ms", 400))
                );

        if (enableServerVad) {
            logger.info("Sending event (VAD):\n" + eventVad.toString(2));
            client.send(eventVad.toString());
        } else {
            logger.info("Sending event (Manual):\n" + eventNoVad.toString(2));
            client.send(eventNoVad.toString());
        }
    }

    /** Send the audio file stream */
    private static void sendAudio(String localAudioPath) throws Exception {
        Thread.sleep(3000); // Wait for the session to be ready
        byte[] allBytes = Files.readAllBytes(Paths.get(localAudioPath));
        logger.info("File reading started");

        int offset = 0;
        while (isRunning.get() && offset < allBytes.length) {
            int chunkSize = Math.min(3200, allBytes.length - offset);
            byte[] chunk = new byte[chunkSize];
            System.arraycopy(allBytes, offset, chunk, 0, chunkSize);
            offset += chunkSize;

            if (client != null && client.isOpen()) {
                String encoded = Base64.getEncoder().encodeToString(chunk);
                JSONObject eventd = new JSONObject()
                        .put("event_id", "event_" + System.currentTimeMillis())
                        .put("type", "input_audio_buffer.append")
                        .put("audio", encoded);

                client.send(eventd.toString());
                logger.info("Sending audio event: " + eventd.getString("event_id"));
            } else {
                break; // Avoid continuing to send after disconnection
            }

            Thread.sleep(100); // Simulate real-time sending
        }

        logger.info("File reading finished");

        if (client != null && client.isOpen()) {
            // Commit is required in non-VAD mode
            if (!enableServerVad) {
                JSONObject commitEvent = new JSONObject()
                        .put("event_id", "event_789")
                        .put("type", "input_audio_buffer.commit");
                client.send(commitEvent.toString());
                logger.info("Sent commit event for manual mode.");
            }

            JSONObject finishEvent = new JSONObject()
                    .put("event_id", "event_987")
                    .put("type", "session.finish");
            client.send(finishEvent.toString());
            logger.info("Sent finish event.");
        }
    }

    /** Initialize logging */
    private static void initLogger() {
        logger.setLevel(Level.ALL);
        Logger rootLogger = Logger.getLogger("");
        for (Handler h : rootLogger.getHandlers()) {
            rootLogger.removeHandler(h);
        }

        Handler consoleHandler = new ConsoleHandler();
        consoleHandler.setLevel(Level.ALL);
        consoleHandler.setFormatter(new SimpleFormatter());
        logger.addHandler(consoleHandler);
    }
}

Node.js

Before you run the example, install the dependencies with the following command:

npm install ws

/**
 * Qwen-ASR Realtime WebSocket client (Node.js version)
 * Features:
 * - Supports VAD mode and Manual mode
 * - Sends session.update to start the session
 * - Continuously sends audio chunks via input_audio_buffer.append
 * - In Manual mode, sends input_audio_buffer.commit
 * - Sends the session.finish event
 * - Closes the connection after receiving the session.finished event
 */

import WebSocket from 'ws';
import fs from 'fs';

// ===== Configuration =====
// The API Key differs between the Singapore and Beijing regions. Get your API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
// If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: const API_KEY = "sk-xxx"
const API_KEY = process.env.DASHSCOPE_API_KEY || 'sk-xxx';
const MODEL = 'qwen3-asr-flash-realtime';
const enableServerVad = true; // true for VAD mode, false for Manual mode
const localAudioPath = 'your_audio_file.pcm'; // Path to the PCM16, 16kHz audio file

// The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ by region.
const baseUrl = 'wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime';
const url = `${baseUrl}?model=${MODEL}`;

console.log(`Connecting to server: ${url}`);

// ===== State control =====
let isRunning = true;

// ===== Establish the connection =====
const ws = new WebSocket(url, {
    headers: {
        'Authorization': `Bearer ${API_KEY}`,
        'OpenAI-Beta': 'realtime=v1'
    }
});

// ===== Event bindings =====
ws.on('open', () => {
    console.log('[WebSocket] Connected to server.');
    sendSessionUpdate();
    // Start the audio sending thread
    sendAudio(localAudioPath);
});

ws.on('message', (message) => {
    try {
        const data = JSON.parse(message);
        console.log('[Received Event]:', JSON.stringify(data, null, 2));

        // The final recognition result is in the transcription.completed event
        if (data.type === 'conversation.item.input_audio_transcription.completed') {
            console.log(`[Final Transcript] ${data.transcript}`);
        }

        // Received the finished event
        if (data.type === 'session.finished') {
            console.log('[Action] Closing WebSocket connection after session finished...');

            if (ws.readyState === WebSocket.OPEN) {
                ws.close(1000, 'ASR finished');
            }
        }
    } catch (e) {
        console.error('[Error] Failed to parse message:', message);
    }
});

ws.on('close', (code, reason) => {
    console.log(`[WebSocket] Connection closed: ${code} - ${reason}`);
});

ws.on('error', (err) => {
    console.error('[WebSocket Error]', err);
});

// ===== Session update =====
function sendSessionUpdate() {
    const eventNoVad = {
        event_id: 'event_123',
        type: 'session.update',
        session: {
            modalities: ['text'],
            input_audio_format: 'pcm',
            sample_rate: 16000,
            // input_audio_transcription: {
            //     language: 'zh'
            // },
            turn_detection: null
        }
    };

    const eventVad = {
        event_id: 'event_123',
        type: 'session.update',
        session: {
            modalities: ['text'],
            input_audio_format: 'pcm',
            sample_rate: 16000,
            // input_audio_transcription: {
            //     language: 'zh'
            // },
            turn_detection: {
                type: 'server_vad',
                threshold: 0.0,
                silence_duration_ms: 400
            }
        }
    };

    if (enableServerVad) {
        console.log('[Send Event] VAD Mode:\n', JSON.stringify(eventVad, null, 2));
        ws.send(JSON.stringify(eventVad));
    } else {
        console.log('[Send Event] Manual Mode:\n', JSON.stringify(eventNoVad, null, 2));
        ws.send(JSON.stringify(eventNoVad));
    }
}

// ===== Send the audio file stream =====
function sendAudio(audioPath) {
    setTimeout(() => {
        console.log(`[File Read Start] ${audioPath}`);
        const buffer = fs.readFileSync(audioPath);

        let offset = 0;
        const chunkSize = 3200; // About 0.1s of PCM16 audio

        function sendChunk() {
            if (!isRunning) return;
            if (offset >= buffer.length) {
                isRunning = false; // Stop sending audio
                console.log('[File Read End]');
                if (ws.readyState === WebSocket.OPEN) {
                    if (!enableServerVad) {
                        const commitEvent = {
                            event_id: 'event_789',
                            type: 'input_audio_buffer.commit'
                        };
                        ws.send(JSON.stringify(commitEvent));
                        console.log('[Send Commit Event]');
                    }

                    const finishEvent = {
                        event_id: 'event_987',
                        type: 'session.finish'
                    };
                    ws.send(JSON.stringify(finishEvent));
                    console.log('[Send Finish Event]');
                }

                return;
            }

            if (ws.readyState !== WebSocket.OPEN) {
                console.log('[Stop] WebSocket is not open.');
                return;
            }

            const chunk = buffer.slice(offset, offset + chunkSize);
            offset += chunkSize;

            const encoded = chunk.toString('base64');
            const appendEvent = {
                event_id: `event_${Date.now()}`,
                type: 'input_audio_buffer.append',
                audio: encoded
            };

            ws.send(JSON.stringify(appendEvent));
            console.log(`[Send Audio Event] ${appendEvent.event_id}`);

            setTimeout(sendChunk, 100); // Simulate real-time sending
        }

        sendChunk();
    }, 3000); // Wait for the session configuration to complete
}

C#

The example code is as follows:

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

class Program {
    private static ClientWebSocket _webSocket = new ClientWebSocket();
    private static CancellationTokenSource _cts = new CancellationTokenSource();
    private static bool _sessionFinished = false;
    private static bool _isRunning = true;

    // Controls whether to use VAD mode
    private const bool EnableServerVad = true;

    // The API Key differs between the Singapore and Beijing regions. Get your API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    // If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: private static readonly string ApiKey = "sk-xxx"
    private static readonly string ApiKey = Environment.GetEnvironmentVariable("DASHSCOPE_API_KEY") ?? throw new InvalidOperationException("DASHSCOPE_API_KEY environment variable is not set.");
    private const string Model = "qwen3-asr-flash-realtime";
    // The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ by region.
    private const string BaseUrl = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime";
    private const string AudioFilePath = "your_audio_file.pcm"; // Replace with the path to your PCM audio file

    static async Task Main(string[] args) {
        var url = $"{BaseUrl}?model={Model}";
        Console.WriteLine($"Connecting to server: {url}");

        // Set authentication headers
        _webSocket.Options.SetRequestHeader("Authorization", $"Bearer {ApiKey}");
        _webSocket.Options.SetRequestHeader("OpenAI-Beta", "realtime=v1");

        await _webSocket.ConnectAsync(new Uri(url), _cts.Token);
        Console.WriteLine("Connected to server.");

        // Start the message receiving task
        var receiveTask = ReceiveMessagesAsync();

        // Send the session.update configuration
        await SendSessionUpdateAsync();

        // Send the audio stream
        await SendAudioStreamAsync();

        // Wait for the session.finished event
        while (!_sessionFinished && !_cts.IsCancellationRequested) {
            await Task.Delay(100);
        }

        if (_webSocket.State == WebSocketState.Open) {
            await _webSocket.CloseAsync(WebSocketCloseStatus.NormalClosure, "ASR finished", _cts.Token);
        }
    }

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

    // Send the session.update event
    private static async Task SendSessionUpdateAsync() {
        var session = new JsonObject {
            ["modalities"] = new JsonArray { "text" },
            ["input_audio_format"] = "pcm",
            ["sample_rate"] = 16000,
            // ["input_audio_transcription"] = new JsonObject { ["language"] = "zh" }
        };
        if (EnableServerVad) {
            session["turn_detection"] = new JsonObject {
                ["type"] = "server_vad",
                ["threshold"] = 0.0,
                ["silence_duration_ms"] = 400
            };
        } else {
            session["turn_detection"] = null;
        }
        var payload = new JsonObject {
            ["event_id"] = "event_123",
            ["type"] = "session.update",
            ["session"] = session
        };
        Console.WriteLine($"Sending session.update: {payload.ToJsonString()}");
        await SendAsync(payload.ToJsonString());
    }

    // Send the audio stream (send one PCM chunk every 100ms)
    private static async Task SendAudioStreamAsync() {
        await Task.Delay(3000); // Wait for the session configuration to complete
        const int chunkSize = 3200; // 100ms @ 16kHz 16bit mono
        using var fs = new FileStream(AudioFilePath, FileMode.Open, FileAccess.Read);
        var buffer = new byte[chunkSize];
        int read;
        while (_isRunning && (read = await fs.ReadAsync(buffer, 0, chunkSize)) > 0) {
            if (_webSocket.State != WebSocketState.Open) break;
            string b64 = Convert.ToBase64String(buffer, 0, read);
            var append = new JsonObject {
                ["event_id"] = $"event_{DateTimeOffset.Now.ToUnixTimeMilliseconds()}",
                ["type"] = "input_audio_buffer.append",
                ["audio"] = b64
            };
            await SendAsync(append.ToJsonString());
            await Task.Delay(100);
        }
        Console.WriteLine("File read end.");
        if (_webSocket.State == WebSocketState.Open) {
            if (!EnableServerVad) {
                var commit = new JsonObject {
                    ["event_id"] = "event_789",
                    ["type"] = "input_audio_buffer.commit"
                };
                await SendAsync(commit.ToJsonString());
            }
            var finish = new JsonObject {
                ["event_id"] = "event_987",
                ["type"] = "session.finish"
            };
            await SendAsync(finish.ToJsonString());
        }
    }

    // Receive and handle server-side events
    private static async Task ReceiveMessagesAsync() {
        var buffer = new byte[16384];
        var sb = new StringBuilder();
        while (_webSocket.State == WebSocketState.Open && !_cts.IsCancellationRequested) {
            try {
                var result = await _webSocket.ReceiveAsync(new ArraySegment<byte>(buffer), _cts.Token);
                if (result.MessageType == WebSocketMessageType.Close) {
                    await _webSocket.CloseAsync(WebSocketCloseStatus.NormalClosure, "Closing", _cts.Token);
                    break;
                }
                sb.Append(Encoding.UTF8.GetString(buffer, 0, result.Count));
                if (!result.EndOfMessage) continue;
                string text = sb.ToString();
                sb.Clear();
                var data = JsonNode.Parse(text);
                string? type = data?["type"]?.GetValue<string>();
                Console.WriteLine($"Received event: {type}");
                if (type == "conversation.item.input_audio_transcription.completed") {
                    Console.WriteLine($"Final transcript: {data!["transcript"]}");
                } else if (type == "session.finished") {
                    Console.WriteLine("Session finished, closing...");
                    _sessionFinished = true;
                    _isRunning = false;
                    break;
                }
            } catch (Exception ex) {
                Console.WriteLine($"Receive error: {ex.Message}");
                break;
            }
        }
    }
}

PHP

The example project has the following directory structure:

my-php-project/

├── composer.json

├── vendor/

└── index.php

The contents of composer.json are as follows. Adjust the dependency versions as needed:

{
    "require": {
        "react/event-loop": "^1.3",
        "react/socket": "^1.11",
        "ratchet/pawl": "^0.4"
    }
}

The contents of index.php are as follows:

<?php

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

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

// The API Key differs between the Singapore and Beijing regions. Get your API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
// If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: $api_key = "sk-xxx"
$api_key = getenv("DASHSCOPE_API_KEY");
$model = 'qwen3-asr-flash-realtime';
// The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ by region.
$base_url = 'wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime';
$websocket_url = $base_url . '?model=' . $model;
$audio_file_path = 'your_audio_file.pcm'; // Replace with the path to your PCM audio file

// Controls whether to use VAD mode
$enable_server_vad = true;

$loop = Loop::get();
$socketConnector = new SocketConnector($loop, [
    'tls' => ['verify_peer' => false, 'verify_peer_name' => false],
]);
$connector = new Connector($loop, $socketConnector);

$headers = [
    'Authorization' => 'Bearer ' . $api_key,
    'OpenAI-Beta' => 'realtime=v1',
];

$is_running = true;

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

    // Listen for server-side events
    $conn->on('message', function($msg) use ($conn, &$is_running) {
        $event = json_decode($msg, true);
        if (!isset($event['type'])) {
            return;
        }
        echo "Received event: {$event['type']}\n";
        if ($event['type'] === 'conversation.item.input_audio_transcription.completed') {
            echo "Final transcript: {$event['transcript']}\n";
        } elseif ($event['type'] === 'session.finished') {
            echo "Session finished, closing...\n";
            $is_running = false;
            $conn->close();
        }
    });
    $conn->on('close', function() {
        echo "Connection closed\n";
    });

    // Send the session.update event
    sendSessionUpdate($conn, $enable_server_vad);

    // Start sending audio after the session configuration completes
    $loop->addTimer(3, function () use ($conn, $audio_file_path, $enable_server_vad, $loop, &$is_running) {
        sendAudioStream($conn, $audio_file_path, $enable_server_vad, $loop, $is_running);
    });
}, function ($e) {
    echo "Unable to connect: {$e->getMessage()}\n";
});

$loop->run();

// Send the session.update event
function sendSessionUpdate($conn, $enable_server_vad) {
    $session = [
        'modalities' => ['text'],
        'input_audio_format' => 'pcm',
        'sample_rate' => 16000,
        // 'input_audio_transcription' => ['language' => 'zh'],
        'turn_detection' => $enable_server_vad ? [
            'type' => 'server_vad',
            'threshold' => 0.0,
            'silence_duration_ms' => 400,
        ] : null,
    ];
    $event = [
        'event_id' => 'event_123',
        'type' => 'session.update',
        'session' => $session,
    ];
    $conn->send(json_encode($event));
    echo "Sent session.update\n";
}

// Send the audio stream (send one PCM chunk every 100ms)
function sendAudioStream($conn, $audio_file_path, $enable_server_vad, $loop, &$is_running) {
    $fp = fopen($audio_file_path, 'rb');
    if (!$fp) {
        echo "Unable to open the audio file\n";
        return;
    }
    $send_chunk = function() use ($conn, $fp, $enable_server_vad, $loop, &$send_chunk, &$is_running) {
        if (!$is_running) {
            fclose($fp);
            return;
        }
        $chunk = fread($fp, 3200); // 100ms @ 16kHz 16bit mono
        if ($chunk === false || strlen($chunk) === 0) {
            fclose($fp);
            echo "Audio stream ended\n";
            if (!$enable_server_vad) {
                $conn->send(json_encode([
                    'event_id' => 'event_789',
                    'type' => 'input_audio_buffer.commit',
                ]));
            }
            $conn->send(json_encode([
                'event_id' => 'event_987',
                'type' => 'session.finish',
            ]));
            return;
        }
        $append = [
            'event_id' => 'event_' . round(microtime(true) * 1000),
            'type' => 'input_audio_buffer.append',
            'audio' => base64_encode($chunk),
        ];
        $conn->send(json_encode($append));
        $loop->addTimer(0.1, $send_chunk);
    };
    $send_chunk();
}

Go

Before you run the example, install the required dependency:

go get github.com/gorilla/websocket

package main

import (
	"encoding/base64"
	"encoding/json"
	"fmt"
	"io"
	"log"
	"net/http"
	"os"
	"time"

	"github.com/gorilla/websocket"
)

const (
	// The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ by region.
	baseURL         = "wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime"
	model           = "qwen3-asr-flash-realtime"
	audioFile       = "your_audio_file.pcm" // Replace with the path to your PCM audio file
	enableServerVad = true                  // Controls whether to use VAD mode
)

// Server-side event structure
type ServerEvent struct {
	Type       string `json:"type"`
	Transcript string `json:"transcript,omitempty"`
}

func main() {
	// The API Key differs between the Singapore and Beijing regions. Get your API Key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
	// If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: apiKey := "sk-xxx"
	apiKey := os.Getenv("DASHSCOPE_API_KEY")

	url := baseURL + "?model=" + model
	log.Printf("Connecting to server: %s", url)

	conn, err := connect(url, apiKey)
	if err != nil {
		log.Fatal("Failed to connect to WebSocket: ", err)
	}
	defer conn.Close()

	// Start a goroutine to receive messages
	sessionFinished := make(chan bool, 1)
	go receiveMessages(conn, sessionFinished)

	// Send session.update
	if err := sendSessionUpdate(conn); err != nil {
		log.Fatal("Failed to send session.update: ", err)
	}

	// Wait for the session configuration to complete
	time.Sleep(3 * time.Second)

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

	// Wait for session.finished
	<-sessionFinished
}

// Establish the WebSocket connection
func connect(url, apiKey string) (*websocket.Conn, error) {
	headers := http.Header{}
	headers.Set("Authorization", "Bearer "+apiKey)
	headers.Set("OpenAI-Beta", "realtime=v1")
	conn, _, err := websocket.DefaultDialer.Dial(url, headers)
	return conn, err
}

// Send the session.update event
func sendSessionUpdate(conn *websocket.Conn) error {
	session := map[string]interface{}{
		"modalities":         []string{"text"},
		"input_audio_format": "pcm",
		"sample_rate":        16000,
		// "input_audio_transcription": map[string]interface{}{
		// 	"language": "zh",
		// },
	}
	if enableServerVad {
		session["turn_detection"] = map[string]interface{}{
			"type":                "server_vad",
			"threshold":           0.0,
			"silence_duration_ms": 400,
		}
	} else {
		session["turn_detection"] = nil
	}
	event := map[string]interface{}{
		"event_id": "event_123",
		"type":     "session.update",
		"session":  session,
	}
	payload, _ := json.Marshal(event)
	log.Printf("Sending session.update: %s", string(payload))
	return conn.WriteMessage(websocket.TextMessage, payload)
}

// Send the audio stream (send one PCM chunk every 100ms)
func sendAudioStream(conn *websocket.Conn) error {
	f, err := os.Open(audioFile)
	if err != nil {
		return err
	}
	defer f.Close()

	chunk := make([]byte, 3200) // 100ms @ 16kHz 16bit mono
	for {
		n, err := f.Read(chunk)
		if n > 0 {
			event := map[string]interface{}{
				"event_id": fmt.Sprintf("event_%d", time.Now().UnixMilli()),
				"type":     "input_audio_buffer.append",
				"audio":    base64.StdEncoding.EncodeToString(chunk[:n]),
			}
			payload, _ := json.Marshal(event)
			if err := conn.WriteMessage(websocket.TextMessage, payload); err != nil {
				return err
			}
			time.Sleep(100 * time.Millisecond)
		}
		if err == io.EOF {
			break
		}
		if err != nil {
			return err
		}
	}
	log.Println("Audio stream ended")
	if !enableServerVad {
		commitEvt := map[string]interface{}{
			"event_id": "event_789",
			"type":     "input_audio_buffer.commit",
		}
		payload, _ := json.Marshal(commitEvt)
		if err := conn.WriteMessage(websocket.TextMessage, payload); err != nil {
			return err
		}
	}
	finishEvt := map[string]interface{}{
		"event_id": "event_987",
		"type":     "session.finish",
	}
	payload, _ := json.Marshal(finishEvt)
	return conn.WriteMessage(websocket.TextMessage, payload)
}

// Receive and handle server-side events
func receiveMessages(conn *websocket.Conn, sessionFinished chan<- bool) {
	for {
		_, msg, err := conn.ReadMessage()
		if err != nil {
			log.Println("Error reading message: ", err)
			sessionFinished <- true
			return
		}
		var evt ServerEvent
		if err := json.Unmarshal(msg, &evt); err != nil {
			log.Println("Error parsing message: ", err)
			continue
		}
		log.Printf("Received event: %s", evt.Type)
		switch evt.Type {
		case "conversation.item.input_audio_transcription.completed":
			log.Printf("Final transcript: %s", evt.Transcript)
		case "session.finished":
			log.Println("Session finished")
			sessionFinished <- true
			return
		}
	}
}