实时语音识别-通义千问

中国大陆（北京）

国际（新加坡）

使用DashScope SDK

使用WebSocket API

以下示例演示如何通过 WebSocket 连接发送本地音频文件并获取识别结果。

1. 获取API Key：获取API Key，安全起见，推荐将API Key配置到环境变量。

2. 编写并运行代码：通过代码实现认证、连接、发送音频和接收结果的完整流程（详情请参见交互流程）。

   Python

   在运行示例前，请确保已使用以下命令安装依赖：

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

   请不要将示例代码文件命名为 websocket.py，否则可能触发如下错误：AttributeError: module 'websocket' has no attribute 'WebSocketApp'. Did you mean: 'WebSocket'?

   # pip install websocket-client
   import os
   import time
   import json
   import threading
   import base64
   import websocket
   import logging
   import logging.handlers
   from datetime import datetime
   
   logger = logging.getLogger(__name__)
   logger.setLevel(logging.DEBUG)
   
   # 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
   # 若没有配置环境变量，请用百炼API Key将下行替换为：API_KEY="sk-xxx"
   API_KEY = os.environ.get("DASHSCOPE_API_KEY", "sk-xxx")
   QWEN_MODEL = "qwen3-asr-flash-realtime"
   # 以下是北京地域baseUrl，如果使用新加坡地域的模型，需要将baseUrl替换为：wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime
   baseUrl = "wss://dashscope.aliyuncs.com/api-ws/v1/realtime"
   url = f"{baseUrl}?model={QWEN_MODEL}"
   print(f"Connecting to server: {url}")
   
   # 注意： 如果是非vad模式，建议持续发送的音频时长累加不超过60s
   enableServerVad = True
   is_running = True  # 增加运行标志位
   
   headers = [
       "Authorization: Bearer " + API_KEY,
       "OpenAI-Beta: realtime=v1"
   ]
   
   def init_logger():
       formatter = logging.Formatter('%(asctime)s|%(levelname)s|%(message)s')
       f_handler = logging.handlers.RotatingFileHandler(
           "omni_tester.log", maxBytes=100 * 1024 * 1024, backupCount=3
       )
       f_handler.setLevel(logging.DEBUG)
       f_handler.setFormatter(formatter)
   
       console = logging.StreamHandler()
       console.setLevel(logging.DEBUG)
       console.setFormatter(formatter)
   
       logger.addHandler(f_handler)
       logger.addHandler(console)
   
   def on_open(ws):
       logger.info("Connected to server.")
   
       # 会话更新事件
       event_manual = {
           "event_id": "event_123",
           "type": "session.update",
           "session": {
               "modalities": ["text"],
               "input_audio_format": "pcm",
               "sample_rate": 16000,
               "input_audio_transcription": {
                   # 语种标识，可选，如果有明确的语种信息，建议设置
                   "language": "zh"
                   # 语料，可选，如果有语料，建议设置以增强识别效果
                   # "corpus": {
                   #     "text": ""
                   # }
               },
               "turn_detection": None
           }
       }
       event_vad = {
           "event_id": "event_123",
           "type": "session.update",
           "session": {
               "modalities": ["text"],
               "input_audio_format": "pcm",
               "sample_rate": 16000,
               "input_audio_transcription": {
                   "language": "zh"
               },
               "turn_detection": {
                   "type": "server_vad",
                   "threshold": 0.2,
                   "silence_duration_ms": 800
               }
           }
       }
       if enableServerVad:
           logger.info(f"Sending event: {json.dumps(event_vad, indent=2)}")
           ws.send(json.dumps(event_vad))
       else:
           logger.info(f"Sending event: {json.dumps(event_manual, indent=2)}")
           ws.send(json.dumps(event_manual))
   
   def on_message(ws, message):
       global is_running
       try:
           data = json.loads(message)
           logger.info(f"Received event: {json.dumps(data, ensure_ascii=False, indent=2)}")
           if data.get("type") == "conversation.item.input_audio_transcription.completed":
               logger.info(f"Final transcript: {data.get('transcript')}")
               logger.info("Closing WebSocket connection after completion...")
               is_running = False  # 停止音频发送线程
               ws.close()
       except json.JSONDecodeError:
           logger.error(f"Failed to parse message: {message}")
   
   def on_error(ws, error):
       logger.error(f"Error: {error}")
   
   def on_close(ws, close_status_code, close_msg):
       logger.info(f"Connection closed: {close_status_code} - {close_msg}")
   
   def send_audio(ws, local_audio_path):
       time.sleep(3)  # 等待会话更新完成
       global is_running
   
       with open(local_audio_path, 'rb') as audio_file:
           logger.info(f"文件读取开始: {datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]}")
           while is_running:
               audio_data = audio_file.read(3200)  # ~0.1s PCM16/16kHz
               if not audio_data:
                   logger.info(f"文件读取完毕: {datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]}")
                   if not enableServerVad and ws.sock and ws.sock.connected:
                       commit_event = {
                           "event_id": "event_789",
                           "type": "input_audio_buffer.commit"
                       }
                       ws.send(json.dumps(commit_event))
                   break
   
               if not ws.sock or not ws.sock.connected:
                   logger.info("WebSocket已关闭，停止发送音频。")
                   break
   
               encoded_data = base64.b64encode(audio_data).decode('utf-8')
               eventd = {
                   "event_id": f"event_{int(time.time() * 1000)}",
                   "type": "input_audio_buffer.append",
                   "audio": encoded_data
               }
               ws.send(json.dumps(eventd))
               logger.info(f"Sending audio event: {eventd['event_id']}")
               time.sleep(0.1)  # 模拟实时采集
   
   # 初始化日志
   init_logger()
   logger.info(f"Connecting to WebSocket server at {url}...")
   
   local_audio_path = "your_audio_file.pcm"
   ws = websocket.WebSocketApp(
       url,
       header=headers,
       on_open=on_open,
       on_message=on_message,
       on_error=on_error,
       on_close=on_close
   )
   
   thread = threading.Thread(target=send_audio, args=(ws, local_audio_path))
   thread.start()
   ws.run_forever()

   Java

   在运行示例前，请确保已安装Java-WebSocket依赖：

   Maven

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

   Gradle

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

   import org.java_websocket.client.WebSocketClient;
   import org.java_websocket.handshake.ServerHandshake;
   import org.json.JSONObject;
   
   import java.net.URI;
   import java.nio.file.Files;
   import java.nio.file.Paths;
   import java.util.Base64;
   import java.util.concurrent.atomic.AtomicBoolean;
   import java.util.logging.*;
   
   public class QwenASRRealtimeClient {
   
       private static final Logger logger = Logger.getLogger(QwenASRRealtimeClient.class.getName());
       // 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
       // 若没有配置环境变量，请用百炼API Key将下行替换为：private static final String API_KEY = "sk-xxx"
       private static final String API_KEY = System.getenv().getOrDefault("DASHSCOPE_API_KEY", "sk-xxx");
       private static final String MODEL = "qwen3-asr-flash-realtime";
   
       // 控制是否使用 VAD 模式
       private static final boolean enableServerVad = true;
   
       private static final AtomicBoolean isRunning = new AtomicBoolean(true);
       private static WebSocketClient client;
   
       public static void main(String[] args) throws Exception {
           initLogger();
   
           // 以下是北京地域baseUrl，如果使用新加坡地域的模型，需要将baseUrl替换为：wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime
           String baseUrl = "wss://dashscope.aliyuncs.com/api-ws/v1/realtime";
           String url = baseUrl + "?model=" + MODEL;
           logger.info("Connecting to server: " + url);
   
           client = new WebSocketClient(new URI(url)) {
               @Override
               public void onOpen(ServerHandshake handshake) {
                   logger.info("Connected to server.");
                   sendSessionUpdate();
               }
   
               @Override
               public void onMessage(String message) {
                   try {
                       JSONObject data = new JSONObject(message);
                       String eventType = data.optString("type");
   
                       logger.info("Received event: " + data.toString(2));
   
                       // 收到最终识别结果事件 → 停止发送线程并关闭连接
                       if ("conversation.item.input_audio_transcription.completed".equals(eventType)) {
                           logger.info("Final transcript: " + data.optString("transcript"));
                           logger.info("Closing WebSocket connection after completion...");
   
                           isRunning.set(false); // 停止发送音频线程
                           if (this.isOpen()) {
                               this.close(1000, "ASR completed");
                           }
                       }
                   } catch (Exception e) {
                       logger.severe("Failed to parse message: " + message);
                   }
               }
   
               @Override
               public void onClose(int code, String reason, boolean remote) {
                   logger.info("Connection closed: " + code + " - " + reason);
               }
   
               @Override
               public void onError(Exception ex) {
                   logger.severe("Error: " + ex.getMessage());
               }
           };
   
           // 添加请求头
           client.addHeader("Authorization", "Bearer " + API_KEY);
           client.addHeader("OpenAI-Beta", "realtime=v1");
   
           client.connectBlocking(); // 阻塞直到连接建立
   
           // 替换为待识别的音频文件路径
           String localAudioPath = "your_audio_file.pcm";
           Thread audioThread = new Thread(() -> {
               try {
                   sendAudio(localAudioPath);
               } catch (Exception e) {
                   logger.severe("Audio sending thread error: " + e.getMessage());
               }
           });
           audioThread.start();
       }
   
       /** 会话更新事件（开启/关闭 VAD） */
       private static void sendSessionUpdate() {
           JSONObject eventNoVad = new JSONObject()
                   .put("event_id", "event_123")
                   .put("type", "session.update")
                   .put("session", new JSONObject()
                           .put("modalities", new String[]{"text"})
                           .put("input_audio_format", "pcm")
                           .put("sample_rate", 16000)
                           .put("input_audio_transcription", new JSONObject()
                                   .put("language", "zh"))
                           .put("turn_detection", JSONObject.NULL) // 手动模式
                   );
   
           JSONObject eventVad = new JSONObject()
                   .put("event_id", "event_123")
                   .put("type", "session.update")
                   .put("session", new JSONObject()
                           .put("modalities", new String[]{"text"})
                           .put("input_audio_format", "pcm")
                           .put("sample_rate", 16000)
                           .put("input_audio_transcription", new JSONObject()
                                   .put("language", "zh"))
                           .put("turn_detection", new JSONObject()
                                   .put("type", "server_vad")
                                   .put("threshold", 0.2)
                                   .put("silence_duration_ms", 800))
                   );
   
           if (enableServerVad) {
               logger.info("Sending event (VAD):\n" + eventVad.toString(2));
               client.send(eventVad.toString());
           } else {
               logger.info("Sending event (Manual):\n" + eventNoVad.toString(2));
               client.send(eventNoVad.toString());
           }
       }
   
       /** 发送音频文件流 */
       private static void sendAudio(String localAudioPath) throws Exception {
           Thread.sleep(3000); // 等会话准备
           byte[] allBytes = Files.readAllBytes(Paths.get(localAudioPath));
           logger.info("文件读取开始");
   
           int offset = 0;
           while (isRunning.get() && offset < allBytes.length) {
               int chunkSize = Math.min(3200, allBytes.length - offset);
               byte[] chunk = new byte[chunkSize];
               System.arraycopy(allBytes, offset, chunk, 0, chunkSize);
               offset += chunkSize;
   
               if (client != null && client.isOpen()) {
                   String encoded = Base64.getEncoder().encodeToString(chunk);
                   JSONObject eventd = new JSONObject()
                           .put("event_id", "event_" + System.currentTimeMillis())
                           .put("type", "input_audio_buffer.append")
                           .put("audio", encoded);
   
                   client.send(eventd.toString());
                   logger.info("Sending audio event: " + eventd.getString("event_id"));
               } else {
                   break; // 避免在断开后继续发送
               }
   
               Thread.sleep(100); // 模拟实时发送
           }
   
           logger.info("文件读取完毕");
   
           // 非 VAD 模式下需要 commit
           if (!enableServerVad && client != null && client.isOpen()) {
               JSONObject commitEvent = new JSONObject()
                       .put("event_id", "event_789")
                       .put("type", "input_audio_buffer.commit");
               client.send(commitEvent.toString());
               logger.info("Sent commit event for manual mode.");
           }
       }
   
       /** 初始化日志 */
       private static void initLogger() {
           logger.setLevel(Level.ALL);
           Logger rootLogger = Logger.getLogger("");
           for (Handler h : rootLogger.getHandlers()) {
               rootLogger.removeHandler(h);
           }
   
           Handler consoleHandler = new ConsoleHandler();
           consoleHandler.setLevel(Level.ALL);
           consoleHandler.setFormatter(new SimpleFormatter());
           logger.addHandler(consoleHandler);
       }
   }

   Node.js

   在运行示例前，请确保已使用以下命令安装依赖：

   npm install ws

   /**
    * Qwen-ASR Realtime WebSocket 客户端（Node.js版）
    * 功能：
    * - 支持 VAD 模式和 Manual 模式
    * - 发送 session.update 启动会话
    * - 持续发送音频块 input_audio_buffer.append
    * - Manual 模式下发送 input_audio_buffer.commit
    * - 收到 completed 事件后关闭连接并停止发送
    */
   
   const WebSocket = require('ws');
   const fs = require('fs');
   
   // ===== 配置 =====
   // 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
   // 若没有配置环境变量，请用百炼API Key将下行替换为：const API_KEY = "sk-xxx"
   const API_KEY = process.env.DASHSCOPE_API_KEY || 'sk-xxx';
   const MODEL = 'qwen3-asr-flash-realtime';
   const enableServerVad = true; // true为VAD模式，false为Manual模式
   const localAudioPath = 'your_audio_file.pcm'; // PCM16、16kHz音频文件路径
   
   // 以下是北京地域baseUrl，如果使用新加坡地域的模型，需要将baseUrl替换为：wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime
   const baseUrl = 'wss://dashscope.aliyuncs.com/api-ws/v1/realtime';
   const url = `${baseUrl}?model=${MODEL}`;
   
   console.log(`Connecting to server: ${url}`);
   
   // ===== 状态控制 =====
   let isRunning = true;
   
   // ===== 建立连接 =====
   const ws = new WebSocket(url, {
       headers: {
           'Authorization': `Bearer ${API_KEY}`,
           'OpenAI-Beta': 'realtime=v1'
       }
   });
   
   // ===== 事件绑定 =====
   ws.on('open', () => {
       console.log('[WebSocket] Connected to server.');
       sendSessionUpdate();
       // 启动音频发送线程
       sendAudio(localAudioPath);
   });
   
   ws.on('message', (message) => {
       try {
           const data = JSON.parse(message);
           console.log('[Received Event]:', JSON.stringify(data, null, 2));
   
           // 收到完成事件
           if (data.type === 'conversation.item.input_audio_transcription.completed') {
               console.log(`[Final Transcript] ${data.transcript}`);
               console.log('[Action] Closing WebSocket connection after completion...');
               isRunning = false; // 停止发送音频
               if (ws.readyState === WebSocket.OPEN) {
                   ws.close(1000, 'ASR completed');
               }
           }
       } catch (e) {
           console.error('[Error] Failed to parse message:', message);
       }
   });
   
   ws.on('close', (code, reason) => {
       console.log(`[WebSocket] Connection closed: ${code} - ${reason}`);
   });
   
   ws.on('error', (err) => {
       console.error('[WebSocket Error]', err);
   });
   
   // ===== 会话更新 =====
   function sendSessionUpdate() {
       const eventNoVad = {
           event_id: 'event_123',
           type: 'session.update',
           session: {
               modalities: ['text'],
               input_audio_format: 'pcm',
               sample_rate: 16000,
               input_audio_transcription: {
                   language: 'zh'
               },
               turn_detection: null
           }
       };
   
       const eventVad = {
           event_id: 'event_123',
           type: 'session.update',
           session: {
               modalities: ['text'],
               input_audio_format: 'pcm',
               sample_rate: 16000,
               input_audio_transcription: {
                   language: 'zh'
               },
               turn_detection: {
                   type: 'server_vad',
                   threshold: 0.2,
                   silence_duration_ms: 800
               }
           }
       };
   
       if (enableServerVad) {
           console.log('[Send Event] VAD Mode:\n', JSON.stringify(eventVad, null, 2));
           ws.send(JSON.stringify(eventVad));
       } else {
           console.log('[Send Event] Manual Mode:\n', JSON.stringify(eventNoVad, null, 2));
           ws.send(JSON.stringify(eventNoVad));
       }
   }
   
   // ===== 发送音频文件流 =====
   function sendAudio(audioPath) {
       setTimeout(() => {
           console.log(`[File Read Start] ${audioPath}`);
           const buffer = fs.readFileSync(audioPath);
   
           let offset = 0;
           const chunkSize = 3200; // 约0.1s的PCM16音频
   
           function sendChunk() {
               if (!isRunning) return;
               if (offset >= buffer.length) {
                   console.log('[File Read End]');
                   if (!enableServerVad && ws.readyState === WebSocket.OPEN) {
                       const commitEvent = {
                           event_id: 'event_789',
                           type: 'input_audio_buffer.commit'
                       };
                       ws.send(JSON.stringify(commitEvent));
                       console.log('[Send Commit Event]');
                   }
                   return;
               }
   
               if (ws.readyState !== WebSocket.OPEN) {
                   console.log('[Stop] WebSocket is not open.');
                   return;
               }
   
               const chunk = buffer.slice(offset, offset + chunkSize);
               offset += chunkSize;
   
               const encoded = chunk.toString('base64');
               const appendEvent = {
                   event_id: `event_${Date.now()}`,
                   type: 'input_audio_buffer.append',
                   audio: encoded
               };
   
               ws.send(JSON.stringify(appendEvent));
               console.log(`[Send Audio Event] ${appendEvent.event_id}`);
   
               setTimeout(sendChunk, 100); // 模拟实时发送
           }
   
           sendChunk();
       }, 3000); // 等待会话配置完成
   }