Gummy实时语音识别、翻译WebSocket API

Go

package main

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

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

const (
	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() {
	// 若没有将API Key配置到环境变量，可将下行替换为：apiKey := "your_api_key"。不建议在生产环境中直接将API Key硬编码到代码中，以减少API Key泄露风险。
	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 {
	Translations  []Translation `json:"translations"`
	Transcription Transcription `json:"transcription"`
}

type Translation struct {
	SentenceID   int    `json:"sentence_id"`
	BeginTime    int64  `json:"begin_time"`
	EndTime      int64  `json:"end_time"`
	Text         string `json:"text"`
	Lang         string `json:"lang"`
	PreEndFailed bool   `json:"pre_end_failed"`
	Words        []Word `json:"words"`
	SentenceEnd  bool   `json:"sentence_end"`
}

type Transcription struct {
	SentenceID   int    `json:"sentence_id"`
	BeginTime    int64  `json:"begin_time"`
	EndTime      int64  `json:"end_time"`
	Text         string `json:"text"`
	Words        []Word `json:"words"`
	SentenceEnd  bool   `json:"sentence_end"`
}

type Word struct {
	BeginTime   int64  `json:"begin_time"`
	EndTime     int64  `json:"end_time"`
	Text        string `json:"text"`
	Punctuation string `json:"punctuation"`
	Fixed       bool   `json:"fixed"`
	SpeakerID   *int   `json:"speaker_id"`
}

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"`
}

type Params struct {
	Format                     string   `json:"format"`
	SampleRate                 int      `json:"sample_rate"`
	VocabularyID               string   `json:"vocabulary_id,omitempty"`
	TranslationTargetLanguages []string `json:"translation_target_languages,omitempty"`
	TranscriptionEnabled       bool     `json:"transcription_enabled,omitempty"`
	TranslationEnabled         bool     `json:"translation_enabled,omitempty"`
}

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("X-DashScope-DataInspection", "enable")
	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:     "gummy-realtime-v1",
			Parameters: Params{
				Format:                     "wav",
				SampleRate:                 16000,
				TranscriptionEnabled:       true,
				TranslationEnabled:         true,
				TranslationTargetLanguages: []string{"en"},
			},
			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) // 假设100ms的音频数据大约为1024字节
	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":
		fmt.Println("服务器返回结果：")
		// 解析 Translations 和 Transcription
		if event.Payload.Output != nil {
			for _, translation := range event.Payload.Output.Translations {
				fmt.Printf("	翻译结果 - Sentence ID：%d, Text：%s\n", translation.SentenceID, translation.Text)
				for _, word := range translation.Words {
					fmt.Printf("	  Word - Begin Time：%d, End Time：%d, Text：%s\n", word.BeginTime, word.EndTime, word.Text)
				}
			}

			transcription := event.Payload.Output.Transcription
			fmt.Printf("	识别结果 - Sentence ID：%d, Text：%s\n", transcription.SentenceID, transcription.Text)
			for _, word := range transcription.Words {
				fmt.Printf("	  Word - Begin Time：%d, End Time：%d, Text：%s\n", word.BeginTime, word.EndTime, word.Text)
			}
		}
	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()
	}
}

C#

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 readonly CancellationTokenSource _cancellationTokenSource = new();
    // 使用TaskCompletionSource替代轮询等待
    private static TaskCompletionSource<bool> _taskStartedTcs = new();
    private static TaskCompletionSource<bool> _taskFinishedTcs = new();

    // 从环境变量获取API密钥（请确保已设置DASHSCOPE_API_KEY）
    // 若没有将API Key配置到环境变量，可将下行替换为：private const string ApiKey="your_api_key"。不建议在生产环境中直接将API Key硬编码到代码中，以减少API Key泄露风险。
    private static readonly string ApiKey = Environment.GetEnvironmentVariable("DASHSCOPE_API_KEY")
        ?? throw new InvalidOperationException("未找到环境变量DASHSCOPE_API_KEY，请先设置API密钥");
    
    // WebSocket服务器地址
    private const string WebSocketUrl = "wss://dashscope.aliyuncs.com/api-ws/v1/inference/";
    // 音频文件路径（请确保文件存在）
    private const string AudioFilePath = "asr_example.wav";

    static async Task Main(string[] args)
    {
        Task? receiveTask = null; // Moved outside try block
        try
        {
            Console.WriteLine("开始建立WebSocket连接...");

            _webSocket.Options.SetRequestHeader("Authorization", ApiKey);
            _webSocket.Options.SetRequestHeader("X-DashScope-DataInspection", "enable");

            await _webSocket.ConnectAsync(new Uri(WebSocketUrl), _cancellationTokenSource.Token);
            Console.WriteLine("WebSocket连接成功");

            receiveTask = ReceiveMessagesAsync(); // Assigned to outer variable

            var taskId = Guid.NewGuid().ToString("N");
            var runTaskJson = GenerateRunTaskJson(taskId);
            await SendAsync(runTaskJson);
            Console.WriteLine("已发送run-task指令");

            if (!await _taskStartedTcs.Task.WaitAsync(TimeSpan.FromSeconds(10)))
            {
                Console.WriteLine("等待task-started事件超时");
                _cancellationTokenSource.Cancel();
                return;
            }

            if (!await SendAudioStreamAsync(AudioFilePath))
            {
                Console.WriteLine("音频流发送失败");
                return;
            }

            var finishTaskJson = GenerateFinishTaskJson(taskId);
            await SendAsync(finishTaskJson);
            Console.WriteLine("已发送finish-task指令");

            if (!await _taskFinishedTcs.Task.WaitAsync(TimeSpan.FromSeconds(30)))
            {
                Console.WriteLine("任务未在规定时间内完成");
                _cancellationTokenSource.Cancel();
                return;
            }
        }
        catch (Exception ex)
        {
            Console.WriteLine($"发生异常: {ex.Message}");
        }
        finally
        {
            try
            {
                if (_webSocket.State == WebSocketState.Open)
                {
                    await _webSocket.CloseAsync(WebSocketCloseStatus.NormalClosure, "正常关闭", _cancellationTokenSource.Token);
                    Console.WriteLine("WebSocket连接已关闭");
                }
            }
            catch (Exception ex)
            {
                Console.WriteLine($"关闭连接时出错: {ex.Message}");
            }
            finally
            {
                _cancellationTokenSource.Cancel();
                if (receiveTask != null) // Null check added
                {
                    try
                    {
                        await receiveTask.ConfigureAwait(false); // Safe await with ConfigureAwait
                    }
                    catch (OperationCanceledException)
                    {
                        // Ignore cancellation
                    }
                    catch (Exception ex)
                    {
                        Console.WriteLine($"等待接收任务完成时出错: {ex.Message}");
                    }
                }
            }
        }
    }

    /// <summary>
    /// 接收并处理WebSocket消息
    /// </summary>
    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("收到任务开始事件");
                            _taskStartedTcs.TrySetResult(true);
                            break;
                        case "result-generated":
                            ParseResultGenerated(message);
                            break;
                        case "task-finished":
                            Console.WriteLine("收到任务完成事件");
                            _taskFinishedTcs.TrySetResult(true);
                            break;
                        case "task-failed":
                            Console.WriteLine($"任务失败: {message["header"]?["error_message"]?.GetValue<string>()}");
                            _taskFinishedTcs.TrySetResult(true);
                            _cancellationTokenSource.Cancel();
                            break;
                    }
                }
            }
        }
        catch (OperationCanceledException)
        {
            Console.WriteLine("消息接收任务已取消");
        }
        catch (Exception ex)
        {
            Console.WriteLine($"接收消息时出错: {ex.Message}");
        }
    }

    /// <summary>
    /// 接收单条WebSocket消息
    /// </summary>
    private static async Task<JsonNode?> ReceiveMessageAsync(CancellationToken cancellationToken)
    {
        var buffer = new byte[8192]; // 增大缓冲区提高效率
        var result = await _webSocket.ReceiveAsync(new ArraySegment<byte>(buffer), cancellationToken);

        if (result.MessageType == WebSocketMessageType.Close)
        {
            Console.WriteLine("服务器要求关闭连接");
            return null;
        }

        // 处理多段消息拼接
        var messageBuilder = new StringBuilder();
        while (true)
        {
            var segment = new ArraySegment<byte>(buffer, 0, result.Count);
            messageBuilder.Append(Encoding.UTF8.GetString(segment.Array!, segment.Offset, segment.Count));
            
            if (result.EndOfMessage)
            {
                break;
            }
            
            result = await _webSocket.ReceiveAsync(new ArraySegment<byte>(buffer), cancellationToken);
        }

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

    /// <summary>
    /// 发送音频流数据
    /// </summary>
    private static async Task<bool> SendAudioStreamAsync(string filePath)
    {
        var fullPath = Path.Combine(AppContext.BaseDirectory, filePath);
        if (!File.Exists(fullPath))
        {
            Console.WriteLine($"音频文件不存在: {fullPath}");
            return false;
        }

        try
        {
            using var audioStream = File.OpenRead(fullPath);
            var buffer = new byte[4096]; // 使用4KB缓冲区
            
            // 计算发送间隔（基于16kHz 16bit mono音频）
            // 16000样本/秒 × 2字节/样本 = 32000字节/秒
            // 4096字节 ≈ 125ms音频数据
            const int intervalMs = 125;

            int bytesRead;
            while ((bytesRead = await audioStream.ReadAsync(buffer, 0, buffer.Length, _cancellationTokenSource.Token)) > 0)
            {
                await _webSocket.SendAsync(new ArraySegment<byte>(buffer, 0, bytesRead), 
                                          WebSocketMessageType.Binary, 
                                          true, 
                                          _cancellationTokenSource.Token);
                await Task.Delay(intervalMs, _cancellationTokenSource.Token);
            }
            Console.WriteLine("音频流发送完成");
            return true;
        }
        catch (OperationCanceledException)
        {
            Console.WriteLine("音频发送被取消");
            return false;
        }
        catch (Exception ex)
        {
            Console.WriteLine($"音频发送出错: {ex.Message}");
            return false;
        }
    }

    /// <summary>
    /// 解析并打印识别结果
    /// </summary>
    private static void ParseResultGenerated(JsonNode message)
    {
        // 提取翻译结果
        var translations = message["payload"]?["output"]?["translations"]?.AsArray();
        if (translations != null)
        {
            foreach (var translation in translations)
            {
                if (translation == null) continue;

                if (translation["sentence_id"] is JsonValue sentenceIdValue && sentenceIdValue.TryGetValue(out int sentenceId) &&
                    translation["begin_time"] is JsonValue beginTimeValue && beginTimeValue.TryGetValue(out int beginTime) &&
                    translation["end_time"] is JsonValue endTimeValue && endTimeValue.TryGetValue(out int endTime) &&
                    translation["text"] is JsonValue textValue && textValue.TryGetValue(out string? text) &&
                    translation["lang"] is JsonValue langValue && langValue.TryGetValue(out string? lang) &&
                    translation["words"] is JsonArray words)
                {
                    Console.WriteLine($"\n翻译结果：");
                    Console.WriteLine($"句子ID：{sentenceId}");
                    Console.WriteLine($"时间范围：{beginTime}ms - {endTime}ms");
                    Console.WriteLine($"翻译文本：{text ?? "未知"}");
                    Console.WriteLine($"语言：{lang ?? "未知"}");

                    Console.WriteLine("单词级信息：");
                    foreach (var word in words)
                    {
                        if (word == null) continue;

                        if (word["begin_time"] is JsonValue wordBeginTimeValue && wordBeginTimeValue.TryGetValue(out int wordBeginTime) &&
                            word["end_time"] is JsonValue wordEndTimeValue && wordEndTimeValue.TryGetValue(out int wordEndTime) &&
                            word["text"] is JsonValue wordTextValue && wordTextValue.TryGetValue(out string? wordText))
                        {
                            Console.WriteLine($"  {wordText} ({wordBeginTime}ms-{wordEndTime}ms)");
                        }
                    }
                }
            }
        }

        // 提取识别结果
        var transcription = message["payload"]?["output"]?["transcription"];
        if (transcription != null)
        {
            if (transcription["sentence_id"] is JsonValue sentenceIdValue && sentenceIdValue.TryGetValue(out int sentenceId) &&
                transcription["begin_time"] is JsonValue beginTimeValue && beginTimeValue.TryGetValue(out int beginTime) &&
                transcription["end_time"] is JsonValue endTimeValue && endTimeValue.TryGetValue(out int endTime) &&
                transcription["text"] is JsonValue textValue && textValue.TryGetValue(out string? text) &&
                transcription["words"] is JsonArray words)
            {
                Console.WriteLine($"\n原声识别结果：");
                Console.WriteLine($"句子ID：{sentenceId}");
                Console.WriteLine($"时间范围：{beginTime}ms - {endTime}ms");
                Console.WriteLine($"识别文本：{text ?? "未知"}");

                Console.WriteLine("单词级信息：");
                foreach (var word in words)
                {
                    if (word == null) continue;

                    if (word["begin_time"] is JsonValue wordBeginTimeValue && wordBeginTimeValue.TryGetValue(out int wordBeginTime) &&
                        word["end_time"] is JsonValue wordEndTimeValue && wordEndTimeValue.TryGetValue(out int wordEndTime) &&
                        word["text"] is JsonValue wordTextValue && wordTextValue.TryGetValue(out string? wordText))
                    {
                        Console.WriteLine($"  {wordText} ({wordBeginTime}ms-{wordEndTime}ms)");
                    }
                }
            }
        }
    }

    /// <summary>
    /// 发送JSON消息到WebSocket
    /// </summary>
    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);
        Console.WriteLine($"已发送消息: {message.Substring(0, Math.Min(100, message.Length))}...");
    }

    /// <summary>
    /// 生成run-task指令的JSON
    /// </summary>
    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"] = "gummy-realtime-v1",
                ["parameters"] = new JsonObject {
                    ["format"] = "wav",
                    ["sample_rate"] = 16000,
                    ["transcription_enabled"] = true,
                    ["translation_enabled"] = true,
                    ["translation_target_languages"] = new JsonArray {
                        "en"
                    }
                },
                ["input"] = new JsonObject()
            }
        };
        return JsonSerializer.Serialize(runTask);
    }

    /// <summary>
    /// 生成finish-task指令的JSON
    /// </summary>
    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;

# 若没有将API Key配置到环境变量，可将下行替换为：$api_key="your_api_key"。不建议在生产环境中直接将API Key硬编码到代码中，以减少API Key泄露风险。
$api_key = getenv("DASHSCOPE_API_KEY");
$websocket_url = 'wss://dashscope.aliyuncs.com/api-ws/v1/inference/'; // WebSocket服务器地址
$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,
    'X-DashScope-DataInspection' => 'enable'
];

$connector($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" => "gummy-realtime-v1",
            "parameters" => [
                "format" => "wav",
                "sample_rate" => 16000,
                "transcription_enabled" => true,
                "translation_enabled" => true,
                "translation_target_languages" => ["en"]
            ],
            "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':
            // 解析 result-generated 事件的数据
            $output = $response['payload']['output'];
            $translations = $output['translations'][0];
            $transcription = $output['transcription'];

            // 输出翻译结果
            echo "翻译结果：" . $translations['text'] . "\n";
            foreach ($translations['words'] as $word) {
                echo "文本：" . $word['text'] . ", 开始时间：" . $word['begin_time'] . ", 结束时间：" . $word['end_time'] . "\n";
            }

            // 输出转录结果
            echo "转录结果：" . $transcription['text'] . "\n";
            foreach ($transcription['words'] as $word) {
                echo "文本：" . $word['text'] . ", 开始时间：" . $word['begin_time'] . ", 结束时间：" . $word['end_time'] . "\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";
        });
    }
}

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

// 若没有将API Key配置到环境变量，可将下行替换为：apiKey = 'your_api_key'。不建议在生产环境中直接将API Key硬编码到代码中，以减少API Key泄露风险。
const apiKey = process.env.DASHSCOPE_API_KEY;
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}`,
    'X-DashScope-DataInspection': 'enable'
  }
});

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('服务器返回结果：');
      // 解析payload中的translations
      if (message.payload.output.translations && message.payload.output.translations.length > 0) {
        message.payload.output.translations.forEach(translation => {
          console.log('翻译结果：');
          console.log(`  Sentence ID：${translation.sentence_id}`);
          console.log(`  Begin Time：${translation.begin_time}ms`);
          console.log(`  End Time：${translation.end_time}ms`);
          console.log(`  Text：${translation.text}`);
          console.log(`  Language：${translation.lang}`);
          if (translation.words) {
            console.log('  Words：');
            translation.words.forEach(word => {
              console.log(`    Begin Time：${word.begin_time}ms`);
              console.log(`    End Time：${word.end_time}ms`);
              console.log(`    Text：${word.text}`);
              console.log(`    Punctuation：${word.punctuation}`);
              console.log(`    Fixed：${word.fixed}`);
            });
          }
          console.log(`  Pre End Failed：${translation.pre_end_failed}`);
          console.log(`  Sentence End：${translation.sentence_end}`);
        });
      }

      // 解析payload中的transcription
      if (message.payload.output.transcription) {
        const transcription = message.payload.output.transcription;
        console.log('识别结果：');
        console.log(`  Sentence ID：${transcription.sentence_id}`);
        console.log(`  Begin Time：${transcription.begin_time}ms`);
        console.log(`  End Time：${transcription.end_time}ms`);
        console.log(`  Text：${transcription.text}`);
        if (transcription.words) {
          console.log('  Words：');
          transcription.words.forEach(word => {
            console.log(`    Begin Time：${word.begin_time}ms`);
            console.log(`    End Time：${word.end_time}ms`);
            console.log(`    Text：${word.text}`);
            console.log(`    Punctuation：${word.punctuation}`);
            console.log(`    Fixed：${word.fixed}`);
          });
        }
        console.log(`  Sentence End：${transcription.sentence_end}`);
      }
      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: 'gummy-realtime-v1',
      parameters: {
        sample_rate: 16000,
        format: 'wav',
        transcription_enabled: true,
        translation_enabled: true,
        translation_target_languages: ['en']
      },
      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);
});