Alibaba Cloud Model Studio:CosyVoice 音声合成 WebSocket API

Go

package main

import (
	"encoding/json"
	"fmt"
	"net/http"
	"os"
	"strings"
	"time"

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

const (
	// Use this URL for Singapore region. For Beijing region, replace with: wss://dashscope.aliyuncs.com/api-ws/v1/inference/
	wsURL      = "wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference/"
	outputFile = "output.mp3"
)

func main() {
	// Get API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
	// If no environment variable is set, replace next line with: apiKey := "sk-xxx"
	apiKey := os.Getenv("DASHSCOPE_API_KEY")

	// Clear output file
	os.Remove(outputFile)
	os.Create(outputFile)

	// Connect WebSocket
	header := make(http.Header)
	header.Add("X-DashScope-DataInspection", "enable")
	header.Add("Authorization", fmt.Sprintf("bearer %s", apiKey))

	conn, resp, err := websocket.DefaultDialer.Dial(wsURL, header)
	if err != nil {
		if resp != nil {
			fmt.Printf("Connection failed HTTP status code: %d\n", resp.StatusCode)
		}
		fmt.Println("Connection failed:", err)
		return
	}
	defer conn.Close()

	// Generate task ID
	taskID := uuid.New().String()
	fmt.Printf("Generated task ID: %s\n", taskID)

	// Send run-task instruction
	runTaskCmd := map[string]interface{}{
		"header": map[string]interface{}{
			"action":    "run-task",
			"task_id":   taskID,
			"streaming": "duplex",
		},
		"payload": map[string]interface{}{
			"task_group": "audio",
			"task":       "tts",
			"function":   "SpeechSynthesizer",
			"model":      "cosyvoice-v3-flash",
			"parameters": map[string]interface{}{
				"text_type":   "PlainText",
				"voice":       "longanyang",
				"format":      "mp3",
				"sample_rate": 22050,
				"volume":      50,
				"rate":        1,
				"pitch":       1,
				// If enable_ssml is true, only one continue-task instruction is allowed. Otherwise, it returns “Text request limit violated, expected 1.”
				"enable_ssml": false,
			},
			"input": map[string]interface{}{},
		},
	}

	runTaskJSON, _ := json.Marshal(runTaskCmd)
	fmt.Printf("Sent run-task instruction: %s\n", string(runTaskJSON))

	err = conn.WriteMessage(websocket.TextMessage, runTaskJSON)
	if err != nil {
		fmt.Println("Failed to send run-task:", err)
		return
	}

	textSent := false

	// Process messages
	for {
		messageType, message, err := conn.ReadMessage()
		if err != nil {
			fmt.Println("Failed to read message:", err)
			break
		}

		// Process binary message
		if messageType == websocket.BinaryMessage {
			fmt.Printf("Received binary message, length: %d\n", len(message))
			file, _ := os.OpenFile(outputFile, os.O_APPEND|os.O_WRONLY|os.O_CREATE, 0644)
			file.Write(message)
			file.Close()
			continue
		}

		// Process text message
		messageStr := string(message)
		fmt.Printf("Received text message: %s\n", strings.ReplaceAll(messageStr, "\n", ""))

		// Simple JSON parse to get event type
		var msgMap map[string]interface{}
		if json.Unmarshal(message, &msgMap) == nil {
			if header, ok := msgMap["header"].(map[string]interface{}); ok {
				if event, ok := header["event"].(string); ok {
					fmt.Printf("Event type: %s\n", event)

					switch event {
					case "task-started":
						fmt.Println("=== Received task-started event ===")

						if !textSent {
							// Send continue-task instruction

							texts := []string{"Before my bed, moonlight shines bright, I suspect it's frost upon the ground.", "I raise my eyes to gaze at the bright moon, then bow my head, thinking of home."}

							for _, text := range texts {
								continueTaskCmd := map[string]interface{}{
									"header": map[string]interface{}{
										"action":    "continue-task",
										"task_id":   taskID,
										"streaming": "duplex",
									},
									"payload": map[string]interface{}{
										"input": map[string]interface{}{
											"text": text,
										},
									},
								}

								continueTaskJSON, _ := json.Marshal(continueTaskCmd)
								fmt.Printf("Sent continue-task instruction: %s\n", string(continueTaskJSON))

								err = conn.WriteMessage(websocket.TextMessage, continueTaskJSON)
								if err != nil {
									fmt.Println("Failed to send continue-task:", err)
									return
								}
							}

							textSent = true

							// Delay before sending finish-task
							time.Sleep(500 * time.Millisecond)

							// Send finish-task instruction
							finishTaskCmd := map[string]interface{}{
								"header": map[string]interface{}{
									"action":    "finish-task",
									"task_id":   taskID,
									"streaming": "duplex",
								},
								"payload": map[string]interface{}{
									"input": map[string]interface{}{},
								},
							}

							finishTaskJSON, _ := json.Marshal(finishTaskCmd)
							fmt.Printf("Sent finish-task instruction: %s\n", string(finishTaskJSON))

							err = conn.WriteMessage(websocket.TextMessage, finishTaskJSON)
							if err != nil {
								fmt.Println("Failed to send finish-task:", err)
								return
							}
						}

					case "task-finished":
						fmt.Println("=== Task completed ===")
						return

					case "task-failed":
						fmt.Println("=== Task failed ===")
						if header["error_message"] != nil {
							fmt.Printf("Error message: %s\n", header["error_message"])
						}
						return

					case "result-generated":
						fmt.Println("Received result-generated event")
					}
				}
			}
		}
	}
}

C#

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

class Program {
    // Get API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    // If no environment variable is set, replace next line with: 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.");

    // Use this URL for Singapore region. For Beijing region, replace with: wss://dashscope.aliyuncs.com/api-ws/v1/inference/
    private const string WebSocketUrl = "wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference/";
    // Output file path
    private const string OutputFilePath = "output.mp3";

    // WebSocket client
    private static ClientWebSocket _webSocket = new ClientWebSocket();
    // Cancellation token source
    private static CancellationTokenSource _cancellationTokenSource = new CancellationTokenSource();
    // Task ID
    private static string? _taskId;
    // Task started flag
    private static TaskCompletionSource<bool> _taskStartedTcs = new TaskCompletionSource<bool>();

    static async Task Main(string[] args) {
        try {
            // Clear output file
            ClearOutputFile(OutputFilePath);

            // Connect to WebSocket service
            await ConnectToWebSocketAsync(WebSocketUrl);

            // Start receiving messages
            Task receiveTask = ReceiveMessagesAsync();

            // Send run-task instruction
            _taskId = GenerateTaskId();
            await SendRunTaskCommandAsync(_taskId);

            // Wait for task-started event
            await _taskStartedTcs.Task;

            // Send continue-task instructions
            string[] texts = {
                "Before my bed, moonlight shines bright",
                "I suspect it's frost upon the ground",
                "I raise my eyes to gaze at the bright moon",
                "then bow my head, thinking of home"
            };
            foreach (string text in texts) {
                await SendContinueTaskCommandAsync(text);
            }

            // Send finish-task instruction
            await SendFinishTaskCommandAsync(_taskId);

            // Wait for receive task to complete
            await receiveTask;

            Console.WriteLine("Task completed. Connection closed.");
        } catch (OperationCanceledException) {
            Console.WriteLine("Task canceled.");
        } catch (Exception ex) {
            Console.WriteLine($"Error: {ex.Message}");
        } finally {
            _cancellationTokenSource.Cancel();
            _webSocket.Dispose();
        }
    }

    private static void ClearOutputFile(string filePath) {
        if (File.Exists(filePath)) {
            File.WriteAllText(filePath, string.Empty);
            Console.WriteLine("Output file cleared.");
        } else {
            Console.WriteLine("Output file does not exist. No action needed.");
        }
    }

    private static async Task ConnectToWebSocketAsync(string url) {
        var uri = new Uri(url);
        if (_webSocket.State == WebSocketState.Connecting || _webSocket.State == WebSocketState.Open) {
            return;
        }

        // Set WebSocket request headers
        _webSocket.Options.SetRequestHeader("Authorization", $"bearer {ApiKey}");
        _webSocket.Options.SetRequestHeader("X-DashScope-DataInspection", "enable");

        try {
            await _webSocket.ConnectAsync(uri, _cancellationTokenSource.Token);
            Console.WriteLine("Successfully connected to WebSocket service.");
        } catch (OperationCanceledException) {
            Console.WriteLine("WebSocket connection canceled.");
        } catch (Exception ex) {
            Console.WriteLine($"WebSocket connection failed: {ex.Message}");
            throw;
        }
    }

    private static async Task SendRunTaskCommandAsync(string taskId) {
        var command = CreateCommand("run-task", taskId, "duplex", new {
            task_group = "audio",
            task = "tts",
            function = "SpeechSynthesizer",
            model = "cosyvoice-v3-flash",
            parameters = new
            {
                text_type = "PlainText",
                voice = "longanyang",
                format = "mp3",
                sample_rate = 22050,
                volume = 50,
                rate = 1,
                pitch = 1,
                // If enable_ssml is true, only one continue-task instruction is allowed. Otherwise, it returns “Text request limit violated, expected 1.”
                enable_ssml = false
            },
            input = new { }
        });

        await SendJsonMessageAsync(command);
        Console.WriteLine("Sent run-task instruction.");
    }

    private static async Task SendContinueTaskCommandAsync(string text) {
        if (_taskId == null) {
            throw new InvalidOperationException("Task ID not initialized.");
        }

        var command = CreateCommand("continue-task", _taskId, "duplex", new {
            input = new {
                text
            }
        });

        await SendJsonMessageAsync(command);
        Console.WriteLine("Sent continue-task instruction.");
    }

    private static async Task SendFinishTaskCommandAsync(string taskId) {
        var command = CreateCommand("finish-task", taskId, "duplex", new {
            input = new { }
        });

        await SendJsonMessageAsync(command);
        Console.WriteLine("Sent finish-task instruction.");
    }

    private static async Task SendJsonMessageAsync(string message) {
        var buffer = Encoding.UTF8.GetBytes(message);
        try {
            await _webSocket.SendAsync(new ArraySegment<byte>(buffer), WebSocketMessageType.Text, true, _cancellationTokenSource.Token);
        } catch (OperationCanceledException) {
            Console.WriteLine("Message send canceled.");
        }
    }

    private static async Task ReceiveMessagesAsync() {
        while (_webSocket.State == WebSocketState.Open) {
            var response = await ReceiveMessageAsync();
            if (response != null) {
                var eventStr = response.RootElement.GetProperty("header").GetProperty("event").GetString();
                switch (eventStr) {
                    case "task-started":
                        Console.WriteLine("Task started.");
                        _taskStartedTcs.TrySetResult(true);
                        break;
                    case "task-finished":
                        Console.WriteLine("Task completed.");
                        _cancellationTokenSource.Cancel();
                        break;
                    case "task-failed":
                        Console.WriteLine("Task failed: " + response.RootElement.GetProperty("header").GetProperty("error_message").GetString());
                        _cancellationTokenSource.Cancel();
                        break;
                    default:
                        // Handle result-generated here
                        break;
                }
            }
        }
    }

    private static async Task<JsonDocument?> ReceiveMessageAsync() {
        var buffer = new byte[1024 * 4];
        var segment = new ArraySegment<byte>(buffer);

        try {
            WebSocketReceiveResult result = await _webSocket.ReceiveAsync(segment, _cancellationTokenSource.Token);

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

            if (result.MessageType == WebSocketMessageType.Binary) {
                // Process binary data
                Console.WriteLine("Received binary data...");

                // Save binary data to file
                using (var fileStream = new FileStream(OutputFilePath, FileMode.Append)) {
                    fileStream.Write(buffer, 0, result.Count);
                }

                return null;
            }

            string message = Encoding.UTF8.GetString(buffer, 0, result.Count);
            return JsonDocument.Parse(message);
        } catch (OperationCanceledException) {
            Console.WriteLine("Message receive canceled.");
            return null;
        }
    }

    private static string GenerateTaskId() {
        return Guid.NewGuid().ToString("N").Substring(0, 32);
    }

    private static string CreateCommand(string action, string taskId, string streaming, object payload) {
        var command = new {
            header = new {
                action,
                task_id = taskId,
                streaming
            },
            payload
        };

        return JsonSerializer.Serialize(command);
    }
}

PHP

サンプルコードのディレクトリ構造：

my-php-project/

├── composer.json

├── vendor/

└── index.php

composer.json の内容（必要に応じてバージョンを調整）：

{
    "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 の内容：

<?php

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

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

// Get API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
// If no environment variable is set, replace next line with: $api_key = "sk-xxx"
$api_key = getenv("DASHSCOPE_API_KEY");
// Use this URL for Singapore region. For Beijing region, replace with: wss://dashscope.aliyuncs.com/api-ws/v1/inference/
$websocket_url = 'wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference/'; // WebSocket サーバーアドレス
$output_file = 'output.mp3'; // 出力ファイルパス

$loop = Loop::get();

if (file_exists($output_file)) {
    // ファイルコンテンツをクリア
    file_put_contents($output_file, '');
}

// カスタムコネクタを作成
$socketConnector = new SocketConnector($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, $output_file) {
    echo "Connected to WebSocket server\n";

    // タスク ID を生成
    $taskId = generateTaskId();

    // run-task 命令を送信
    sendRunTaskMessage($conn, $taskId);

    // continue-task 命令を送信する関数を定義
    $sendContinueTask = function() use ($conn, $loop, $taskId) {
        // 送信するテキスト
        $texts = ["Before my bed, moonlight shines bright", "I suspect it's frost upon the ground", "I raise my eyes to gaze at the bright moon", "then bow my head, thinking of home"];
        $continueTaskCount = 0;
        foreach ($texts as $text) {
            $continueTaskMessage = json_encode([
                "header" => [
                    "action" => "continue-task",
                    "task_id" => $taskId,
                    "streaming" => "duplex"
                ],
                "payload" => [
                    "input" => [
                        "text" => $text
                    ]
                ]
            ]);
            echo "Preparing to send continue-task instruction: " . $continueTaskMessage . "\n";
            $conn->send($continueTaskMessage);
            $continueTaskCount++;
        }
        echo "Number of continue-task instructions sent: " . $continueTaskCount . "\n";

        // finish-task 命令を送信
        sendFinishTaskMessage($conn, $taskId);
    };

    // task-started イベントのフラグ
    $taskStarted = false;

    // メッセージをリッスン
    $conn->on('message', function($msg) use ($conn, $sendContinueTask, $loop, &$taskStarted, $taskId, $output_file) {
        if ($msg->isBinary()) {
            // バイナリデータをローカルファイルに書き込み
            file_put_contents($output_file, $msg->getPayload(), FILE_APPEND);
        } else {
            // 非バイナリメッセージを処理
            $response = json_decode($msg, true);

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

    // 接続クローズをリッスン
    $conn->on('close', function($code = null, $reason = null) {
        echo "Connection closed\n";
        if ($code !== null) {
            echo "Close code: " . $code . "\n";
        }
        if ($reason !== null) {
            echo "Close reason: " . $reason . "\n";
        }
    });
}, function ($e) {
    echo "Cannot connect: {$e->getMessage()}\n";
});

$loop->run();

/**
 * タスク ID を生成
 * @return string
 */
function generateTaskId(): string {
    return bin2hex(random_bytes(16));
}

/**
 * run-task 命令を送信
 * @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" => "tts",
            "function" => "SpeechSynthesizer",
            "model" => "cosyvoice-v3-flash",
            "parameters" => [
                "text_type" => "PlainText",
                "voice" => "longanyang",
                "format" => "mp3",
                "sample_rate" => 22050,
                "volume" => 50,
                "rate" => 1,
                "pitch" => 1,
                // If enable_ssml is true, only one continue-task instruction is allowed. Otherwise, it returns “Text request limit violated, expected 1.”
                "enable_ssml" => false
            ],
            "input" => (object) []
        ]
    ]);
    echo "Preparing to send run-task instruction: " . $runTaskMessage . "\n";
    $conn->send($runTaskMessage);
    echo "run-task instruction sent\n";
}

/**
 * 音声ファイルを読み込み
 * @param string $filePath
 * @return bool|string
 */
function readAudioFile(string $filePath) {
    $voiceData = file_get_contents($filePath);
    if ($voiceData === false) {
        echo "Cannot read audio file\n";
    }
    return $voiceData;
}

/**
 * 音声データを分割
 * @param string $data
 * @param int $chunkSize
 * @return array
 */
function splitAudioData(string $data, int $chunkSize): array {
    return str_split($data, $chunkSize);
}

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

/**
 * イベントを処理
 * @param $conn
 * @param $response
 * @param $sendContinueTask
 * @param $loop
 * @param $taskId
 * @param $taskStarted
 */
function handleEvent($conn, $response, $sendContinueTask, $loop, $taskId, &$taskStarted) {
    switch ($response['header']['event']) {
        case 'task-started':
            echo "Task started. Sending continue-task instructions...\n";
            $taskStarted = true;
            // continue-task 命令を送信
            $sendContinueTask();
            break;
        case 'result-generated':
            // result-generated イベントを受信
            break;
        case 'task-finished':
            echo "Task completed\n";
            $conn->close();
            break;
        case 'task-failed':
            echo "Task failed\n";
            echo "Error code: " . $response['header']['error_code'] . "\n";
            echo "Error message: " . $response['header']['error_message'] . "\n";
            $conn->close();
            break;
        case 'error':
            echo "Error: " . $response['payload']['message'] . "\n";
            break;
        default:
            echo "Unknown event: " . $response['header']['event'] . "\n";
            break;
    }

    // タスクが完了した場合、接続を閉じる
    if ($response['header']['event'] == 'task-finished') {
        // すべてのデータが送信されることを保証するために 1 秒待機
        $loop->addTimer(1, function() use ($conn) {
            $conn->close();
            echo "Client closed connection\n";
        });
    }

    // task-started イベントが受信されなかった場合、接続を閉じる
    if (!$taskStarted && in_array($response['header']['event'], ['task-failed', 'error'])) {
        $conn->close();
    }
}

Node.js

依存関係をインストール：

npm install ws
npm install uuid

サンプルコード：

const WebSocket = require('ws');
const fs = require('fs');
const uuid = require('uuid').v4;

// Get API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
// If no environment variable is set, replace next line with: const apiKey = "sk-xxx"
const apiKey = process.env.DASHSCOPE_API_KEY;
// Use this URL for Singapore region. For Beijing region, replace with: wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference/
const url = 'wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference/';
// Output file path
const outputFilePath = 'output.mp3';

// Clear output file
fs.writeFileSync(outputFilePath, '');

// Create WebSocket client
const ws = new WebSocket(url, {
  headers: {
    Authorization: `bearer ${apiKey}`,
    'X-DashScope-DataInspection': 'enable'
  }
});

let taskStarted = false;
let taskId = uuid();

ws.on('open', () => {
  console.log('Connected to WebSocket server');

  // Send run-task instruction
  const runTaskMessage = JSON.stringify({
    header: {
      action: 'run-task',
      task_id: taskId,
      streaming: 'duplex'
    },
    payload: {
      task_group: 'audio',
      task: 'tts',
      function: 'SpeechSynthesizer',
      model: 'cosyvoice-v3-flash',
      parameters: {
        text_type: 'PlainText',
        voice: 'longanyang', // 音声
        format: 'mp3', // 音声フォーマット
        sample_rate: 22050, // サンプルレート
        volume: 50, // ボリューム
        rate: 1, // 話速
        pitch: 1, // ピッチ
        enable_ssml: false // SSML を有効化。true の場合、continue-task 命令は 1 つのみ許可されます。そうでない場合、「Text request limit violated, expected 1.」が返されます。
      },
      input: {}
    }
  });
  ws.send(runTaskMessage);
  console.log('Sent run-task message');
});

const fileStream = fs.createWriteStream(outputFilePath, { flags: 'a' });
ws.on('message', (data, isBinary) => {
  if (isBinary) {
    // バイナリデータをファイルに書き込み
    fileStream.write(data);
  } else {
    const message = JSON.parse(data);

    switch (message.header.event) {
      case 'task-started':
        taskStarted = true;
        console.log('Task started');
        // continue-task 命令を送信
        sendContinueTasks(ws);
        break;
      case 'task-finished':
        console.log('Task completed');
        ws.close();
        fileStream.end(() => {
          console.log('File stream closed');
        });
        break;
      case 'task-failed':
        console.error('Task failed: ', message.header.error_message);
        ws.close();
        fileStream.end(() => {
          console.log('File stream closed');
        });
        break;
      default:
        // result-generated をここで処理
        break;
    }
  }
});

function sendContinueTasks(ws) {
  const texts = [
    'Before my bed, moonlight shines bright,',
    'I suspect it\'s frost upon the ground.',
    'I raise my eyes to gaze at the bright moon,',
    'then bow my head, thinking of home.'
  ];

  texts.forEach((text, index) => {
    setTimeout(() => {
      if (taskStarted) {
        const continueTaskMessage = JSON.stringify({
          header: {
            action: 'continue-task',
            task_id: taskId,
            streaming: 'duplex'
          },
          payload: {
            input: {
              text: text
            }
          }
        });
        ws.send(continueTaskMessage);
        console.log(`Sent continue-task, text: ${text}`);
      }
    }, index * 1000); // 1 秒ごとに送信
  });

  // finish-task 命令を送信
  setTimeout(() => {
    if (taskStarted) {
      const finishTaskMessage = JSON.stringify({
        header: {
          action: 'finish-task',
          task_id: taskId,
          streaming: 'duplex'
        },
        payload: {
          input: {}
        }
      });
      ws.send(finishTaskMessage);
      console.log('Sent finish-task');
    }
  }, texts.length * 1000 + 1000); // 最後の continue-task から 1 秒後に送信
}

ws.on('close', () => {
  console.log('Disconnected from WebSocket server');
});

Java

Java を使用する場合、Java DashScope SDK の使用を推奨します。「Java SDK」をご参照ください。

以下は Java WebSocket の使用例です。実行前に、以下の依存関係をインポートしてください。

• Java-WebSocket

• jackson-databind

Maven または Gradle で依存関係を管理することを推奨します。構成例：

<dependencies>
    <!-- WebSocket Client -->
    <dependency>
        <groupId>org.java-websocket</groupId>
        <artifactId>Java-WebSocket</artifactId>
        <version>1.5.3</version>
    </dependency>

    <!-- JSON Processing -->
    <dependency>
        <groupId>com.fasterxml.jackson.core</groupId>
        <artifactId>jackson-databind</artifactId>
        <version>2.13.0</version>
    </dependency>
</dependencies>

// 他のコードは省略
dependencies {
  // WebSocket Client
  implementation 'org.java-websocket:Java-WebSocket:1.5.3'
  // JSON Processing
  implementation 'com.fasterxml.jackson.core:jackson-databind:2.13.0'
}
// 他のコードは省略

Java コード：

import com.fasterxml.jackson.databind.ObjectMapper;

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

import java.io.FileOutputStream;
import java.io.IOException;
import java.net.URI;
import java.nio.ByteBuffer;
import java.util.*;

public class TTSWebSocketClient extends WebSocketClient {
    private final String taskId = UUID.randomUUID().toString();
    private final String outputFile = "output_" + System.currentTimeMillis() + ".mp3";
    private boolean taskFinished = false;

    public TTSWebSocketClient(URI serverUri, Map<String, String> headers) {
        super(serverUri, headers);
    }

    @Override
    public void onOpen(ServerHandshake serverHandshake) {
        System.out.println("Connection successful");

        // Send run-task instruction
        // If enable_ssml is true, only one continue-task instruction is allowed. Otherwise, it returns “Text request limit violated, expected 1.”
        String runTaskCommand = "{ \"header\": { \"action\": \"run-task\", \"task_id\": \"" + taskId + "\", \"streaming\": \"duplex\" }, \"payload\": { \"task_group\": \"audio\", \"task\": \"tts\", \"function\": \"SpeechSynthesizer\", \"model\": \"cosyvoice-v3-flash\", \"parameters\": { \"text_type\": \"PlainText\", \"voice\": \"longanyang\", \"format\": \"mp3\", \"sample_rate\": 22050, \"volume\": 50, \"rate\": 1, \"pitch\": 1, \"enable_ssml\": false }, \"input\": {} }}";
        send(runTaskCommand);
    }

    @Override
    public void onMessage(String message) {
        System.out.println("Received server message: " + message);
        try {
            // Parse JSON message
            Map<String, Object> messageMap = new ObjectMapper().readValue(message, Map.class);

            if (messageMap.containsKey("header")) {
                Map<String, Object> header = (Map<String, Object>) messageMap.get("header");

                if (header.containsKey("event")) {
                    String event = (String) header.get("event");

                    if ("task-started".equals(event)) {
                        System.out.println("Received task-started event");

                        List<String> texts = Arrays.asList(
                                "Before my bed, moonlight shines bright, I suspect it's frost upon the ground",
                                "I raise my eyes to gaze at the bright moon, then bow my head, thinking of home"
                        );

                        for (String text : texts) {
                            // Send continue-task instruction
                            sendContinueTask(text);
                        }

                        // Send finish-task instruction
                        sendFinishTask();
                    } else if ("task-finished".equals(event)) {
                        System.out.println("Received task-finished event");
                        taskFinished = true;
                        closeConnection();
                    } else if ("task-failed".equals(event)) {
                        System.out.println("Task failed: " + message);
                        closeConnection();
                    }
                }
            }
        } catch (Exception e) {
            System.err.println("Exception occurred: " + e.getMessage());
        }
    }

    @Override
    public void onMessage(ByteBuffer message) {
        System.out.println("Received binary audio data size: " + message.remaining());

        try (FileOutputStream fos = new FileOutputStream(outputFile, true)) {
            byte[] buffer = new byte[message.remaining()];
            message.get(buffer);
            fos.write(buffer);
            System.out.println("Audio data written to local file " + outputFile);
        } catch (IOException e) {
            System.err.println("Failed to write audio data to local file: " + e.getMessage());
        }
    }

    @Override
    public void onClose(int code, String reason, boolean remote) {
        System.out.println("Connection closed: " + reason + " (" + code + ")");
    }

    @Override
    public void onError(Exception ex) {
        System.err.println("Error: " + ex.getMessage());
        ex.printStackTrace();
    }

    private void sendContinueTask(String text) {
        String command = "{ \"header\": { \"action\": \"continue-task\", \"task_id\": \"" + taskId + "\", \"streaming\": \"duplex\" }, \"payload\": { \"input\": { \"text\": \"" + text + "\" } }}";
        send(command);
    }

    private void sendFinishTask() {
        String command = "{ \"header\": { \"action\": \"finish-task\", \"task_id\": \"" + taskId + "\", \"streaming\": \"duplex\" }, \"payload\": { \"input\": {} }}";
        send(command);
    }

    private void closeConnection() {
        if (!isClosed()) {
            close();
        }
    }

    public static void main(String[] args) {
        try {
            // Get API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
            // If no environment variable is set, replace next line with: String apiKey = "sk-xxx"
            String apiKey = System.getenv("DASHSCOPE_API_KEY");
            if (apiKey == null || apiKey.isEmpty()) {
                System.err.println("Set DASHSCOPE_API_KEY environment variable");
                return;
            }

            Map<String, String> headers = new HashMap<>();
            headers.put("Authorization", "bearer " + apiKey);
            // Use this URL for Singapore region. For Beijing region, replace with: wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference/
            TTSWebSocketClient client = new TTSWebSocketClient(new URI("wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference/"), headers);

            client.connect();

            while (!client.isClosed() && !client.taskFinished) {
                Thread.sleep(1000);
            }
        } catch (Exception e) {
            System.err.println("Failed to connect to WebSocket service: " + e.getMessage());
            e.printStackTrace();
        }
    }
}

Python

Python を使用する場合、Python DashScope SDK の使用を推奨します。「Python SDK」をご参照ください。

以下は Python WebSocket の使用例です。実行前に、依存関係をインストールしてください。

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

import websocket
import json
import uuid
import os
import time


class TTSClient:
    def __init__(self, api_key, uri):
        """
    TTSClient インスタンスを初期化

    パラメーター：
        api_key (str): 認証用の API キー
        uri (str): WebSocket サービスアドレス
    """
        self.api_key = api_key  # API キーに置き換え
        self.uri = uri  # WebSocket アドレスに置き換え
        self.task_id = str(uuid.uuid4())  # 一意のタスク ID を生成
        self.output_file = f"output_{int(time.time())}.mp3"  # 出力音声ファイルパス
        self.ws = None  # WebSocketApp インスタンス
        self.task_started = False  # task-started が受信されたかどうか
        self.task_finished = False  # task-finished または task-failed が受信されたかどうか

    def on_open(self, ws):
        """
    WebSocket 接続が開いたときのコールバック
    音声合成を開始するために run-task 命令を送信
    """
        print("WebSocket connected")

        # run-task 命令を構築
        run_task_cmd = {
            "header": {
                "action": "run-task",
                "task_id": self.task_id,
                "streaming": "duplex"
            },
            "payload": {
                "task_group": "audio",
                "task": "tts",
                "function": "SpeechSynthesizer",
                "model": "cosyvoice-v3-flash",
                "parameters": {
                    "text_type": "PlainText",
                    "voice": "longanyang",
                    "format": "mp3",
                    "sample_rate": 22050,
                    "volume": 50,
                    "rate": 1,
                    "pitch": 1,
                    # enable_ssml が True の場合、continue-task 命令は 1 つのみ許可されます。そうでない場合、「Text request limit violated, expected 1.」が返されます。
                    "enable_ssml": False
                },
                "input": {}
            }
        }

        # run-task 命令を送信
        ws.send(json.dumps(run_task_cmd))
        print("Sent run-task instruction")

    def on_message(self, ws, message):
        """
    メッセージ受信時のコールバック
    テキストメッセージとバイナリメッセージを個別に処理
    """
        if isinstance(message, str):
            # JSON テキストメッセージを処理
            try:
                msg_json = json.loads(message)
                print(f"Received JSON message: {msg_json}")

                if "header" in msg_json:
                    header = msg_json["header"]

                    if "event" in header:
                        event = header["event"]

                        if event == "task-started":
                            print("Task started")
                            self.task_started = True

                            # continue-task 命令を送信
                            texts = [
                                "Before my bed, moonlight shines bright, I suspect it's frost upon the ground",
                                "I raise my eyes to gaze at the bright moon, then bow my head, thinking of home"
                            ]

                            for text in texts:
                                self.send_continue_task(text)

                            # すべての continue-task 命令の後に finish-task を送信
                            self.send_finish_task()

                        elif event == "task-finished":
                            print("Task completed")
                            self.task_finished = True
                            self.close(ws)

                        elif event == "task-failed":
                            error_msg = msg_json.get("error_message", "Unknown error")
                            print(f"Task failed: {error_msg}")
                            self.task_finished = True
                            self.close(ws)

            except json.JSONDecodeError as e:
                print(f"JSON parsing failed: {e}")
        else:
            # バイナリメッセージ（音声データ）を処理
            print(f"Received binary message, size: {len(message)} bytes")
            with open(self.output_file, "ab") as f:
                f.write(message)
            print(f"Audio data written to local file {self.output_file}")

    def on_error(self, ws, error):
        """エラー時のコールバック"""
        print(f"WebSocket error: {error}")

    def on_close(self, ws, close_status_code, close_msg):
        """クローズ時のコールバック"""
        print(f"WebSocket closed: {close_msg} ({close_status_code})")

    def send_continue_task(self, text):
        """合成対象テキストを含む continue-task 命令を送信"""
        cmd = {
            "header": {
                "action": "continue-task",
                "task_id": self.task_id,
                "streaming": "duplex"
            },
            "payload": {
                "input": {
                    "text": text
                }
            }
        }

        self.ws.send(json.dumps(cmd))
        print(f"Sent continue-task instruction, text: {text}")

    def send_finish_task(self):
        """音声合成を終了するために finish-task 命令を送信"""
        cmd = {
            "header": {
                "action": "finish-task",
                "task_id": self.task_id,
                "streaming": "duplex"
            },
            "payload": {
                "input": {}
            }
        }

        self.ws.send(json.dumps(cmd))
        print("Sent finish-task instruction")

    def close(self, ws):
        """接続を手動で閉じる"""
        if ws and ws.sock and ws.sock.connected:
            ws.close()
            print("Manually closed connection")

    def run(self):
        """WebSocket クライアントを開始"""
        # リクエストヘッダー（認証）を設定
        header = {
            "Authorization": f"bearer {self.api_key}",
            "X-DashScope-DataInspection": "enable"
        }

        # WebSocketApp インスタンスを作成
        self.ws = websocket.WebSocketApp(
            self.uri,
            header=header,
            on_open=self.on_open,
            on_message=self.on_message,
            on_error=self.on_error,
            on_close=self.on_close
        )

        print("Listening for WebSocket messages...")
        self.ws.run_forever()  # 長期接続を開始


# 使用例
if __name__ == "__main__":
    # Get API key: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    # If no environment variable is set, replace next line with: API_KEY = "sk-xxx"
    API_KEY = os.environ.get("DASHSCOPE_API_KEY")
    # Use this URL for Singapore region. For Beijing region, replace with: wss://dashscope.aliyuncs.com/api-ws/v1/inference/
    SERVER_URI = "wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference/"  # WebSocket アドレスに置き換え

    client = TTSClient(API_KEY, SERVER_URI)
    client.run()