实时语音识别

Node.js

需安装相关依赖：

npm install ws
npm install uuid

示例代码如下：

const fs = require('fs');
const WebSocket = require('ws');
const { v4: uuidv4 } = require('uuid'); // 用于生成UUID

// 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
// 若没有配置环境变量，请用百炼API Key将下行替换为：const apiKey = "sk-xxx"
const apiKey = process.env.DASHSCOPE_API_KEY;
// 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference/
const url = 'wss://dashscope.aliyuncs.com/api-ws/v1/inference/'; // WebSocket服务器地址
const audioFile = 'asr_example.wav'; // 替换为您的音频文件路径

// 生成32位随机ID
const TASK_ID = uuidv4().replace(/-/g, '').slice(0, 32);

// 创建WebSocket客户端
const ws = new WebSocket(url, {
  headers: {
    Authorization: `bearer ${apiKey}`
  }
});

let taskStarted = false; // 标记任务是否已启动

// 连接打开时发送run-task指令
ws.on('open', () => {
  console.log('连接到服务器');
  sendRunTask();
});

// 接收消息处理
ws.on('message', (data) => {
  const message = JSON.parse(data);
  switch (message.header.event) {
    case 'task-started':
      console.log('任务开始');
      taskStarted = true;
      sendAudioStream();
      break;
    case 'result-generated':
      console.log('识别结果：', message.payload.output.sentence.text);
      if (message.payload.usage) {
        console.log('任务计费时长（秒）：', message.payload.usage.duration);
      }
      break;
    case 'task-finished':
      console.log('任务完成');
      ws.close();
      break;
    case 'task-failed':
      console.error('任务失败：', message.header.error_message);
      ws.close();
      break;
    default:
      console.log('未知事件：', message.header.event);
  }
});

// 如果没有收到task-started事件，关闭连接
ws.on('close', () => {
  if (!taskStarted) {
    console.error('任务未启动，关闭连接');
  }
});

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

// 发送音频流
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); // 每100ms发送一次
    }
  }

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

  audioStream.on('end', () => {
    console.log('音频流结束');
    sendFinishTask();
  });

  audioStream.on('error', (err) => {
    console.error('读取音频文件错误：', err);
    ws.close();
  });
}

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

// 错误处理
ws.on('error', (error) => {
  console.error('WebSocket错误：', error);
});

C#

示例代码如下：

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;
    // 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
    // 若没有配置环境变量，请用百炼API Key将下行替换为：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.");

    // 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference/
    private const string WebSocketUrl = "wss://dashscope.aliyuncs.com/api-ws/v1/inference/";
    // 替换为您的音频文件路径
    private const string AudioFilePath = "asr_example.wav";

    static async Task Main(string[] args) {
        // 建立WebSocket连接，配置headers进行鉴权
        _webSocket.Options.SetRequestHeader("Authorization", $"bearer {ApiKey}");

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

        // 启动线程异步接收WebSocket消息
        var receiveTask = ReceiveMessagesAsync();

        // 发送run-task指令
        string _taskId = Guid.NewGuid().ToString("N"); // 生成32位随机ID
        var runTaskJson = GenerateRunTaskJson(_taskId);
        await SendAsync(runTaskJson);

        // 等待task-started事件
        while (!_taskStartedReceived) {
            await Task.Delay(100, _cancellationTokenSource.Token);
        }

        // 读取本地文件，向服务器发送待识别音频流
        await SendAudioStreamAsync(AudioFilePath);

        // 发送finish-task指令结束任务
        var finishTaskJson = GenerateFinishTaskJson(_taskId);
        await SendAsync(finishTaskJson);

        // 等待task-finished事件
        while (!_taskFinishedReceived && !_cancellationTokenSource.IsCancellationRequested) {
            try {
                await Task.Delay(100, _cancellationTokenSource.Token);
            } catch (OperationCanceledException) {
                // 任务已被取消，退出循环
                break;
            }
        }

        // 关闭连接
        if (!_cancellationTokenSource.IsCancellationRequested) {
            await _webSocket.CloseAsync(WebSocketCloseStatus.NormalClosure, "Closing", _cancellationTokenSource.Token);
        }

        _cancellationTokenSource.Cancel();
        try {
            await receiveTask;
        } catch (OperationCanceledException) {
            // 忽略操作取消异常
        }
    }

    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("任务开启成功");
                            _taskStartedReceived = true;
                            break;
                        case "result-generated":
                            Console.WriteLine($"识别结果：{message["payload"]?["output"]?["sentence"]?["text"]?.GetValue<string>()}");
                            if (message["payload"]?["usage"] != null && message["payload"]?["usage"]?["duration"] != null) {
                                Console.WriteLine($"任务计费时长（秒）：{message["payload"]?["usage"]?["duration"]?.GetValue<int>()}");
                            }
                            break;
                        case "task-finished":
                            Console.WriteLine("任务完成");
                            _taskFinishedReceived = true;
                            _cancellationTokenSource.Cancel();
                            break;
                        case "task-failed":
                            Console.WriteLine($"任务失败：{message["header"]?["error_message"]?.GetValue<string>()}");
                            _cancellationTokenSource.Cancel();
                            break;
                    }
                }
            }
        } catch (OperationCanceledException) {
            // 忽略操作取消异常
        }
    }

    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]; // 每次发送100ms的音频数据
            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); // 间隔100ms
            }
        }
    }

    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"] = "fun-asr-realtime",
                ["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

示例代码目录结构为：

my-php-project/

├── composer.json

├── vendor/

└── index.php

composer.json内容如下，相关依赖的版本号请根据实际情况自行决定：

{
    "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/"
        }
    }
}

index.php内容如下：

<?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;

// 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
// 若没有配置环境变量，请用百炼API Key将下行替换为：$api_key = "sk-xxx"
$api_key = getenv("DASHSCOPE_API_KEY");
// 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference/
$websocket_url = 'wss://dashscope.aliyuncs.com/api-ws/v1/inference/';
$audio_file_path = 'asr_example.wav'; // 替换为您的音频文件路径

$loop = Loop::get();

// 创建自定义的连接器
$socketConnector = new SocketConnector($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 "连接到WebSocket服务器\n";

    // 启动异步接收WebSocket消息的线程
    $conn->on('message', function($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 "未知的消息格式\n";
        }
    });

    // 监听连接关闭
    $conn->on('close', function($code = null, $reason = null) {
        echo "连接已关闭\n";
        if ($code !== null) {
            echo "关闭代码: " . $code . "\n";
        }
        if ($reason !== null) {
            echo "关闭原因：" . $reason . "\n";
        }
    });

    // 生成任务ID
    $taskId = generateTaskId();

    // 发送 run-task 指令
    sendRunTaskMessage($conn, $taskId);

}, function ($e) {
    echo "无法连接：{$e->getMessage()}\n";
});

$loop->run();

/**
 * 生成任务ID
 * @return string
 */
function generateTaskId(): string {
    return bin2hex(random_bytes(16));
}

/**
 * 发送 run-task 指令
 * @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" => "fun-asr-realtime",
            "parameters" => [
                "format" => "wav",
                "sample_rate" => 16000
            ],
            "input" => []
        ]
    ]);
    echo "准备发送run-task指令：" . $runTaskMessage . "\n";
    $conn->send($runTaskMessage);
    echo "run-task指令已发送\n";
}

/**
 * 读取音频文件
 * @param string $filePath
 * @return bool|string
 */
function readAudioFile(string $filePath) {
    $voiceData = file_get_contents($filePath);
    if ($voiceData === false) {
        echo "无法读取音频文件\n";
    }
    return $voiceData;
}

/**
 * 分割音频数据
 * @param string $data
 * @param int $chunkSize
 * @return array
 */
function splitAudioData(string $data, int $chunkSize): array {
    return str_split($data, $chunkSize);
}

/**
 * 发送 finish-task 指令
 * @param $conn
 * @param $taskId
 */
function sendFinishTaskMessage($conn, $taskId) {
    $finishTaskMessage = json_encode([
        "header" => [
            "action" => "finish-task",
            "task_id" => $taskId,
            "streaming" => "duplex"
        ],
        "payload" => [
            "input" => []
        ]
    ]);
    echo "准备发送finish-task指令: " . $finishTaskMessage . "\n";
    $conn->send($finishTaskMessage);
    echo "finish-task指令已发送\n";
}

/**
 * 处理事件
 * @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 "任务开始，发送音频数据...\n";
            // 读取音频文件
            $voiceData = readAudioFile($audio_file_path);
            if ($voiceData === false) {
                echo "无法读取音频文件\n";
                $conn->close();
                return;
            }

            // 分割音频数据
            $chunks = splitAudioData($voiceData, 1024);

            // 定义发送函数
            $sendChunk = function() use ($conn, &$chunks, $loop, &$sendChunk, &$allChunksSent, $taskId) {
                if (!empty($chunks)) {
                    $chunk = array_shift($chunks);
                    $binaryMsg = new Frame($chunk, true, Frame::OP_BINARY);
                    $conn->send($binaryMsg);
                    // 100ms后发送下一个片段
                    $loop->addTimer(0.1, $sendChunk);
                } else {
                    echo "所有数据块已发送\n";
                    $allChunksSent = true;

                    // 发送 finish-task 指令
                    sendFinishTaskMessage($conn, $taskId);
                }
            };

            // 开始发送音频数据
            $sendChunk();
            break;
        case 'result-generated':
            $result = $response['payload']['output']['sentence'];
            echo "识别结果：" . $result['text'] . "\n";
            if (isset($response['payload']['usage']['duration'])) {
                echo "任务计费时长（秒）：" . $response['payload']['usage']['duration'] . "\n";
            }
            break;
        case 'task-finished':
            echo "任务完成\n";
            $conn->close();
            break;
        case 'task-failed':
            echo "任务失败\n";
            echo "错误代码：" . $response['header']['error_code'] . "\n";
            echo "错误信息：" . $response['header']['error_message'] . "\n";
            $conn->close();
            break;
        case 'error':
            echo "错误：" . $response['payload']['message'] . "\n";
            break;
        default:
            echo "未知事件：" . $response['header']['event'] . "\n";
            break;
    }

    // 如果所有数据已发送且任务已完成，关闭连接
    if ($allChunksSent && $response['header']['event'] == 'task-finished') {
        // 等待1秒以确保所有数据都已传输完毕
        $loop->addTimer(1, function() use ($conn) {
            $conn->close();
            echo "客户端关闭连接\n";
        });
    }
}

Go

package main

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

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

const (
	// 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference/
	wsURL     = "wss://dashscope.aliyuncs.com/api-ws/v1/inference/" // WebSocket服务器地址
	audioFile = "asr_example.wav"                                   // 替换为您的音频文件路径
)

var dialer = websocket.DefaultDialer

func main() {
	// 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
    // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey := "sk-xxx"
	apiKey := os.Getenv("DASHSCOPE_API_KEY")

	// 连接WebSocket服务
	conn, err := connectWebSocket(apiKey)
	if err != nil {
		log.Fatal("连接WebSocket失败：", err)
	}
	defer closeConnection(conn)

	// 启动一个goroutine来接收结果
	taskStarted := make(chan bool)
	taskDone := make(chan bool)
	startResultReceiver(conn, taskStarted, taskDone)

	// 发送run-task指令
	taskID, err := sendRunTaskCmd(conn)
	if err != nil {
		log.Fatal("发送run-task指令失败：", err)
	}

	// 等待task-started事件
	waitForTaskStarted(taskStarted)

	// 发送待识别音频文件流
	if err := sendAudioData(conn); err != nil {
		log.Fatal("发送音频失败：", err)
	}

	// 发送finish-task指令
	if err := sendFinishTaskCmd(conn, taskID); err != nil {
		log.Fatal("发送finish-task指令失败：", err)
	}

	// 等待任务完成或失败
	<-taskDone
}

// 定义结构体来表示JSON数据
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"`
}

// 连接WebSocket服务
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
}

// 启动一个goroutine异步接收WebSocket消息
func startResultReceiver(conn *websocket.Conn, taskStarted chan<- bool, taskDone chan<- bool) {
	go func() {
		for {
			_, message, err := conn.ReadMessage()
			if err != nil {
				log.Println("解析服务器消息失败：", err)
				return
			}
			var event Event
			err = json.Unmarshal(message, &event)
			if err != nil {
				log.Println("解析事件失败：", err)
				continue
			}
			if handleEvent(conn, event, taskStarted, taskDone) {
				return
			}
		}
	}()
}

// 发送run-task指令
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
}

// 生成run-task指令
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:     "fun-asr-realtime",
			Parameters: Params{
				Format:     "wav",
				SampleRate: 16000,
			},
			Input: Input{},
		},
	}
	runTaskCmdJSON, err := json.Marshal(runTaskCmd)
	return string(runTaskCmdJSON), taskID, err
}

// 等待task-started事件
func waitForTaskStarted(taskStarted chan bool) {
	select {
	case <-taskStarted:
		fmt.Println("任务开启成功")
	case <-time.After(10 * time.Second):
		log.Fatal("等待task-started超时，任务开启失败")
	}
}

// 发送音频数据
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
}

// 发送finish-task指令
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
}

// 生成finish-task指令
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
}

// 处理事件
func handleEvent(conn *websocket.Conn, event Event, taskStarted chan<- bool, taskDone chan<- bool) bool {
	switch event.Header.Event {
	case "task-started":
		fmt.Println("收到task-started事件")
		taskStarted <- true
	case "result-generated":
		if event.Payload.Output.Sentence.Text != "" {
			fmt.Println("识别结果：", event.Payload.Output.Sentence.Text)
		}
		if event.Payload.Usage != nil {
			fmt.Println("任务计费时长（秒）：", event.Payload.Usage.Duration)
		}
	case "task-finished":
		fmt.Println("任务完成")
		taskDone <- true
		return true
	case "task-failed":
		handleTaskFailed(event, conn)
		taskDone <- true
		return true
	default:
		log.Printf("预料之外的事件：%v", event)
	}
	return false
}

// 处理任务失败事件
func handleTaskFailed(event Event, conn *websocket.Conn) {
	if event.Header.ErrorMessage != "" {
		log.Fatalf("任务失败：%s", event.Header.ErrorMessage)
	} else {
		log.Fatal("未知原因导致任务失败")
	}
}

// 关闭连接
func closeConnection(conn *websocket.Conn) {
	if conn != nil {
		conn.Close()
	}
}

Python

在运行示例前，请确保已使用以下命令安装依赖：

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

请不要将示例代码文件命名为 websocket.py，这会与 websocket 库产生命名冲突，导致如下错误：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)

# 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
# 若没有配置环境变量，请用百炼API Key将下行替换为：API_KEY="sk-xxx"
API_KEY = os.environ.get("DASHSCOPE_API_KEY", "sk-xxx")
QWEN_MODEL = "qwen3-asr-flash-realtime"
# 以下是北京地域baseUrl，如果使用新加坡地域的模型，需要将baseUrl替换为：wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime
baseUrl = "wss://dashscope.aliyuncs.com/api-ws/v1/realtime"
url = f"{baseUrl}?model={QWEN_MODEL}"
print(f"Connecting to server: {url}")

# 注意： 如果是非vad模式，建议持续发送的音频时长累加不超过60s
enableServerVad = True
is_running = True  # 增加运行标志位

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.")

    # 会话更新事件
    event_manual = {
        "event_id": "event_123",
        "type": "session.update",
        "session": {
            "modalities": ["text"],
            "input_audio_format": "pcm",
            "sample_rate": 16000,
            "input_audio_transcription": {
                # 语种标识，可选，如果有明确的语种信息，建议设置
                "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  # 停止音频发送线程
            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)  # 等待会话更新完成
    global is_running

    with open(local_audio_path, 'rb') as audio_file:
        logger.info(f"文件读取开始: {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"文件读取完毕: {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已关闭，停止发送音频。")
                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)  # 模拟实时采集

# 初始化日志
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

在运行示例前，请确保已安装Java-WebSocket依赖：

<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());
    // 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
    // 若没有配置环境变量，请用百炼API Key将下行替换为：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";

    // 控制是否使用 VAD 模式
    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();

        // 以下是北京地域baseUrl，如果使用新加坡地域的模型，需要将baseUrl替换为：wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime
        String baseUrl = "wss://dashscope.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));

                    // 最终识别结果在 transcription.completed 事件中
                    if ("conversation.item.input_audio_transcription.completed".equals(eventType)) {
                        logger.info("Final transcript: " + data.optString("transcript"));
                    }

                    // 收到结束事件 → 停止发送线程并关闭连接
                    if ("session.finished".equals(eventType)) {
                        logger.info("Closing WebSocket connection after session finished...");

                        isRunning.set(false); // 停止发送音频线程
                        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());
            }
        };

        // 添加请求头
        client.addHeader("Authorization", "Bearer " + API_KEY);
        client.addHeader("OpenAI-Beta", "realtime=v1");

        client.connectBlocking(); // 阻塞直到连接建立

        // 替换为待识别的音频文件路径
        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();
    }

    /** 会话更新事件（开启/关闭 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) // 手动模式
                );

        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());
        }
    }

    /** 发送音频文件流 */
    private static void sendAudio(String localAudioPath) throws Exception {
        Thread.sleep(3000); // 等会话准备
        byte[] allBytes = Files.readAllBytes(Paths.get(localAudioPath));
        logger.info("文件读取开始");

        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; // 避免在断开后继续发送
            }

            Thread.sleep(100); // 模拟实时发送
        }

        logger.info("文件读取完毕");

        if (client != null && client.isOpen()) {
            // 非 VAD 模式下需要 commit
            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.");
        }
    }

    /** 初始化日志 */
    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

在运行示例前，请确保已使用以下命令安装依赖：

npm install ws

/**
 * Qwen-ASR Realtime WebSocket 客户端（Node.js版）
 * 功能：
 * - 支持 VAD 模式和 Manual 模式
 * - 发送 session.update 启动会话
 * - 持续发送音频块 input_audio_buffer.append
 * - 如果是Manual模式，需要发送 input_audio_buffer.commit
 * - 发送session.finish事件
 * - 收到 session.finished 事件后关闭连接
 */

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

// ===== 配置 =====
// 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
// 若没有配置环境变量，请用百炼API Key将下行替换为：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为VAD模式，false为Manual模式
const localAudioPath = 'your_audio_file.pcm'; // PCM16、16kHz音频文件路径

// 以下是北京地域baseUrl，如果使用新加坡地域的模型，需要将baseUrl替换为：wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime
const baseUrl = 'wss://dashscope.aliyuncs.com/api-ws/v1/realtime';
const url = `${baseUrl}?model=${MODEL}`;

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

// ===== 状态控制 =====
let isRunning = true;

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

// ===== 事件绑定 =====
ws.on('open', () => {
    console.log('[WebSocket] Connected to server.');
    sendSessionUpdate();
    // 启动音频发送线程
    sendAudio(localAudioPath);
});

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

        // 最终识别结果在 transcription.completed 事件中
        if (data.type === 'conversation.item.input_audio_transcription.completed') {
            console.log(`[Final Transcript] ${data.transcript}`);
        }

        // 收到结束事件
        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);
});

// ===== 会话更新 =====
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));
    }
}

// ===== 发送音频文件流 =====
function sendAudio(audioPath) {
    setTimeout(() => {
        console.log(`[File Read Start] ${audioPath}`);
        const buffer = fs.readFileSync(audioPath);

        let offset = 0;
        const chunkSize = 3200; // 约0.1s的PCM16音频

        function sendChunk() {
            if (!isRunning) return;
            if (offset >= buffer.length) {
                isRunning = false; // 停止发送音频
                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); // 模拟实时发送
        }

        sendChunk();
    }, 3000); // 等待会话配置完成
}