server.js

@@ -9,7 +9,7 @@ const { MessageHistory } = require('./src/message_history.js');
 const app = express();
 const server = http.createServer(app);
 const io = socketIo(server, {
-  pingTimeout: 300000,    // 60秒超时
+  pingTimeout: 60000,    // 60秒超时
   pingInterval: 25000,   // 25秒心跳间隔
   upgradeTimeout: 30000, // 30秒升级超时
   allowEIO3: true,       // 允许Engine.IO v3客户端
@@ -135,65 +135,28 @@ const scenes = [
     defaultVideo: 'qc-bd-4.mp4',
     interactionVideo: 'qc-hc-7.mp4',
     tag: 'wakeup',
-    apiKey: 'bot-20250724150616-xqpz8', // 起床场景的API key
+    apiKey: 'bot-20250724150616-xqpz8' // 起床场景的API key
-    openingLines: [
-      // '你靠得近点...像梦里那样',
-      "刚醒就看到你，比闹钟好使一百倍。",
-      // "昨晚梦里喊你名字喊醒了，现在视频看到你，心跳比梦里还烫。",
-      // "你穿我T恤的样子...让我想咬住衣领不放。",
-      "宝贝早...你声音比阳光还暖。",
-      // "喉咙里有咖啡味...要不要来尝尝？记得上次你咬我锁骨时，咖啡还温着。",
-      "晨雾遮住你半张脸...但你的呼吸声比雾气更潮湿，让我想起你咬我耳垂的感觉。"
-    ]
   },
   {
     name: '开车',
     defaultVideo: 'kc-bd-3.mp4',
     interactionVideo: 'kc-sh-3.mp4',
     tag: 'driving',
-    apiKey: 'bot-20250623140339-r8f8b', // 开车场景的API key
+    apiKey: 'bot-20250623140339-r8f8b' // 开车场景的API key
-    openingLines: [
-      '宝贝起了？看到你的脸，我这早起的怨气‘咻’一下就飞走了。车窗外的阳光都没你眼睛亮。',
-      '刚过桥，下面河水在闪光，突然就好想带你来兜风…你负责吃零食看风景，我负责偷瞄你。',
-      // '看到那个大钟楼没？每次路过都想你。想着要是能牵着你的手，站在最高层往下看该多好。',
-      '唉，快到了…真不想挂。感觉你像块小磁铁，隔着屏幕都想把我吸过去。今天上班肯定满脑子都是你。',
-      '要开始堵车了...要是你在副驾的话，这段路该多甜呀',
-      '宝贝起床了，刚过红绿灯就忍不住想你了，路上全是你的影子~',
-      '车载音乐随机到那首我们接吻时哼的歌，心跳又乱了',
-      '导航说今天要开58分钟，其实想开58小时去你心里'
-    ]
   },
   {
-    name: '咖啡',
+    name: '喝茶',
     defaultVideo: 'hc-bd-3.mp4',
     interactionVideo: 'hc-sh-3(1).mp4',
-    tag: 'coffee',
+    tag: 'tea',
-    apiKey: 'bot-20250804180724-4dgtk', // 喝茶场景的API key
+    apiKey: 'bot-20250804180724-4dgtk' // 喝茶场景的API key
-    openingLines: [
-      '拿铁拉花是你上次画的爱心形状，甜度刚好',
-      '摩卡有点苦，要是加上你的笑容就甜了',
-      '咖啡师问我一个人？我说在等我的甜度',
-      '今天的冰拿铁好甜，是不是你偷偷往我杯子里撒糖了？',
-      '拉花师给我在咖啡里画了颗心形的奶泡，说是给视频里的小仙女加糖',
-      // '这杯好苦…但一看到你，就自动回甘了。比加十包糖都管用。你说你是不是我的专属甜味剂？'
-    ]
   },
   {
     name: '睡觉',
     defaultVideo: '8-8-sj-bd.mp4',
     interactionVideo: '8-8-sj-sh-1.mp4',
     tag: 'sleep',
-    apiKey: 'bot-20250808120704-lbxwj', // 睡觉场景的API key
+    apiKey: 'bot-20250808120704-lbxwj' // 睡觉场景的API key
-    openingLines: [
-      '宝贝，一看到你，我这电量‘噌’就满了。准备关机前最后充会儿电…嗯，用眼睛充。',
-      '熄灯前最后一道光是你，真好。感觉今天积攒的烦心事，都被你眼睛里的星星照没了。',
-      '唉…手指头碰不到你屏幕都嫌凉。下次见面，这距离得用抱抱补回来，利息按秒算。',
-      '周围好安静，就剩你的呼吸声当背景音乐了。比什么助眠App都好使…就是听久了，心跳会抢拍子。',
-      '困不困？我眼皮在打架了…但就是想再多看你几秒。感觉多看一秒，梦里遇见你的概率就大一点。',
-      '好啦，我的小月亮，该哄世界睡觉了…但你先哄哄我？随便说句什么，我当睡前故事收藏。',
-      '捕捉到一只睡前小可爱…成功！',
-      '世界要静音了…但你的声音是白名单。多说几句？'
-    ]
   }
 ];
 
@@ -310,37 +273,6 @@ app.get('/api/default-video', (req, res) => {
   });
 });
 
-// 在现有的API接口后添加
-app.get('/api/current-scene/opening-line', (req, res) => {
-  try {
-    const currentScene = getCurrentScene();
-    if (currentScene && currentScene.openingLines && currentScene.openingLines.length > 0) {
-      // 随机选择一个开场白
-      const randomIndex = Math.floor(Math.random() * currentScene.openingLines.length);
-      const selectedOpeningLine = currentScene.openingLines[randomIndex];
-      
-      res.json({
-        success: true,
-        openingLine: selectedOpeningLine,
-        sceneName: currentScene.name,
-        sceneTag: currentScene.tag
-      });
-    } else {
-      res.json({
-        success: false,
-        message: '当前场景没有配置开场白'
-      });
-    }
-  } catch (error) {
-    console.error('获取开场白失败:', error);
-    res.status(500).json({
-      success: false,
-      message: '获取开场白失败',
-      error: error.message
-    });
-  }
-});
-
 // Socket.IO 连接处理
 io.on('connection', (socket) => {
   console.log('用户连接:', socket.id);

src/chat_with_audio.js

@@ -61,15 +61,16 @@ function updateHistoryMessage(userInput, assistantResponse) {
     );
     
     // 可选：限制历史消息数量，保持最近的对话
-    const maxMessages = 20; // 保留最近10轮对话（20条消息）
+    // const maxMessages = 20; // 保留最近10轮对话（20条消息）
-    if (historyMessage.length > maxMessages) {
+    // if (historyMessage.length > maxMessages) {
-        // 保留系统消息和最近的对话
+    //     // 保留系统消息和最近的对话
-        const systemMessages = historyMessage.filter(msg => msg.role === 'system');
+    //     const systemMessages = historyMessage.filter(msg => msg.role === 'system');
-        const recentMessages = historyMessage.slice(-maxMessages + systemMessages.length);
+    //     const recentMessages = historyMessage.slice(-maxMessages + systemMessages.length);
-        historyMessage = [...systemMessages, ...recentMessages.filter(msg => msg.role !== 'system')];
+    //     historyMessage = [...systemMessages, ...recentMessages.filter(msg => msg.role !== 'system')];
-    }
+    // }
 }
 
+// 保存消息到服务端
 // 保存消息到服务端
 async function saveMessage(userInput, assistantResponse) {
     try {
@@ -197,7 +198,7 @@ async function chatWithAudioStream(userInput) {
 }
 
 // 导出初始化函数，供外部调用
-export { chatWithAudioStream, initializeHistoryMessage, getCurrentHistoryMessage, saveMessage, updateHistoryMessage };
+export { chatWithAudioStream, initializeHistoryMessage, getCurrentHistoryMessage };
 
 // 处理音频播放队列
 async function processAudioQueue() {

src/config.example.js

@@ -0,0 +1,94 @@
+// 示例配置文件 - 请复制此文件为 config.js 并填入实际的API密钥
+export const config = {
+  // LLM API配置
+  llm: {
+    apiKey: 'your_ark_api_key_here', // 请替换为实际的ARK API密钥
+    model: 'bot-20250720193048-84fkp',
+  },
+  
+  // Minimaxi API配置
+  minimaxi: {
+    apiKey: 'your_minimaxi_api_key_here', // 请替换为实际的Minimaxi API密钥
+    groupId: 'your_minimaxi_group_id_here', // 请替换为实际的Minimaxi Group ID
+  },
+  
+  // 音频配置
+  audio: {
+    model: 'speech-02-hd',
+    voiceSetting: {
+      voice_id: 'yantu-qinggang',
+      speed: 1,
+      vol: 1,
+      pitch: 0,
+      emotion: 'happy',
+    },
+    audioSetting: {
+      sample_rate: 32000,
+      bitrate: 128000,
+      format: 'mp3',
+    },
+  },
+  
+  // 系统配置
+  system: {
+    language_boost: 'auto',
+    output_format: 'hex',
+    stream: true,
+  },
+};
+
+// 验证配置是否完整
+export function validateConfig() {
+  const requiredFields = [
+    'llm.apiKey',
+    'llm.model',
+    'minimaxi.apiKey',
+    'minimaxi.groupId'
+  ];
+  
+  const missingFields = [];
+  
+  for (const field of requiredFields) {
+    const keys = field.split('.');
+    let value = config;
+    for (const key of keys) {
+      value = value[key];
+      if (!value) break;
+    }
+    
+    if (!value || value === 'your_ark_api_key_here' || value === 'your_minimaxi_api_key_here' || value === 'your_minimaxi_group_id_here') {
+      missingFields.push(field);
+    }
+  }
+  
+  if (missingFields.length > 0) {
+    console.warn('配置不完整，请检查以下字段:', missingFields);
+    return false;
+  }
+  
+  return true;
+}
+
+// 获取配置的便捷方法
+export function getLLMConfig() {
+  return {
+    apiKey: config.llm.apiKey,
+    model: config.llm.model,
+  };
+}
+
+export function getMinimaxiConfig() {
+  return {
+    apiKey: config.minimaxi.apiKey,
+    groupId: config.minimaxi.groupId,
+  };
+}
+
+export function getAudioConfig() {
+  return {
+    model: config.audio.model,
+    voiceSetting: config.audio.voiceSetting,
+    audioSetting: config.audio.audioSetting,
+    ...config.system,
+  };
+} 

src/debug_audio.js

@@ -0,0 +1,26 @@
+// 调试音频数据
+function debugAudioData(audioHex) {
+  console.log('=== 音频数据调试 ===');
+  console.log('音频数据长度:', audioHex.length);
+  console.log('音频数据前100个字符:', audioHex.substring(0, 100));
+  console.log('音频数据后100个字符:', audioHex.substring(audioHex.length - 100));
+  
+  // 检查是否有重复模式
+  const halfLength = Math.floor(audioHex.length / 2);
+  const firstHalf = audioHex.substring(0, halfLength);
+  const secondHalf = audioHex.substring(halfLength);
+  
+  if (firstHalf === secondHalf) {
+    console.log('⚠️ 警告：音频数据可能是重复的！');
+  } else {
+    console.log('✅ 音频数据没有重复');
+  }
+}
+
+// 如果在浏览器环境中运行
+if (typeof window !== 'undefined') {
+  window.debugAudioData = debugAudioData;
+  console.log('音频调试函数已挂载到 window.debugAudioData');
+}
+
+export { debugAudioData }; 

src/index.js

@@ -1,8 +1,7 @@
 console.log('视频文件:');
 // WebRTC 音视频通话应用
 // import { chatWithAudioStream } from './chat_with_audio.js';
-import { chatWithAudioStream, initializeHistoryMessage, updateHistoryMessage } from './chat_with_audio.js';
+import { chatWithAudioStream, initializeHistoryMessage } from './chat_with_audio.js';
-
 import { AudioProcessor } from './audio_processor.js';
 
 // 在应用初始化时调用
@@ -75,10 +74,6 @@ class WebRTCChat {
         this.preloadVideoResources();
         this.bindEvents();
 
-        // 添加开场白相关属性
-        this.openingAudioData = null;
-        this.isOpeningAudioReady = false;
-        
         // 在初始化完成后预加载常用视频
         // setTimeout(() => {
         //     this.logMessage('开始预加载常用视频...', 'info');
@@ -239,110 +234,6 @@ class WebRTCChat {
         }
     }
 
-    // 新增方法：初始化开场白音频
-    async initializeOpeningAudio() {
-        try {
-            console.log('开始初始化开场白音频...');
-            
-            // 获取当前场景的开场白
-            const response = await fetch('/api/current-scene/opening-line');
-            const data = await response.json();
-            
-            if (data.success && data.openingLine) {
-                console.log(`获取到开场白: ${data.openingLine}`);
-                
-                // 生成开场白音频
-                await this.generateOpeningAudio(data.openingLine);
-                this.logMessage(`开场白音频已准备就绪: ${data.openingLine}`, 'success');
-            } else {
-                console.warn('未获取到开场白:', data.message);
-            }
-        } catch (error) {
-            console.error('初始化开场白音频失败:', error);
-            this.logMessage(`开场白音频初始化失败: ${error.message}`, 'error');
-        }
-    }
-    
-    // 新增方法：生成开场白音频
-    async generateOpeningAudio(text) {
-        try {
-            // 动态导入 minimaxi_stream 模块
-            const { requestMinimaxi } = await import('./minimaxi_stream.js');
-            const { getMinimaxiConfig, getAudioConfig, getLLMConfigByScene } = await import('./config.js');
-            const { saveMessage } = await import('./chat_with_audio.js');
-            
-            const minimaxiConfig = getMinimaxiConfig();
-            const audioConfig = getAudioConfig();
-            const llmConfig = await getLLMConfigByScene();
-            
-            const requestBody = {
-                model: audioConfig.model,
-                text: text,
-                voice_setting: audioConfig.voiceSetting,
-                audio_setting: audioConfig.audioSetting,
-                language_boost: 'auto',
-                output_format: 'hex'
-            };
-            
-            console.log('开始生成开场白音频...');
-            
-            // 生成音频数据
-            const audioHexData = await requestMinimaxi({
-                apiKey: minimaxiConfig.apiKey,
-                groupId: minimaxiConfig.groupId,
-                body: requestBody,
-                stream: false, // 非流式，一次性获取完整音频
-                textPlay: false
-            });
-            
-            if (audioHexData && audioHexData.data && audioHexData.data.audio) {
-                this.openingAudioData = audioHexData.data.audio;
-                this.isOpeningAudioReady = true;
-                console.log('开场白音频生成成功');
-            }
-            // 先更新本地历史消息
-            updateHistoryMessage(`场景切换-${llmConfig.sceneName}`, text);
-
-            await saveMessage(`场景切换-${llmConfig.sceneName}`,text);
-
-        } catch (error) {
-            console.error('生成开场白音频失败:', error);
-            throw error;
-        }
-    }
-    
-    // 新增方法：播放开场白音频
-    async playOpeningAudio() {
-        if (!this.isOpeningAudioReady || !this.openingAudioData) {
-            console.warn('开场白音频未准备就绪');
-            return;
-        }
-        
-        try {
-            // 动态导入 addAudioToQueue 函数
-            const { addAudioToQueue } = await import('./minimaxi_stream.js');
-            
-            console.log('将开场白音频添加到队列');
-            await addAudioToQueue(this.openingAudioData);
-            
-            this.logMessage('开场白音频已开始播放', 'success');
-        } catch (error) {
-            console.error('播放开场白音频失败:', error);
-            this.logMessage(`播放开场白音频失败: ${error.message}`, 'error');
-        }
-    }
-    
-    // 新增方法：获取开场白音频时长
-    getOpeningAudioDuration() {
-        // 估算开场白音频时长，可以根据实际情况调整
-        // 这里假设平均每个字符对应100ms的音频时长
-        if (this.openingAudioData) {
-            // 简单估算：假设开场白大约3-5秒
-            return 4000; // 4秒
-        }
-        return 3000; // 默认3秒
-    }
-
     async loadVideoMapping() {
         try {
             const response = await fetch('/api/video-mapping');
@@ -541,7 +432,6 @@ class WebRTCChat {
 
     // 预创建重要视频流
     async precreateImportantVideos() {
-
         if (this.isInitialized) return;
         
         console.log('开始预创建重要流...', 'info');
@@ -1262,9 +1152,6 @@ class WebRTCChat {
             // 切换到通话中图标
             this.switchToCallingIcon();
             
-            // 在初始化完成后生成开场白音频
-            await this.initializeOpeningAudio();
-            
             // 现在才开始显示视频
             await this.startDefaultVideoStream();
             
@@ -1277,54 +1164,35 @@ class WebRTCChat {
             console.log('麦克风权限获取成功');
             
             await this.createPeerConnection();
+            await this.startVoiceRecording();
             
             this.startButton.disabled = true;
-        this.startButton.style.opacity = '0.5'
+            this.startButton.style.opacity = '0.5'
-        this.stopButton.disabled = false;
+            this.stopButton.disabled = false;
 
-        // 隐藏头像，显示视频
+            // 隐藏头像，显示视频
-        if (this.videoContainer) {
+            if (this.videoContainer) {
 
-            this.videoContainer.classList.add('calling');
+                this.videoContainer.classList.add('calling');
-        }
+            }
             
-        // 显示结束通话按钮
+            // 显示结束通话按钮
-        this.stopButton.style.display = 'block';
+            this.stopButton.style.display = 'block';
             
             
             
-        this.updateAudioStatus('已连接', 'connected');
+            this.updateAudioStatus('已连接', 'connected');
-        this.logMessage('音频通话已开始', 'success');
+            this.logMessage('音频通话已开始', 'success');
             
-        // 确保视频映射已加载
+            // 确保视频映射已加载
-        if (Object.keys(this.videoMapping).length === 0) {
+            if (Object.keys(this.videoMapping).length === 0) {
-            await this.loadVideoMapping();
+                await this.loadVideoMapping();
-        }
+            }
             
-        this.logMessage(`视频映射已加载: ${Object.keys(this.videoMapping).length} 个映射`, 'info');
+            this.logMessage(`视频映射已加载: ${Object.keys(this.videoMapping).length} 个映射`, 'info');
             
-        // 通知服务器通话开始
+            // 通知服务器通话开始
-        this.socket.emit('call-started');
+            this.socket.emit('call-started');
-        
-        // 播放开场白，然后启动语音录制
-        if (this.isOpeningAudioReady) {
-            console.log('播放开场白音频...');
-            await this.playOpeningAudio();
-            
-            // 等待开场白播放完成后再启动语音录制
-            setTimeout(async () => {
-                console.log('开场白播放完成，启动语音录制...');
-                await this.startVoiceRecording();
-                this.logMessage('语音录制已启动，可以开始对话', 'success');
-            }, this.getOpeningAudioDuration() + 1000); // 开场白时长 + 1秒缓冲
-        } else {
-            console.warn('开场白音频尚未准备就绪，延迟启动语音录制');
-            // 如果没有开场白，延迟500ms后启动录制
-            setTimeout(async () => {
-                await this.startVoiceRecording();
-                this.logMessage('语音录制已启动，可以开始对话', 'success');
-            }, 500);
-        }
             
             // 开始播放当前场景的默认视频
             // await this.precreateImportantVideos();

src/llm_stream.js

@@ -1,35 +1,5 @@
 // 以流式方式请求LLM大模型接口，并打印流式返回内容
 
-// 过滤旁白内容的函数
-function filterNarration(text) {
-  if (!text) return text;
-  
-  // 匹配各种括号内的旁白内容
-  // 包括：（）、【】、[]、{}、〈〉、《》等
-  const narrationPatterns = [
-    /（[^）]*）/g,  // 中文圆括号
-    /\([^)]*\)/g,   // 英文圆括号
-    /【[^】]*】/g,   // 中文方括号
-    /\[[^\]]*\]/g,  // 英文方括号
-    /\{[^}]*\}/g,   // 花括号
-    /〈[^〉]*〉/g,   // 中文尖括号
-    /《[^》]*》/g,   // 中文书名号
-    /<[^>]*>/g     // 英文尖括号
-  ];
-  
-  let filteredText = text;
-  
-  // 逐个应用过滤规则
-  narrationPatterns.forEach(pattern => {
-    filteredText = filteredText.replace(pattern, '');
-  });
-  
-  // 清理多余的空格和换行
-  filteredText = filteredText.replace(/\s+/g, ' ').trim();
-  
-  return filteredText;
-}
-
 async function requestLLMStream({ apiKey, model, messages, onSegment }) {
   const response = await fetch('https://ark.cn-beijing.volces.com/api/v3/bots/chat/completions', {
     method: 'POST',
@@ -84,14 +54,7 @@ async function requestLLMStream({ apiKey, model, messages, onSegment }) {
             // 处理最后的待处理文本（无论长度是否大于5个字）
             if (pendingText.trim() && onSegment) {
               console.log('处理最后的待处理文本:', pendingText.trim());
-              // 过滤旁白内容
+              await onSegment(pendingText.trim(), true);
-              const filteredText = filterNarration(pendingText.trim());
-              if (filteredText.trim()) {
-                console.log('过滤旁白后的最后文本:', filteredText);
-                await onSegment(filteredText, true);
-              } else {
-                console.log('最后的文本被完全过滤，跳过');
-              }
             }
             continue;
           }
@@ -102,15 +65,12 @@ async function requestLLMStream({ apiKey, model, messages, onSegment }) {
               const deltaContent = obj.choices[0].delta.content;
               content += deltaContent;
               pendingText += deltaContent;
-              console.log('【未过滤】LLM内容片段:', pendingText);
+              console.log('LLM内容片段:', deltaContent);
               
-              // 先过滤旁白，再检查分段分隔符
+              // 检查是否包含分段分隔符
-              const filteredPendingText = filterNarration(pendingText);
+              if (segmentDelimiters.test(pendingText)) {
-              
+                // 按分隔符分割文本
-              // 检查过滤后的文本是否包含分段分隔符
+                const segments = pendingText.split(segmentDelimiters);
-              if (segmentDelimiters.test(filteredPendingText)) {
-                // 按分隔符分割已过滤的文本
-                const segments = filteredPendingText.split(segmentDelimiters);
                 
                 // 重新组合处理：只处理足够长的完整段落
                 let accumulatedText = '';
@@ -121,30 +81,25 @@ async function requestLLMStream({ apiKey, model, messages, onSegment }) {
                   if (segment) {
                     accumulatedText += segment;
                     // 找到分隔符
-                    const delimiterMatch = filteredPendingText.match(segmentDelimiters);
+                    const delimiterMatch = pendingText.match(segmentDelimiters);
                     if (delimiterMatch) {
                       accumulatedText += delimiterMatch[0];
                     }
                     
                     // 如果累积文本长度大于5个字，处理它
                     if (accumulatedText.length > 8 && onSegment) {
-                      console.log('【已过滤】检测到完整段落:', accumulatedText);
+                      console.log('检测到完整段落:', accumulatedText);
-                      // 文本已经过滤过旁白，直接使用
+                      await onSegment(accumulatedText, false);
-                      if (accumulatedText.trim()) {
-                        console.log('处理过滤后的文本:', accumulatedText);
-                        await onSegment(accumulatedText, false);
-                      }
                       hasProcessed = true;
                       accumulatedText = ''; // 重置
                     }
                   }
                 }
                 
-                // 更新pendingText - 使用原始文本但需要相应调整
+                // 更新pendingText
                 if (hasProcessed) {
-                  // 计算已处理的原始文本长度，更新pendingText
+                  // 保留未处理的累积文本和最后一个不完整段落
-                  const processedLength = pendingText.length - (segments[segments.length - 1] || '').length;
+                  pendingText = accumulatedText + (segments[segments.length - 1] || '');
-                  pendingText = pendingText.substring(processedLength);
                 }
               }
             }

src/minimaxi_stream.js

@@ -431,4 +431,4 @@ function generateUUID() {
   });
 }
 
-export { requestMinimaxi, requestVolcanTTS, addAudioToQueue };
+export { requestMinimaxi, requestVolcanTTS };

src/new_app.js

@@ -0,0 +1,346 @@
+let ASRTEXT = ''
+
+class HttpASRRecognizer {
+    constructor() {
+        this.mediaRecorder = null;
+        this.audioContext = null;
+        this.isRecording = false;
+        this.audioChunks = [];
+        
+        // VAD相关属性
+        this.isSpeaking = false;
+        this.silenceThreshold = 0.01;
+        this.silenceTimeout = 1000;
+        this.minSpeechDuration = 300;
+        this.silenceTimer = null;
+        this.speechStartTime = null;
+        this.audioBuffer = [];
+        
+        // API配置
+        this.apiConfig = {
+            url: 'https://openspeech.bytedance.com/api/v3/auc/bigmodel/recognize/flash',
+            headers: {
+                'X-Api-App-Key': '1988591469',
+                'X-Api-Access-Key': 'mdEyhgZ59on1-NK3GXWAp3L4iLldSG0r',
+                'X-Api-Resource-Id': 'volc.bigasr.auc_turbo',
+                'X-Api-Request-Id': this.generateUUID(),
+                'X-Api-Sequence': '-1',
+                'Content-Type': 'application/json'
+            }
+        };
+        
+        this.recordBtn = document.getElementById('startVoiceButton');
+        this.statusDiv = document.getElementById('status');
+        this.resultsDiv = document.getElementById('results');
+        
+        this.initEventListeners();
+    }
+    
+    initEventListeners() {
+        this.recordBtn.addEventListener('click', () => {
+            if (this.isRecording) {
+                this.stopRecording();
+            } else {
+                this.startRecording();
+            }
+        });
+    }
+    
+    // 生成UUID
+    generateUUID() {
+        return 'xxxxxxxx-xxxx-4xxx-yxxx-xxxxxxxxxxxx'.replace(/[xy]/g, function(c) {
+            const r = Math.random() * 16 | 0;
+            const v = c == 'x' ? r : (r & 0x3 | 0x8);
+            return v.toString(16);
+        });
+    }
+    
+    // 计算音频能量(音量)
+    calculateAudioLevel(audioData) {
+        let sum = 0;
+        for (let i = 0; i < audioData.length; i++) {
+            sum += audioData[i] * audioData[i];
+        }
+        return Math.sqrt(sum / audioData.length);
+    }
+    
+    // 语音活动检测
+    detectVoiceActivity(audioData) {
+        const audioLevel = this.calculateAudioLevel(audioData);
+        const currentTime = Date.now();
+        
+        if (audioLevel > this.silenceThreshold) {
+            if (!this.isSpeaking) {
+                this.isSpeaking = true;
+                this.speechStartTime = currentTime;
+                this.audioBuffer = [];
+                this.updateStatus('检测到语音，开始录音...', 'speaking');
+                console.log('开始说话');
+            }
+            
+            if (this.silenceTimer) {
+                clearTimeout(this.silenceTimer);
+                this.silenceTimer = null;
+            }
+            
+            return true;
+        } else {
+            if (this.isSpeaking && !this.silenceTimer) {
+                this.silenceTimer = setTimeout(() => {
+                    this.onSpeechEnd();
+                }, this.silenceTimeout);
+            }
+            
+            return this.isSpeaking;
+        }
+    }
+    
+    // 语音结束处理
+    async onSpeechEnd() {
+        if (this.isSpeaking) {
+            const speechDuration = Date.now() - this.speechStartTime;
+            
+            if (speechDuration >= this.minSpeechDuration) {
+                console.log(`语音结束，时长: ${speechDuration}ms`);
+                await this.processAudioBuffer();
+                // this.updateStatus('语音识别中...', 'processing');
+                console.log('语音识别中')
+            } else {
+                console.log('说话时长太短，忽略');
+                // this.updateStatus('等待语音输入...', 'ready');
+                console.log('等待语音输入...')
+
+            }
+            
+            this.isSpeaking = false;
+            this.speechStartTime = null;
+            this.audioBuffer = [];
+        }
+        
+        if (this.silenceTimer) {
+            clearTimeout(this.silenceTimer);
+            this.silenceTimer = null;
+        }
+    }
+    
+    // 处理音频缓冲区并发送到API
+    async processAudioBuffer() {
+        if (this.audioBuffer.length === 0) {
+            return;
+        }
+        
+        try {
+            // 合并所有音频数据
+            const totalLength = this.audioBuffer.reduce((sum, buffer) => sum + buffer.length, 0);
+            const combinedBuffer = new Float32Array(totalLength);
+            let offset = 0;
+            
+            for (const buffer of this.audioBuffer) {
+                combinedBuffer.set(buffer, offset);
+                offset += buffer.length;
+            }
+            
+            // 转换为WAV格式并编码为base64
+            const wavBuffer = this.encodeWAV(combinedBuffer, 16000);
+            const base64Audio = this.arrayBufferToBase64(wavBuffer);
+            
+            // 调用ASR API
+            await this.callASRAPI(base64Audio);
+            
+        } catch (error) {
+            console.error('处理音频数据失败:', error);
+            this.updateStatus('识别失败', 'error');
+        }
+    }
+    
+    // 调用ASR API
+    async callASRAPI(base64AudioData) {
+        try {
+            const requestBody = {
+                user: {
+                    uid: "1988591469"
+                },
+                audio: {
+                    data: base64AudioData
+                },
+                request: {
+                    model_name: "bigmodel"
+                }
+            };
+            
+            const response = await fetch(this.apiConfig.url, {
+                method: 'POST',
+                headers: this.apiConfig.headers,
+                body: JSON.stringify(requestBody)
+            });
+            
+            if (!response.ok) {
+                throw new Error(`HTTP error! status: ${response.status}`);
+            }
+            
+            const result = await response.json();
+            this.handleASRResponse(result);
+            
+        } catch (error) {
+            console.error('ASR API调用失败:', error);
+            this.updateStatus('API调用失败', 'error');
+        }
+    }
+    
+    // 处理ASR响应
+    handleASRResponse(response) {
+        console.log('ASR响应:', response);
+        
+        if (response && response.data && response.data.result) {
+            ASRTEXT = response.data.result;
+            // this.displayResult(text);
+            // this.updateStatus('识别完成', 'completed');
+            console.log('识别完成')
+        } else {
+            console.log('未识别到文字');
+            // this.updateStatus('未识别到文字', 'ready');
+
+        }
+    }
+    
+    // 显示识别结果
+    displayResult(text) {
+        const resultElement = document.createElement('div');
+        resultElement.className = 'result-item';
+        resultElement.innerHTML = `
+            <span class="timestamp">${new Date().toLocaleTimeString()}</span>
+            <span class="text">${text}</span>
+        `;
+        this.resultsDiv.appendChild(resultElement);
+        this.resultsDiv.scrollTop = this.resultsDiv.scrollHeight;
+    }
+    
+    // 更新状态显示
+    updateStatus(message, status) {
+        this.statusDiv.textContent = message;
+        this.statusDiv.className = `status ${status}`;
+    }
+    
+    // 编码WAV格式
+    encodeWAV(samples, sampleRate) {
+        const length = samples.length;
+        const buffer = new ArrayBuffer(44 + length * 2);
+        const view = new DataView(buffer);
+        
+        // WAV文件头
+        const writeString = (offset, string) => {
+            for (let i = 0; i < string.length; i++) {
+                view.setUint8(offset + i, string.charCodeAt(i));
+            }
+        };
+        
+        writeString(0, 'RIFF');
+        view.setUint32(4, 36 + length * 2, true);
+        writeString(8, 'WAVE');
+        writeString(12, 'fmt ');
+        view.setUint32(16, 16, true);
+        view.setUint16(20, 1, true);
+        view.setUint16(22, 1, true);
+        view.setUint32(24, sampleRate, true);
+        view.setUint32(28, sampleRate * 2, true);
+        view.setUint16(32, 2, true);
+        view.setUint16(34, 16, true);
+        writeString(36, 'data');
+        view.setUint32(40, length * 2, true);
+        
+        // 写入音频数据
+        let offset = 44;
+        for (let i = 0; i < length; i++) {
+            const sample = Math.max(-1, Math.min(1, samples[i]));
+            view.setInt16(offset, sample * 0x7FFF, true);
+            offset += 2;
+        }
+        
+        return buffer;
+    }
+    
+    // ArrayBuffer转Base64
+    arrayBufferToBase64(buffer) {
+        let binary = '';
+        const bytes = new Uint8Array(buffer);
+        for (let i = 0; i < bytes.byteLength; i++) {
+            binary += String.fromCharCode(bytes[i]);
+        }
+        return btoa(binary);
+    }
+    
+    async startRecording() {
+        try {
+            const stream = await navigator.mediaDevices.getUserMedia({
+                audio: {
+                    sampleRate: 16000,
+                    channelCount: 1,
+                    echoCancellation: true,
+                    noiseSuppression: true
+                }
+            });
+            
+            this.audioContext = new (window.AudioContext || window.webkitAudioContext)({
+                sampleRate: 16000
+            });
+            
+            const source = this.audioContext.createMediaStreamSource(stream);
+            const processor = this.audioContext.createScriptProcessor(4096, 1, 1);
+            
+            processor.onaudioprocess = (event) => {
+                const inputBuffer = event.inputBuffer;
+                const inputData = inputBuffer.getChannelData(0);
+                
+                // 语音活动检测
+                if (this.detectVoiceActivity(inputData)) {
+                    // 如果检测到语音活动，缓存音频数据
+                    this.audioBuffer.push(new Float32Array(inputData));
+                }
+            };
+            
+            source.connect(processor);
+            processor.connect(this.audioContext.destination);
+            
+            this.isRecording = true;
+            this.recordBtn.textContent = '停止录音';
+            this.recordBtn.className = 'btn recording';
+            // this.updateStatus('等待语音输入...', 'ready');
+            
+        } catch (error) {
+            console.error('启动录音失败:', error);
+            // this.updateStatus('录音启动失败', 'error');
+        }
+    }
+    
+    stopRecording() {
+        if (this.audioContext) {
+            this.audioContext.close();
+            this.audioContext = null;
+        }
+        
+        if (this.silenceTimer) {
+            clearTimeout(this.silenceTimer);
+            this.silenceTimer = null;
+        }
+        
+        // 如果正在说话，处理最后的音频
+        if (this.isSpeaking) {
+            this.onSpeechEnd();
+        }
+        
+        this.isRecording = false;
+        this.isSpeaking = false;
+        this.audioBuffer = [];
+        
+        this.recordBtn.textContent = '开始录音';
+        this.recordBtn.className = 'btn';
+        console.log('录音已停止');
+        // this.updateStatus('录音已停止', 'stopped');
+    }
+}
+
+// 初始化应用
+document.addEventListener('DOMContentLoaded', () => {
+    const asrRecognizer = new HttpASRRecognizer();
+    console.log('HTTP ASR识别器已初始化');
+});

src/video_audio_sync.js

@@ -0,0 +1,44 @@
+import { requestMinimaxi } from './minimaxi_stream.js';
+import { getMinimaxiConfig } from './config.js';
+
+export async function playVideoWithAudio(videoPath, text) {
+  // 1. 初始化视频播放
+  const video = document.createElement('video');
+  video.src = videoPath;
+  document.body.appendChild(video);
+  
+  // 2. 启动音频合成流
+  const minimaxiConfig = getMinimaxiConfig();
+  const audioStream = await requestMinimaxi({
+    apiKey: minimaxiConfig.apiKey,
+    groupId: minimaxiConfig.groupId,
+    body: {
+      model: 'speech-01-turbo',
+      text,
+      output_format: 'hex', // 流式场景必须使用hex
+      voice_setting: {
+        voice_id: 'tianbing_xinggan_03',
+        speed: 1
+      }
+    },
+    stream: true
+  });
+
+  // 3. 将音频hex转换为可播放格式
+  const audioCtx = new AudioContext();
+  const audioBuffer = await audioCtx.decodeAudioData(
+    hexToArrayBuffer(audioStream.data.audio)
+  );
+  
+  // 4. 同步播放
+  const source = audioCtx.createBufferSource();
+  source.buffer = audioBuffer;
+  source.connect(audioCtx.destination);
+  
+  video.play();
+  source.start(0);
+}
+
+function hexToArrayBuffer(hex) {
+  // ... hex转ArrayBuffer实现
+}

src/video_queue_test.js

@@ -0,0 +1,89 @@
+// 视频播放队列系统测试
+// 这个文件用于测试新的视频播放逻辑
+
+export class VideoQueueTester {
+    constructor(webrtcApp) {
+        this.webrtcApp = webrtcApp;
+    }
+    
+    // 测试视频队列功能
+    async testVideoQueue() {
+        console.log('开始测试视频播放队列系统...');
+        
+        // 测试1: 添加视频到队列
+        await this.testAddToQueue();
+        
+        // 测试2: 测试视频播放完成等待
+        await this.testWaitForVideoFinish();
+        
+        // 测试3: 测试音频视频同步
+        await this.testAudioVideoSync();
+        
+        console.log('视频播放队列系统测试完成');
+    }
+    
+    // 测试添加视频到队列
+    async testAddToQueue() {
+        console.log('测试1: 添加视频到队列');
+        
+        // 清空队列
+        this.webrtcApp.videoQueue = [];
+        
+        // 添加测试视频
+        await this.webrtcApp.addToVideoQueue('5.mp4', 'test', '测试视频1');
+        await this.webrtcApp.addToVideoQueue('s-1.mp4', 'test', '测试视频2');
+        
+        console.log(`队列长度: ${this.webrtcApp.videoQueue.length}`);
+        console.log('队列内容:', this.webrtcApp.videoQueue);
+    }
+    
+    // 测试等待视频播放完成
+    async testWaitForVideoFinish() {
+        console.log('测试2: 等待视频播放完成');
+        
+        // 模拟视频播放状态
+        this.webrtcApp.isVideoPlaying = true;
+        
+        // 模拟视频播放完成
+        setTimeout(() => {
+            this.webrtcApp.isVideoPlaying = false;
+            console.log('模拟视频播放完成');
+        }, 2000);
+        
+        console.log('等待视频播放完成...');
+        await this.webrtcApp.waitForCurrentVideoToFinish();
+        console.log('视频播放完成等待测试通过');
+    }
+    
+    // 测试音频视频同步
+    async testAudioVideoSync() {
+        console.log('测试3: 音频视频同步');
+        
+        // 模拟音频播放开始
+        window.isPlaying = true;
+        
+        // 添加视频到队列
+        await this.webrtcApp.addToVideoQueue('5.mp4', 'audio', '音频同步测试');
+        
+        // 模拟音频播放结束
+        setTimeout(() => {
+            window.isPlaying = false;
+            console.log('模拟音频播放结束');
+        }, 3000);
+        
+        console.log('音频视频同步测试完成');
+    }
+    
+    // 运行所有测试
+    async runAllTests() {
+        try {
+            await this.testVideoQueue();
+            console.log('所有测试通过！');
+        } catch (error) {
+            console.error('测试失败:', error);
+        }
+    }
+}
+
+// 导出测试类
+export default VideoQueueTester;