实时语音识别

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 {

    // 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，请用阿里云百炼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");
    // 以下为华北2（北京）地域的配置，调用时请将"{WorkspaceId}"替换为真实的业务空间ID，各地域的配置不同。
    private static final String URL = "wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/inference";
    private static final String AUDIO_FILE = "{YOUR_AUDIO_FILE}"; // 替换为您的音频文件路径
    private static final String MODEL = "qwen-audio-3.1-asr-flash-streaming";

    // 生成32位随机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("连接到服务器");
                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("任务开始");
                        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("识别结果：" + text);
                        if (payload.has("usage")) {
                            System.out.println("任务计费时长（秒）：" + payload.getJSONObject("usage").get("duration"));
                        }
                        break;
                    case "task-finished":
                        System.out.println("任务完成");
                        close();
                        break;
                    case "task-failed":
                        String errMsg = message.getJSONObject("header").optString("error_message");
                        System.err.println("任务失败：" + errMsg);
                        close();
                        break;
                    default:
                        System.out.println("未知事件：" + event);
                }
            }

            @Override
            public void onClose(int code, String reason, boolean remote) {
                if (!taskStarted.get()) {
                    System.err.println("任务未启动，关闭连接");
                }
            }

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

    // 发送run-task指令
    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());
    }

    // 发送音频流（每100ms发送一个二进制chunk）
    private static void sendAudioStream() {
        int chunkSize = 3200; // 100ms @ 16kHz 16bit 单声道
        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("音频流结束");
            sendFinishTask();
        } catch (Exception e) {
            System.err.println("读取音频文件错误：" + e.getMessage());
            client.close();
        }
    }

    // 发送finish-task指令
    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());
    }
}

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，请用阿里云百炼API Key将下行替换为：const apiKey = "sk-xxx"
const apiKey = process.env.DASHSCOPE_API_KEY;
// 以下为华北2（北京）地域的配置，调用时请将"{WorkspaceId}"替换为真实的业务空间ID，各地域的配置不同。
const url = 'wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/inference'; // WebSocket服务器地址
const audioFile = '{YOUR_AUDIO_FILE}'; // 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: 'qwen-audio-3.1-asr-flash-streaming',
      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);
});

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，请用阿里云百炼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.");

    // 以下为华北2（北京）地域的配置，调用时请将"{WorkspaceId}"替换为真实的业务空间ID，各地域的配置不同。
    private const string WebSocketUrl = "wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/inference";
    // 替换为您的音频文件路径
    private const string AudioFilePath = "{YOUR_AUDIO_FILE}";

    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 sb = new StringBuilder();
        WebSocketReceiveResult result;
        // 循环接收并拼接分片，直到 EndOfMessage，避免长消息被截断导致 JSON 解析失败
        do {
            result = await _webSocket.ReceiveAsync(segment, cancellationToken);
            if (result.MessageType == WebSocketMessageType.Close) {
                await _webSocket.CloseAsync(WebSocketCloseStatus.NormalClosure, "Closing", cancellationToken);
                return null;
            }
            sb.Append(Encoding.UTF8.GetString(buffer, 0, result.Count));
        } while (!result.EndOfMessage);

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

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

    private static async Task SendAudioStreamAsync(string filePath) {
        using (var audioStream = File.OpenRead(filePath)) {
            var buffer = new byte[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"] = "qwen-audio-3.1-asr-flash-streaming",
                ["parameters"] = new JsonObject {
                    ["format"] = "wav",
                    ["sample_rate"] = 16000,
                },
                ["input"] = new JsonObject()
            }
        };
        return JsonSerializer.Serialize(runTask);
    }

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

<?php

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

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

// 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，请用阿里云百炼API Key将下行替换为：$api_key = "sk-xxx"
$api_key = getenv("DASHSCOPE_API_KEY");
// 以下为华北2（北京）地域的配置，调用时请将"{WorkspaceId}"替换为真实的业务空间ID，各地域的配置不同。
$websocket_url = 'wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/inference';
$audio_file_path = '{YOUR_AUDIO_FILE}'; // 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',
    ],
    // 警告：关闭 TLS 证书校验存在中间人攻击风险，仅限本地调试；生产环境务必将 verify_peer/verify_peer_name 设为 true
    '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" => "qwen-audio-3.0-asr-flash-streaming",
            "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";
        });
    }
}

package main

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

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

const (
	// 以下为华北2（北京）地域的配置，调用时请将"{WorkspaceId}"替换为真实的业务空间ID，各地域的配置不同。
	wsURL     = "wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/inference" // WebSocket服务器地址
	audioFile = "{YOUR_AUDIO_FILE}"                                   // 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，请用阿里云百炼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:     "qwen-audio-3.1-asr-flash-streaming",
			Parameters: Params{
				Format:     "wav",
				SampleRate: 16000,
			},
			Input: Input{},
		},
	}
	runTaskCmdJSON, err := json.Marshal(runTaskCmd)
	return string(runTaskCmdJSON), taskID, err
}

// 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()
	}
}