Merge branch 'py_test_error_response' into fix/2075

.github/workflows/build-base-image.yml

@@ -37,7 +37,7 @@ jobs:
           file: Dockerfile-server-base
           push: true
           tags: ghcr.io/${{ github.repository }}:server-base
-          platforms: linux/amd64
+          platforms: linux/amd64,linux/arm64
           cache-from: type=gha,scope=server-base
           cache-to: type=gha,mode=max,scope=server-base
           build-args: |

.github/workflows/docker-image.yml

@@ -66,7 +66,7 @@ jobs:
           push: true
           tags: |
             ${{ env.IS_VERSION == 'true' && format('ghcr.io/{0}:server_{1},ghcr.io/{0}:server_latest', github.repository, env.VERSION) || format('ghcr.io/{0}:server_latest', github.repository) }}
-          platforms: linux/amd64
+          platforms: linux/amd64,linux/arm64
           cache-from: type=gha
           cache-to: type=gha,mode=max
           build-args: |
@@ -81,7 +81,7 @@ jobs:
           push: true
           tags: |
             ${{ env.IS_VERSION == 'true' && format('ghcr.io/{0}:web_{1},ghcr.io/{0}:web_latest', github.repository, env.VERSION) || format('ghcr.io/{0}:web_latest', github.repository) }}
-          platforms: linux/amd64
+          platforms: linux/amd64,linux/arm64
           cache-from: type=gha
           cache-to: type=gha,mode=max
           build-args: |

Dockerfile-web

@@ -1,5 +1,5 @@
 # 第一阶段：构建Vue前端
-FROM node:18 as web-builder
+FROM node:18 AS web-builder
 WORKDIR /app
 COPY main/manager-web/package*.json ./
 RUN npm install
@@ -7,7 +7,7 @@ COPY main/manager-web .
 RUN npm run build
 
 # 第二阶段：构建Java后端
-FROM maven:3.9.4-eclipse-temurin-21 as api-builder
+FROM maven:3.9.4-eclipse-temurin-21 AS api-builder
 WORKDIR /app
 COPY main/manager-api/pom.xml .
 COPY main/manager-api/src ./src
@@ -18,18 +18,19 @@ FROM bellsoft/liberica-runtime-container:jre-21-glibc
 
 # 安装Nginx和字体库
 RUN apk update && \
-    apk add --no-cache --repository=http://dl-cdn.alpinelinux.org/alpine/edge/testing/ \
+    apk add --no-cache --no-scripts \
         nginx \
         bash \
         fontconfig \
         ttf-dejavu \
-        msttcorefonts-installer \
+    && rm -rf /var/cache/apk/* \
-    && ACCEPT_EULA=Y apk add --no-cache msttcorefonts-installer \
+    && mkdir -p /run/nginx /var/log/nginx /var/tmp/nginx /etc/nginx/conf.d
-    && fc-cache -f -v \
+
-    && rm -rf /var/cache/apk/*
+# 复制项目自带的中文字体
+COPY main/manager-web/public/generator/static/fonts/*.ttf /usr/share/fonts/
 
 # 更新字体缓存
-RUN (printf 'YES\n' | update-ms-fonts || true) && fc-cache -f -v
+RUN fc-cache -f -v
 
 # 配置Nginx
 COPY docs/docker/nginx.conf /etc/nginx/nginx.conf

main/manager-api/src/main/java/xiaozhi/common/constant/Constant.java

@@ -304,7 +304,7 @@ public interface Constant {
     /**
      * 版本号
      */
-    public static final String VERSION = "0.8.11";
+    public static final String VERSION = "0.9.1";
 
     /**
      * 无效固件URL

main/manager-api/src/main/java/xiaozhi/modules/agent/service/impl/AgentServiceImpl.java

@@ -1,6 +1,12 @@
 package xiaozhi.modules.agent.service.impl;
 
-import java.util.*;
+import java.util.ArrayList;
+import java.util.Date;
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+import java.util.Optional;
+import java.util.UUID;
 import java.util.function.Function;
 import java.util.stream.Collectors;
 
@@ -81,9 +87,9 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
 
         if (agent.getMemModelId() != null && agent.getMemModelId().equals(Constant.MEMORY_NO_MEM)) {
             agent.setChatHistoryConf(Constant.ChatHistoryConfEnum.IGNORE.getCode());
-            if (agent.getChatHistoryConf() == null) {
+        }
-                agent.setChatHistoryConf(Constant.ChatHistoryConfEnum.RECORD_TEXT_AUDIO.getCode());
+        if (agent.getChatHistoryConf() == null) {
-            }
+            agent.setChatHistoryConf(Constant.ChatHistoryConfEnum.RECORD_TEXT_AUDIO.getCode());
         }
 
         // 查询上下文源配置
@@ -132,7 +138,8 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
         if (StringUtils.isNotBlank(keyword)) {
             if ("mac".equals(searchType)) {
                 // 按MAC地址搜索：先搜索设备，再获取对应的智能体
-                List<DeviceEntity> devices = Optional.ofNullable(deviceService.searchDevicesByMacAddress(keyword, userId)).orElseGet(ArrayList::new);
+                List<DeviceEntity> devices = Optional
+                        .ofNullable(deviceService.searchDevicesByMacAddress(keyword, userId)).orElseGet(ArrayList::new);
                 // 获取设备对应的智能体ID列表
                 List<String> agentIds = devices.stream()
                         .map(DeviceEntity::getAgentId)

main/manager-api/src/main/resources/db/changelog/202601141645.sql

@@ -0,0 +1,31 @@
+-- 批量清理 ai_model_provider 中的 sample_rate 字段定义
+UPDATE `ai_model_provider` ap
+JOIN (
+    SELECT 
+        id,
+        JSON_ARRAYAGG(
+            JSON_OBJECT('key', jt.k, 'label', jt.l, 'type', jt.t)
+        ) AS new_fields
+    FROM `ai_model_provider`,
+         JSON_TABLE(`fields`, '$[*]' COLUMNS (
+             k VARCHAR(50) PATH '$.key',
+             l VARCHAR(100) PATH '$.label',
+             t VARCHAR(20) PATH '$.type'
+         )) AS jt
+    WHERE `model_type` = 'TTS' 
+      AND jt.k != 'sample_rate'
+    GROUP BY id
+) filtered ON ap.id = filtered.id
+SET ap.fields = filtered.new_fields;
+
+-- 清理 config_json 顶层的 sample_rate
+UPDATE `ai_model_config`
+SET `config_json` = JSON_REMOVE(`config_json`, '$.sample_rate')
+WHERE `model_type` = 'TTS'
+  AND JSON_EXTRACT(`config_json`, '$.sample_rate') IS NOT NULL;
+
+-- 清理Minimax流式TTS的sample_rate参数（位于audio_setting内部）
+UPDATE `ai_model_config` SET 
+`config_json` = JSON_SET(`config_json`, '$.audio_setting', JSON_REMOVE(JSON_EXTRACT(`config_json`, '$.audio_setting'), '$.sample_rate'))
+WHERE `id` = 'TTS_MinimaxStreamTTS'
+AND JSON_EXTRACT(`config_json`, '$.audio_setting.sample_rate') IS NOT NULL;

main/manager-api/src/main/resources/db/changelog/202601231530.sql

@@ -0,0 +1,87 @@
+-- 更新HuoshanDoubleStreamTTS供应器配置，将分散的参数改为JSON字典配置
+-- 将 speech_rate, loudness_rate, pitch, emotion, emotion_scale 等参数整合为 audio_params, additions, mix_speaker 三个JSON字典
+
+UPDATE `ai_model_provider`
+SET `fields` = '[
+  {"key": "ws_url", "type": "string", "label": "WebSocket地址"},
+  {"key": "appid", "type": "string", "label": "应用ID"},
+  {"key": "access_token", "type": "string", "label": "访问令牌"},
+  {"key": "resource_id", "type": "string", "label": "资源ID"},
+  {"key": "speaker", "type": "string", "label": "默认音色"},
+  {"key": "enable_ws_reuse", "type": "boolean", "label": "是否开启链接复用", "default": true},
+  {"key": "audio_params", "type": "dict", "label": "音频输出配置"},
+  {"key": "additions", "type": "dict", "label": "高级文本处理配置"},
+  {"key": "mix_speaker", "type": "dict", "label": "混音控制配置"}
+]'
+WHERE `id` = 'SYSTEM_TTS_HSDSTTS';
+
+-- 更新现有配置，将旧的分散参数迁移到新的JSON字典结构
+UPDATE `ai_model_config`
+SET `config_json` = JSON_SET(
+    `config_json`,
+    '$.audio_params', JSON_OBJECT(
+        'speech_rate', CAST(COALESCE(NULLIF(JSON_UNQUOTE(JSON_EXTRACT(`config_json`, '$.speech_rate')), ''), '0') AS SIGNED),
+        'loudness_rate', CAST(COALESCE(NULLIF(JSON_UNQUOTE(JSON_EXTRACT(`config_json`, '$.loudness_rate')), ''), '0') AS SIGNED)
+    ),
+    '$.additions', JSON_OBJECT(
+        'aigc_metadata', JSON_OBJECT(),
+        'cache_config', JSON_OBJECT(),
+        'post_process', JSON_OBJECT(
+            'pitch', CAST(COALESCE(NULLIF(JSON_UNQUOTE(JSON_EXTRACT(`config_json`, '$.pitch')), ''), '0') AS SIGNED)
+        )
+    ),
+    '$.mix_speaker', JSON_OBJECT()
+)
+WHERE `id` = 'TTS_HuoshanDoubleStreamTTS';
+
+-- 删除旧的分散参数字段
+UPDATE `ai_model_config`
+SET `config_json` = JSON_REMOVE(
+    `config_json`,
+    '$.speech_rate',
+    '$.loudness_rate',
+    '$.pitch',
+    '$.emotion',
+    '$.emotion_scale'
+)
+WHERE `id` = 'TTS_HuoshanDoubleStreamTTS';
+
+-- 更新文档链接和备注说明
+UPDATE `ai_model_config` SET
+`doc_link` = 'https://www.volcengine.com/docs/6561/1329505',
+`remark` = '火山引擎双向流式TTS配置说明：
+1. 访问 https://www.volcengine.com/ 注册并开通火山引擎账号
+2. 访问 https://console.volcengine.com/speech/service/10007 开通语音合成大模型，购买音色
+3. 在页面底部获取appid和access_token
+4. 资源ID固定为：volc.service_type.10029（大模型语音合成及混音）
+5. 链接复用：开启WebSocket连接复用，默认true减少链接损耗（注意：复用后设备处于聆听状态时空闲链接会占并发数）
+
+详细参数文档：https://www.volcengine.com/docs/6561/1329505
+【audio_params】音频输出配置 - 用户可自定义添加火山引擎支持的任何音频参数
+  - speech_rate: 语速(-50~100)，默认0
+  - loudness_rate: 音量(-50~100)，默认0
+  - emotion: 情感类型（仅部分音色支持），可选值：neutral、happy、sad、angry、fearful、disgusted、surprised
+  - emotion_scale: 情感强度(1~5)，默认4
+  示例：{"speech_rate": 10, "loudness_rate": 5, "emotion": "happy", "emotion_scale": 4}
+
+【additions】高级文本处理配置 - 用户可自定义添加火山引擎支持的任何高级参数
+  - post_process.pitch: 音高(-12~12)，默认0
+  - aigc_metadata: AIGC元数据配置
+  - cache_config: 缓存配置
+  示例：{"post_process": {"pitch": 2}, "aigc_metadata": {}, "cache_config": {}}
+
+【mix_speaker】混音控制配置 - 多音色混合（仅 TTS 1.0）
+  示例：
+    {"speakers": [
+      {"source_speaker": "zh_male_bvlazysheep","mix_factor": 0.3}, 
+      {"source_speaker": "BV120_streaming","mix_factor": 0.3}, 
+      {"source_speaker": "zh_male_ahu_conversation_wvae_bigtts","mix_factor": 0.4}
+    ]}
+
+注意：
+- 多情感音色参数（emotion、emotion_scale）仅部分音色支持
+- 相关音色列表：https://www.volcengine.com/docs/6561/1257544
+- 用户可根据火山引擎API文档自行添加更多参数
+- 混音功能主要适用于豆包语音合成模型1.0的音色，使用时需要将req_params.speaker设置为custom_mix_bigtts
+'
+WHERE `id` = 'TTS_HuoshanDoubleStreamTTS';

main/manager-api/src/main/resources/db/changelog/202601261730.sql

@@ -0,0 +1,14 @@
+-- 更新小智参数中的默认采样率从 16000 改为 24000
+UPDATE `sys_params`
+SET `param_value` = '{
+  "type": "hello",
+  "version": 1,
+  "transport": "websocket",
+  "audio_params": {
+    "format": "opus",
+    "sample_rate": 24000,
+    "channels": 1,
+    "frame_duration": 60
+  }
+}'
+WHERE `id` = 309 AND `param_code` = 'xiaozhi';

main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml

@@ -487,6 +487,27 @@ databaseChangeLog:
         - sqlFile:
             encoding: utf8
             path: classpath:db/changelog/202601051433.sql
+  - changeSet:
+      id: 202601141645
+      author: RanChen
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202601141645.sql
+  - changeSet:
+      id: 202601231530
+      author: RanChen
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202601231530.sql
+  - changeSet:
+      id: 202601261730
+      author: RanChen
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202601261730.sql
   - changeSet:
       id: 202601291552
       author: shengzhou1216

main/manager-mobile/src/pages/settings/index.vue

@@ -235,7 +235,7 @@ function showAbout() {
     title: t('settings.aboutApp', { appName: import.meta.env.VITE_APP_TITLE }),
     content: t('settings.aboutContent', {
       appName: import.meta.env.VITE_APP_TITLE,
-      version: '0.8.11'
+      version: '0.9.1'
     }),
     showCancel: false,
     confirmText: t('common.confirm'),

main/manager-web/public/generator/index.html

@@ -4,9 +4,10 @@
     <meta charset="UTF-8" />
     <link rel="icon" type="image/svg+xml" href="/vite.svg" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <link rel="icon" href="./favicon.ico">
     <title>Xiaozhi AI Customization</title>
-    <script type="module" crossorigin src="./assets/index-FKVSBRAB.js"></script>
+    <script type="module" crossorigin src="./assets/index-B8r0c7xg.js"></script>
-    <link rel="stylesheet" crossorigin href="./assets/index-NXxBVrod.css">
+    <link rel="stylesheet" crossorigin href="./assets/index-CrIJdTCK.css">
   </head>
   <body>
     <div id="app"></div>

main/manager-web/src/views/DeviceManagement.vue

@@ -64,7 +64,7 @@
                   <el-button size="mini" type="text" @click="handleUnbind(scope.row.device_id)">
                     {{ $t('device.unbind') }}
                   </el-button>
-                  <el-button v-if="isGenerate(scope.row)" size="mini" type="text" @click="handleGenertor">
+                  <el-button v-if="isGenerate(scope.row)" size="mini" type="text" @click="handleGenertor(scope.row)">
                     {{ $t('device.deviceThemeGeneration') }}
                   </el-button>
                 </template>
@@ -337,10 +337,10 @@ export default {
         });
       });
     },
-    handleGenertor() {
+    handleGenertor(row) {
       const pathname = window.location.pathname;
       const basePath = pathname.split('/').slice(0, -1).join('/');
-      const url = `${window.location.origin}${basePath}/generator/`;
+      const url = `${window.location.origin}${basePath}/generator/?deviceId=${row.device_id}`;
       sessionStorage.setItem('devicePath', window.location.href);
       window.location.href = url;
     },

main/xiaozhi-server/config.yaml

@@ -89,7 +89,8 @@ xiaozhi:
   transport: websocket
   audio_params:
     format: opus
-    sample_rate: 16000
+    # Opus支持的采样率范围为[8000, 12000, 16000, 24000, 48000]
+    sample_rate: 24000
     channels: 1
     frame_duration: 60
 
@@ -717,13 +718,31 @@ TTS:
     speaker: zh_female_wanwanxiaohe_moon_bigtts
     # 开启WebSocket连接复用，默认复用（注意：复用后设备处于聆听状态时空闲链接会占并发数）
     enable_ws_reuse: True
-    speech_rate: 0
+    # 相关参数文档：https://www.volcengine.com/docs/6561/1329505
-    loudness_rate: 0
+    # 音频输出配置（audio_params）- 用户可自定义添加火山引擎支持的任何音频参数
-    pitch: 0
+    audio_params:
-    # 多情感音色参数，注意：当前仅部分音色支持设置情感。
+      speech_rate: 0  # 语速(-50~100)
-    # 相关音色列表：https://www.volcengine.com/docs/6561/1257544
+      loudness_rate: 0  # 音量(-50~100)
-    emotion: "neutral"  # 情感类型，可选值为：neutral、happy、sad、angry、fearful、disgusted、surprised
+      # 多情感音色参数，注意：当前仅部分音色支持设置情感。
-    emotion_scale: 4  # 情感强度，可选值为：1~5，默认值为4
+      # 相关音色列表：https://www.volcengine.com/docs/6561/1257544
+      # emotion: "neutral"  # 情感类型（仅部分音色支持）：neutral、happy、sad、angry、fearful、disgusted、surprised
+      # emotion_scale: 4  # 情感强度(1~5)
+    # 高级文本处理配置（additions）- 用户可自定义添加火山引擎支持的任何高级参数
+    additions:
+      post_process:
+        pitch: 0  # 音高(-12~12)
+      # aigc_metadata: {}  # AIGC元数据配置
+      # cache_config: {}  # 缓存配置
+    # 混音控制配置（mix_speaker）- 多音色混合（仅 TTS 1.0）
+    # 混音功能主要适用于豆包语音合成模型1.0的音色，使用时需要将req_params.speaker设置为custom_mix_bigtts
+    # mix_speaker:
+    #   speakers:
+    #     - source_speaker: zh_male_bvlazysheep
+    #       mix_factor: 0.3
+    #     - source_speaker: BV120_streaming
+    #       mix_factor: 0.3
+    #     - source_speaker: zh_male_ahu_conversation_wvae_bigtts
+    #       mix_factor: 0.4
   CosyVoiceSiliconflow:
     type: siliconflow
     # 硅基流动TTS
@@ -840,7 +859,6 @@ TTS:
     #       - "处理/(chu3)(li3)"
     #       - "危险/dangerous"
     # audio_setting:
-    #     sample_rate: 24000
     #     bitrate: 128000
     #     format: "mp3"
     #     channel: 1
@@ -868,7 +886,6 @@ TTS:
 
     # 以下可不用设置，使用默认设置
     # format: wav
-    # sample_rate: 16000
     # volume: 50
     # speech_rate: 0
     # pitch_rate: 0
@@ -892,7 +909,6 @@ TTS:
     host: nls-gateway-cn-beijing.aliyuncs.com
     # 以下可不用设置，使用默认设置
     # format: pcm  # 音频格式：pcm、wav、mp3
-    # sample_rate: 16000  # 采样率：8000、16000、24000
     # volume: 50  # 音量：0-100
     # speech_rate: 0  # 语速：-500到500
     # pitch_rate: 0  # 语调：-500到500
@@ -1007,7 +1023,6 @@ TTS:
     protocol: websocket # protocol choices = ['websocket', 'http']
     url: ws://127.0.0.1:8092/paddlespeech/tts/streaming  # TTS 服务的 URL 地址，指向本地服务器 [websocket默认ws://127.0.0.1:8092/paddlespeech/tts/streaming，http默认http://127.0.0.1:8090/paddlespeech/tts]
     spk_id: 0  # 发音人 ID，0 通常表示默认的发音人
-    sample_rate: 24000  # 采样率 [websocket默认24000，http默认0 自动选择]
     speed: 1.0  # 语速，1.0 表示正常语速，>1 表示加快，<1 表示减慢
     volume: 1.0  # 音量，1.0 表示正常音量，>1 表示增大，<1 表示减小
     save_path:   # 保存路径
@@ -1031,7 +1046,6 @@ TTS:
     output_dir: tmp/
     # 以下可不用设置，使用默认设置
     # format: pcm  # 音频格式：pcm、wav、mp3、opus
-    # sample_rate: 24000  # 采样率：16000, 24000, 48000
     # volume: 50  # 音量：0-100
     # rate: 1  # 语速：0.5~2
     # pitch: 1  # 语调：0.5~2
@@ -1053,7 +1067,6 @@ TTS:
     # stop_split: 0  # 关闭服务端拆句 不关闭：0，关闭：1
     # remain: 0  # 是否保留原书面语的样子	保留:1, 不保留:0
     # format: raw  # 音频格式：raw(PCM), lame(MP3), speex, opus, opus-wb, opus-swb, speex-wb
-    # sample_rate: 24000  # 采样率：16000, 8000, 24000
     # volume: 50  # 音量：0-100
     # speed: 50  # 语速：0-100
     # pitch: 50  # 语调：0-100

main/xiaozhi-server/config/logger.py

@@ -5,7 +5,7 @@ from config.config_loader import load_config
 from config.settings import check_config_file
 from datetime import datetime
 
-SERVER_VERSION = "0.8.11"
+SERVER_VERSION = "0.9.1"
 _logger_initialized = False
 
 

main/xiaozhi-server/core/connection.py

@@ -87,6 +87,7 @@ class ConnectionHandler:
         self.max_output_size = 0
         self.chat_history_conf = 0
         self.audio_format = "opus"
+        self.sample_rate = 24000  # 默认采样率，从客户端 hello 消息中动态更新
 
         # 客户端状态相关
         self.client_abort = False
@@ -208,6 +209,10 @@ class ConnectionHandler:
             self.welcome_msg = self.config["xiaozhi"]
             self.welcome_msg["session_id"] = self.session_id
 
+            # 从配置中读取采样率
+            self.sample_rate = self.welcome_msg["audio_params"]["sample_rate"]
+            self.logger.bind(tag=TAG).info(f"配置输出音频采样率为: {self.sample_rate}")
+
             # 在后台初始化配置和组件（完全不阻塞主循环）
             asyncio.create_task(self._background_initialize())
 
@@ -1184,6 +1189,8 @@ class ConnectionHandler:
 
             if self.tts:
                 await self.tts.close()
+            if self.asr:
+                await self.asr.close()
 
             # 最后关闭线程池（避免阻塞）
             if self.executor:
@@ -1232,11 +1239,21 @@ class ConnectionHandler:
                 f"清理结束: TTS队列大小={self.tts.tts_text_queue.qsize()}, 音频队列大小={self.tts.tts_audio_queue.qsize()}"
             )
 
-    def reset_vad_states(self):
+    def reset_audio_states(self):
-        self.client_audio_buffer = bytearray()
+        """
+        重置所有音频相关状态(VAD + ASR)
+        """
+        # Reset VAD states
+        self.client_audio_buffer.clear()
         self.client_have_voice = False
         self.client_voice_stop = False
-        self.logger.bind(tag=TAG).debug("VAD states reset.")
+        self.client_voice_window.clear()
+        self.last_is_voice = False
+
+        # Clear ASR buffers
+        self.asr_audio.clear()
+
+        self.logger.bind(tag=TAG).debug("All audio states reset.")
 
     def chat_and_close(self, text):
         """Chat with the user and then close the connection"""

main/xiaozhi-server/core/handle/helloHandle.py

@@ -142,7 +142,8 @@ async def wakeupWordsResponse(conn):
         # 获取当前音色
         voice = getattr(conn.tts, "voice", "default")
 
-        wav_bytes = opus_datas_to_wav_bytes(tts_result, sample_rate=16000)
+        # 使用链接的sample_rate
+        wav_bytes = opus_datas_to_wav_bytes(tts_result, sample_rate=conn.sample_rate)
         file_path = wakeup_words_config.generate_file_path(voice)
         with open(file_path, "wb") as f:
             f.write(wav_bytes)

main/xiaozhi-server/core/handle/receiveAudioHandle.py

@@ -17,7 +17,6 @@ async def handleAudioMessage(conn, audio):
     if hasattr(conn, "just_woken_up") and conn.just_woken_up:
         have_voice = False
         # 设置一个短暂延迟后恢复VAD检测
-        conn.asr_audio.clear()
         if not hasattr(conn, "vad_resume_task") or conn.vad_resume_task.done():
             conn.vad_resume_task = asyncio.create_task(resume_vad_detection(conn))
         return

main/xiaozhi-server/core/handle/textHandler/listenMessageHandler.py

@@ -26,10 +26,9 @@ class ListenTextMessageHandler(TextMessageHandler):
                 f"客户端拾音模式：{conn.client_listen_mode}"
             )
         if msg_json["state"] == "start":
-            conn.client_have_voice = True
+            # 设备从播放模式切回录音模式,清除所有音频状态和缓冲区
-            conn.client_voice_stop = False
+            conn.reset_audio_states()
         elif msg_json["state"] == "stop":
-            conn.client_have_voice = True
             conn.client_voice_stop = True
             if conn.asr.interface_type == InterfaceType.STREAM:
                 # 流式模式下，发送结束请求
@@ -38,14 +37,13 @@ class ListenTextMessageHandler(TextMessageHandler):
                 # 非流式模式：直接触发ASR识别
                 if len(conn.asr_audio) > 0:
                     asr_audio_task = conn.asr_audio.copy()
-                    conn.asr_audio.clear()
+                    conn.reset_audio_states()
-                    conn.reset_vad_states()
 
                     if len(asr_audio_task) > 0:
                         await conn.asr.handle_voice_stop(conn, asr_audio_task)
         elif msg_json["state"] == "detect":
             conn.client_have_voice = False
-            conn.asr_audio.clear()
+            conn.reset_audio_states()
             if "text" in msg_json:
                 conn.last_activity_time = time.time() * 1000
                 original_text = msg_json["text"]  # 保留原始文本

main/xiaozhi-server/core/providers/asr/aliyun.py

@@ -213,36 +213,24 @@ class ASRProvider(ASRProviderBase):
             return None
 
     async def speech_to_text(
-        self, opus_data: List[bytes], session_id: str, audio_format="opus"
+        self, opus_data: List[bytes], session_id: str, audio_format="opus", artifacts=None
     ) -> Tuple[Optional[str], Optional[str]]:
         """将语音数据转换为文本"""
         if self._is_token_expired():
             logger.warning("Token已过期，正在自动刷新...")
             self._refresh_token()
 
-        file_path = None
         try:
-            # 解码Opus为PCM
+            if artifacts is None:
-            if audio_format == "pcm":
+                return "", None
-                pcm_data = opus_data
-            else:
-                pcm_data = self.decode_opus(opus_data)
-            combined_pcm_data = b"".join(pcm_data)
-
-            # 判断是否保存为WAV文件
-            if self.delete_audio_file:
-                pass
-            else:
-                file_path = self.save_audio_to_file(pcm_data, session_id)
-
             # 发送请求并获取文本
-            text = await self._send_request(combined_pcm_data)
+            text = await self._send_request(artifacts.pcm_bytes)
 
             if text:
-                return text, file_path
+                return text, artifacts.file_path
 
-            return "", file_path
+            return "", artifacts.file_path
 
         except Exception as e:
             logger.bind(tag=TAG).error(f"语音识别失败: {e}", exc_info=True)
-            return "", file_path
+            return "", None

main/xiaozhi-server/core/providers/asr/aliyun_stream.py

@@ -126,16 +126,8 @@ class ASRProvider(ASRProviderBase):
         await super().open_audio_channels(conn)
 
     async def receive_audio(self, conn, audio, audio_have_voice):
-        # 初始化音频缓存
+        # 先调用父类方法处理基础逻辑
-        if not hasattr(conn, 'asr_audio_for_voiceprint'):
+        await super().receive_audio(conn, audio, audio_have_voice)
-            conn.asr_audio_for_voiceprint = []
-        
-        # 存储音频数据
-        if audio:
-            conn.asr_audio_for_voiceprint.append(audio)
-        
-        conn.asr_audio.append(audio)
-        conn.asr_audio = conn.asr_audio[-10:]
 
         # 只在有声音且没有连接时建立连接（排除正在停止的情况）
         if audio_have_voice and not self.is_processing and not self.asr_ws:
@@ -204,6 +196,8 @@ class ASRProvider(ASRProviderBase):
         """转发识别结果"""
         try:
             while not conn.stop_event.is_set():
+                # 获取当前连接的音频数据
+                audio_data = conn.asr_audio
                 try:
                     response = await asyncio.wait_for(self.asr_ws.recv(), timeout=1.0)
                     result = json.loads(response)
@@ -257,19 +251,12 @@ class ASRProvider(ASRProviderBase):
 
                                 # 手动模式下，只有在收到stop信号后才触发处理（仅处理一次）
                                 if conn.client_voice_stop:
-                                    audio_data = getattr(conn, 'asr_audio_for_voiceprint', [])
+                                    logger.bind(tag=TAG).debug("收到最终识别结果，触发处理")
-                                    if len(audio_data) > 0:
+                                    await self.handle_voice_stop(conn, audio_data)
-                                        logger.bind(tag=TAG).debug("收到最终识别结果，触发处理")
-                                        await self.handle_voice_stop(conn, audio_data)
-                                        # 清理音频缓存
-                                        conn.asr_audio.clear()
-                                        conn.reset_vad_states()
                                     break
                             else:
                                 # 自动模式下直接覆盖
                                 self.text = text
-                                conn.reset_vad_states()
-                                audio_data = getattr(conn, 'asr_audio_for_voiceprint', [])
                                 await self.handle_voice_stop(conn, audio_data)
                                 break
 
@@ -289,11 +276,7 @@ class ASRProvider(ASRProviderBase):
         finally:
             # 清理连接的音频缓存
             await self._cleanup()
-            if conn:
+            conn.reset_audio_states()
-                if hasattr(conn, 'asr_audio_for_voiceprint'):
-                    conn.asr_audio_for_voiceprint = []
-                if hasattr(conn, 'asr_audio'):
-                    conn.asr_audio = []
 
     async def _send_stop_request(self):
         """发送停止识别请求（不关闭连接）"""
@@ -341,7 +324,7 @@ class ASRProvider(ASRProviderBase):
 
         logger.bind(tag=TAG).debug("ASR会话清理完成")
 
-    async def speech_to_text(self, opus_data, session_id, audio_format):
+    async def speech_to_text(self, opus_data, session_id, audio_format, artifacts=None):
         """获取识别结果"""
         result = self.text
         self.text = ""

main/xiaozhi-server/core/providers/asr/aliyunbl_stream.py

@@ -52,16 +52,8 @@ class ASRProvider(ASRProviderBase):
         await super().open_audio_channels(conn)
 
     async def receive_audio(self, conn, audio, audio_have_voice):
-        # 初始化音频缓存
+        # 先调用父类方法处理基础逻辑
-        if not hasattr(conn, 'asr_audio_for_voiceprint'):
+        await super().receive_audio(conn, audio, audio_have_voice)
-            conn.asr_audio_for_voiceprint = []
-
-        # 存储音频数据
-        if audio:
-            conn.asr_audio_for_voiceprint.append(audio)
-
-        conn.asr_audio.append(audio)
-        conn.asr_audio = conn.asr_audio[-10:]
 
         # 只在有声音且没有连接时建立连接
         if audio_have_voice and not self.is_processing and not self.asr_ws:
@@ -166,6 +158,8 @@ class ASRProvider(ASRProviderBase):
         """转发识别结果"""
         try:
             while not conn.stop_event.is_set():
+                # 获取当前连接的音频数据
+                audio_data = conn.asr_audio
                 try:
                     response = await asyncio.wait_for(self.asr_ws.recv(), timeout=1.0)
                     result = json.loads(response)
@@ -214,19 +208,12 @@ class ASRProvider(ASRProviderBase):
 
                                 # 手动模式下,只有在收到stop信号后才触发处理
                                 if conn.client_voice_stop:
-                                    audio_data = getattr(conn, 'asr_audio_for_voiceprint', [])
+                                    logger.bind(tag=TAG).debug("收到最终识别结果，触发处理")
-                                    if len(audio_data) > 0:
+                                    await self.handle_voice_stop(conn, audio_data)
-                                        logger.bind(tag=TAG).debug("收到最终识别结果，触发处理")
-                                        await self.handle_voice_stop(conn, audio_data)
-                                        # 清理音频缓存
-                                        conn.asr_audio.clear()
-                                        conn.reset_vad_states()
                                     break
                             else:
                                 # 自动模式下直接覆盖
                                 self.text = text
-                                conn.reset_vad_states()
-                                audio_data = getattr(conn, 'asr_audio_for_voiceprint', [])
                                 await self.handle_voice_stop(conn, audio_data)
                                 break
 
@@ -257,11 +244,7 @@ class ASRProvider(ASRProviderBase):
         finally:
             # 清理连接的音频缓存
             await self._cleanup()
-            if conn:
+            conn.reset_audio_states()
-                if hasattr(conn, 'asr_audio_for_voiceprint'):
-                    conn.asr_audio_for_voiceprint = []
-                if hasattr(conn, 'asr_audio'):
-                    conn.asr_audio = []
 
     async def _send_stop_request(self):
         """发送停止请求(用于手动模式停止录音)"""
@@ -325,7 +308,7 @@ class ASRProvider(ASRProviderBase):
 
         logger.bind(tag=TAG).debug("ASR会话清理完成")
 
-    async def speech_to_text(self, opus_data, session_id, audio_format):
+    async def speech_to_text(self, opus_data, session_id, audio_format, artifacts=None):
         """获取识别结果"""
         result = self.text
         self.text = ""

main/xiaozhi-server/core/providers/asr/baidu.py

@@ -30,37 +30,26 @@ class ASRProvider(ASRProviderBase):
         os.makedirs(self.output_dir, exist_ok=True)
 
     async def speech_to_text(
-        self, opus_data: List[bytes], session_id: str, audio_format="opus"
+        self, opus_data: List[bytes], session_id: str, audio_format="opus", artifacts=None
     ) -> Tuple[Optional[str], Optional[str]]:
         """将语音数据转换为文本"""
         if not opus_data:
             logger.bind(tag=TAG).warning("音频数据为空！")
             return None, None
 
-        file_path = None
         try:
             # 检查配置是否已设置
             if not self.app_id or not self.api_key or not self.secret_key:
                 logger.bind(tag=TAG).error("百度语音识别配置未设置，无法进行识别")
-                return None, file_path
+                return None, None
 
-            # 将Opus音频数据解码为PCM
+            if artifacts is None:
-            if audio_format == "pcm":
+                return "", None
-                pcm_data = opus_data
-            else:
-                pcm_data = self.decode_opus(opus_data)
-            combined_pcm_data = b"".join(pcm_data)
-
-            # 判断是否保存为WAV文件
-            if self.delete_audio_file:
-                pass
-            else:
-                self.save_audio_to_file(pcm_data, session_id)
 
             start_time = time.time()
             # 识别本地文件
             result = self.client.asr(
-                combined_pcm_data,
+                artifacts.pcm_bytes,
                 "pcm",
                 16000,
                 {
@@ -73,13 +62,13 @@ class ASRProvider(ASRProviderBase):
                     f"百度语音识别耗时: {time.time() - start_time:.3f}s | 结果: {result}"
                 )
                 result = result["result"][0]
-                return result, file_path
+                return result, artifacts.file_path
             else:
                 raise Exception(
                     f"百度语音识别失败，错误码: {result['err_no']}，错误信息: {result['err_msg']}"
                 )
-                return None, file_path
+                return None, artifacts.file_path
 
         except Exception as e:
             logger.bind(tag=TAG).error(f"处理音频时发生错误！{e}", exc_info=True)
-            return None, file_path
+            return None, None

main/xiaozhi-server/core/providers/asr/base.py

@@ -8,14 +8,18 @@ import queue
 import asyncio
 import traceback
 import threading
+import shutil
 import opuslib_next
+
 from abc import ABC, abstractmethod
 from config.logger import setup_logging
-from typing import Optional, Tuple, List
+from typing import Optional, Tuple, List, NamedTuple
+from core.providers.asr.dto.dto import InterfaceType
 from core.handle.receiveAudioHandle import startToChat
 from core.handle.reportHandle import enqueue_asr_report
 from core.utils.util import remove_punctuation_and_length
 from core.handle.receiveAudioHandle import handleAudioMessage
+import tempfile
 
 TAG = __name__
 logger = setup_logging()
@@ -57,18 +61,17 @@ class ASRProviderBase(ABC):
             conn.asr_audio.append(audio)
         else:
             # 自动/实时模式：使用VAD检测
-            have_voice = audio_have_voice
-
             conn.asr_audio.append(audio)
-            if not have_voice and not conn.client_have_voice:
+
+            # 如果没有语音，且之前也没有声音，缓存部分音频
+            if not audio_have_voice and not conn.client_have_voice:
                 conn.asr_audio = conn.asr_audio[-10:]
                 return
 
             # 自动模式下通过VAD检测到语音停止时触发识别
-            if conn.client_voice_stop:
+            if conn.asr.interface_type != InterfaceType.STREAM and conn.client_voice_stop:
                 asr_audio_task = conn.asr_audio.copy()
-                conn.asr_audio.clear()
+                conn.reset_audio_states()
-                conn.reset_vad_states()
 
                 if len(asr_audio_task) > 15:
                     await self.handle_voice_stop(conn, asr_audio_task)
@@ -93,10 +96,14 @@ class ASRProviderBase(ABC):
                 wav_data = self._pcm_to_wav(combined_pcm_data)
 
             # 定义ASR任务
-            asr_task = self.speech_to_text(asr_audio_task, conn.session_id, conn.audio_format)
+            asr_task = self.speech_to_text_wrapper(
+                asr_audio_task, conn.session_id, conn.audio_format
+            )
 
             if conn.voiceprint_provider and wav_data:
-                voiceprint_task = conn.voiceprint_provider.identify_speaker(wav_data, conn.session_id)
+                voiceprint_task = conn.voiceprint_provider.identify_speaker(
+                    wav_data, conn.session_id
+                )
                 # 并发等待两个结果
                 asr_result, voiceprint_result = await asyncio.gather(
                     asr_task, voiceprint_task, return_exceptions=True
@@ -159,20 +166,20 @@ class ASRProviderBase(ABC):
             if text_len > 0:
                 # 使用自定义模块进行上报
                 await startToChat(conn, enhanced_text)
-                enqueue_asr_report(conn, enhanced_text, asr_audio_task)
+                audio_snapshot = asr_audio_task.copy()
-                
+                enqueue_asr_report(conn, enhanced_text, audio_snapshot)
         except Exception as e:
             logger.bind(tag=TAG).error(f"处理语音停止失败: {e}")
             import traceback
+
             logger.bind(tag=TAG).debug(f"异常详情: {traceback.format_exc()}")
 
     def _build_enhanced_text(self, text: str, speaker_name: Optional[str]) -> str:
         """构建包含说话人信息的文本（仅用于纯文本ASR）"""
         if speaker_name and speaker_name.strip():
-            return json.dumps({
+            return json.dumps(
-                "speaker": speaker_name,
+                {"speaker": speaker_name, "content": text}, ensure_ascii=False
-                "content": text
+            )
-            }, ensure_ascii=False)
         else:
             return text
 
@@ -181,23 +188,23 @@ class ASRProviderBase(ABC):
         if len(pcm_data) == 0:
             logger.bind(tag=TAG).warning("PCM数据为空，无法转换WAV")
             return b""
-        
+
         # 确保数据长度是偶数（16位音频）
         if len(pcm_data) % 2 != 0:
             pcm_data = pcm_data[:-1]
-        
+
         # 创建WAV文件头
         wav_buffer = io.BytesIO()
         try:
-            with wave.open(wav_buffer, 'wb') as wav_file:
+            with wave.open(wav_buffer, "wb") as wav_file:
-                wav_file.setnchannels(1)      # 单声道
+                wav_file.setnchannels(1)  # 单声道
-                wav_file.setsampwidth(2)      # 16位
+                wav_file.setsampwidth(2)  # 16位
                 wav_file.setframerate(16000)  # 16kHz采样率
                 wav_file.writeframes(pcm_data)
-            
+
             wav_buffer.seek(0)
             wav_data = wav_buffer.read()
-            
+
             return wav_data
         except Exception as e:
             logger.bind(tag=TAG).error(f"WAV转换失败: {e}")
@@ -206,6 +213,44 @@ class ASRProviderBase(ABC):
     def stop_ws_connection(self):
         pass
 
+    async def close(self):
+        pass
+
+    class AudioArtifacts(NamedTuple):
+        pcm_frames: List[bytes]
+        """PCM音频帧列表"""
+        pcm_bytes: bytes
+        """合并后的PCM音频字节数据"""
+        file_path: Optional[str]
+        """WAV文件路径"""
+        temp_path: Optional[str]
+        """临时WAV文件路径"""
+
+    def get_current_artifacts(self) -> Optional["ASRProviderBase.AudioArtifacts"]:
+        return self._current_artifacts
+
+    def requires_file(self) -> bool:
+        """是否需要文件输入"""
+        return False
+
+    def prefers_temp_file(self) -> bool:
+        """是否优先使用临时文件"""
+        return False
+
+    def build_temp_file(self, pcm_bytes: bytes) -> Optional[str]:
+        try:
+            with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as temp_file:
+                temp_path = temp_file.name
+            with wave.open(temp_path, "wb") as wav_file:
+                wav_file.setnchannels(1)
+                wav_file.setsampwidth(2)
+                wav_file.setframerate(16000)
+                wav_file.writeframes(pcm_bytes)
+            return temp_path
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"临时音频文件生成失败: {e}")
+            return None
+
     def save_audio_to_file(self, pcm_data: List[bytes], session_id: str) -> str:
         """PCM数据保存为WAV文件"""
         module_name = __name__.split(".")[-1]
@@ -220,11 +265,80 @@ class ASRProviderBase(ABC):
 
         return file_path
 
-    @abstractmethod
+    async def speech_to_text_wrapper(
-    async def speech_to_text(
         self, opus_data: List[bytes], session_id: str, audio_format="opus"
     ) -> Tuple[Optional[str], Optional[str]]:
-        """将语音数据转换为文本"""
+        file_path = None
+        temp_path = None
+        try:
+            if audio_format == "pcm":
+                pcm_data = opus_data
+            else:
+                pcm_data = self.decode_opus(opus_data)
+            combined_pcm_data = b"".join(pcm_data)
+
+            free_space = shutil.disk_usage(self.output_dir).free
+            if free_space < len(combined_pcm_data) * 2:
+                raise OSError("磁盘空间不足")
+
+            if self.requires_file() and self.prefers_temp_file():
+                temp_path = self.build_temp_file(combined_pcm_data)
+
+            if (hasattr(self, "delete_audio_file") and not self.delete_audio_file) or (
+                self.requires_file() and not self.prefers_temp_file()
+            ):
+                file_path = self.save_audio_to_file(pcm_data, session_id)
+
+            if len(combined_pcm_data) == 0:
+                artifacts = None
+            else:
+                artifacts = ASRProviderBase.AudioArtifacts(
+                    pcm_frames=pcm_data,
+                    pcm_bytes=combined_pcm_data,
+                    file_path=file_path,
+                    temp_path=temp_path,
+                )
+
+            text, _ = await self.speech_to_text(
+                opus_data, session_id, audio_format, artifacts
+            )
+            return text, file_path
+        except OSError as e:
+            logger.bind(tag=TAG).error(f"文件操作错误: {e}")
+            return None, None
+        except Exception as e:
+            logger.bind(tag=TAG).error(f"语音识别失败: {e}")
+            return None, None
+        finally:
+            try:
+                if temp_path and os.path.exists(temp_path):
+                    os.unlink(temp_path)
+                if (
+                    hasattr(self, "delete_audio_file")
+                    and self.delete_audio_file
+                    and file_path
+                    and os.path.exists(file_path)
+                ):
+                    os.remove(file_path)
+            except Exception as e:
+                logger.bind(tag=TAG).error(f"文件清理失败: {e}")
+
+    @abstractmethod
+    async def speech_to_text(
+        self,
+        opus_data: List[bytes],
+        session_id: str,
+        audio_format="opus",
+        artifacts: Optional[AudioArtifacts] = None,
+    ) -> Tuple[Optional[str], Optional[str]]:
+        """将语音数据转换为文本
+
+        :param opus_data: 输入的Opus音频数据
+        :param session_id: 会话ID
+        :param audio_format: 音频格式，默认"opus"
+        :param artifacts: 音频工件，包含PCM数据、文件路径等
+        :return: 识别结果文本和文件路径（如果有）
+        """
         pass
 
     @staticmethod
@@ -235,23 +349,23 @@ class ASRProviderBase(ABC):
             decoder = opuslib_next.Decoder(16000, 1)
             pcm_data = []
             buffer_size = 960  # 每次处理960个采样点 (60ms at 16kHz)
-            
+
             for i, opus_packet in enumerate(opus_data):
                 try:
                     if not opus_packet or len(opus_packet) == 0:
                         continue
-                    
+
                     pcm_frame = decoder.decode(opus_packet, buffer_size)
                     if pcm_frame and len(pcm_frame) > 0:
                         pcm_data.append(pcm_frame)
-                        
+
                 except opuslib_next.OpusError as e:
                     logger.bind(tag=TAG).warning(f"Opus解码错误，跳过数据包 {i}: {e}")
                 except Exception as e:
                     logger.bind(tag=TAG).error(f"音频处理错误，数据包 {i}: {e}")
-            
+
             return pcm_data
-            
+
         except Exception as e:
             logger.bind(tag=TAG).error(f"音频解码过程发生错误: {e}")
             return []

main/xiaozhi-server/core/providers/asr/doubao.py

@@ -232,24 +232,13 @@ class ASRProvider(ASRProviderBase):
             yield data[offset:data_len], True
 
     async def speech_to_text(
-        self, opus_data: List[bytes], session_id: str, audio_format="opus"
+        self, opus_data: List[bytes], session_id: str, audio_format="opus", artifacts=None
     ) -> Tuple[Optional[str], Optional[str]]:
         """将语音数据转换为文本"""
 
-        file_path = None
         try:
-            # 合并所有opus数据包
+            if artifacts is None:
-            if audio_format == "pcm":
+                return "", None
-                pcm_data = opus_data
-            else:
-                pcm_data = self.decode_opus(opus_data)
-            combined_pcm_data = b"".join(pcm_data)
-
-            # 判断是否保存为WAV文件
-            if self.delete_audio_file:
-                pass
-            else:
-                file_path = self.save_audio_to_file(pcm_data, session_id)
 
             # 直接使用PCM数据
             # 计算分段大小 (单声道, 16bit, 16kHz采样率)
@@ -258,14 +247,14 @@ class ASRProvider(ASRProviderBase):
 
             # 语音识别
             start_time = time.time()
-            text = await self._send_request(combined_pcm_data, segment_size)
+            text = await self._send_request(artifacts.pcm_bytes, segment_size)
             if text:
                 logger.bind(tag=TAG).debug(
                     f"语音识别耗时: {time.time() - start_time:.3f}s | 结果: {text}"
                 )
-                return text, file_path
+                return text, artifacts.file_path
-            return "", file_path
+            return "", artifacts.file_path
 
         except Exception as e:
             logger.bind(tag=TAG).error(f"语音识别失败: {e}", exc_info=True)
-            return "", file_path
+            return "", None

main/xiaozhi-server/core/providers/asr/doubao_stream.py

@@ -60,17 +60,8 @@ class ASRProvider(ASRProviderBase):
         await super().open_audio_channels(conn)
 
     async def receive_audio(self, conn, audio, audio_have_voice):
-        conn.asr_audio.append(audio)
+        # 先调用父类方法处理基础逻辑
-        conn.asr_audio = conn.asr_audio[-10:]
+        await super().receive_audio(conn, audio, audio_have_voice)
-        # 存储音频数据
-        if not hasattr(conn, 'asr_audio_for_voiceprint'):
-            conn.asr_audio_for_voiceprint = []
-        conn.asr_audio_for_voiceprint.append(audio)
-
-        # 当没有音频数据时处理完整语音片段
-        if conn.client_listen_mode != "manual" and not audio and len(conn.asr_audio_for_voiceprint) > 0:
-            await self.handle_voice_stop(conn, conn.asr_audio_for_voiceprint)
-            conn.asr_audio_for_voiceprint = []
 
         # 如果本次有声音，且之前没有建立连接
         if audio_have_voice and self.asr_ws is None and not self.is_processing:
@@ -164,7 +155,7 @@ class ASRProvider(ASRProviderBase):
         try:
             while self.asr_ws and not conn.stop_event.is_set():
                 # 获取当前连接的音频数据
-                audio_data = getattr(conn, 'asr_audio_for_voiceprint', [])
+                audio_data = conn.asr_audio
                 try:
                     response = await self.asr_ws.recv()
                     result = self.parse_response(response)
@@ -189,7 +180,6 @@ class ASRProvider(ASRProviderBase):
                             ):
                                 logger.bind(tag=TAG).error(f"识别文本：空")
                                 self.text = ""
-                                conn.reset_vad_states()
                                 if len(audio_data) > 15:  # 确保有足够音频数据
                                     await self.handle_voice_stop(conn, audio_data)
                                 break
@@ -200,12 +190,9 @@ class ASRProvider(ASRProviderBase):
                                 if self.enable_multilingual:
                                     continue
 
-                                if conn.client_listen_mode == "manual" and conn.client_voice_stop and len(audio_data) > 0:
+                                if conn.client_listen_mode == "manual" and conn.client_voice_stop and len(audio_data) > 15:
                                     logger.bind(tag=TAG).debug("消息结束收到停止信号，触发处理")
                                     await self.handle_voice_stop(conn, audio_data)
-                                    # 清理音频缓存
-                                    conn.asr_audio.clear()
-                                    conn.reset_vad_states()
                                     break
 
                             for utterance in utterances:
@@ -226,14 +213,10 @@ class ASRProvider(ASRProviderBase):
                                         if conn.client_voice_stop and len(audio_data) > 0:
                                             logger.bind(tag=TAG).debug("消息中途收到停止信号，触发处理")
                                             await self.handle_voice_stop(conn, audio_data)
-                                            # 清理音频缓存
-                                            conn.asr_audio.clear()
-                                            conn.reset_vad_states()
                                         break
                                     else:
                                         # 自动模式下直接覆盖
                                         self.text = current_text
-                                        conn.reset_vad_states()
                                         if len(audio_data) > 15:  # 确保有足够音频数据
                                             await self.handle_voice_stop(conn, audio_data)
                                     break
@@ -262,11 +245,8 @@ class ASRProvider(ASRProviderBase):
                 await self.asr_ws.close()
                 self.asr_ws = None
             self.is_processing = False
-            if conn:
+            # 重置所有音频相关状态
-                if hasattr(conn, 'asr_audio_for_voiceprint'):
+            conn.reset_audio_states()
-                    conn.asr_audio_for_voiceprint = []
-                if hasattr(conn, 'asr_audio'):
-                    conn.asr_audio = []
 
     def stop_ws_connection(self):
         if self.asr_ws:
@@ -408,7 +388,7 @@ class ASRProvider(ASRProviderBase):
             logger.bind(tag=TAG).error(f"原始响应数据: {res.hex()}")
             raise
 
-    async def speech_to_text(self, opus_data, session_id, audio_format):
+    async def speech_to_text(self, opus_data, session_id, audio_format, artifacts=None):
         result = self.text
         self.text = ""  # 清空text
         return result, None
@@ -435,11 +415,3 @@ class ASRProvider(ASRProviderBase):
                 logger.bind(tag=TAG).debug("Doubao decoder resources released")
             except Exception as e:
                 logger.bind(tag=TAG).debug(f"释放Doubao decoder资源时出错: {e}")
-
-        # 清理所有连接的音频缓冲区
-        if hasattr(self, '_connections'):
-            for conn in self._connections.values():
-                if hasattr(conn, 'asr_audio_for_voiceprint'):
-                    conn.asr_audio_for_voiceprint = []
-                if hasattr(conn, 'asr_audio'):
-                    conn.asr_audio = []

main/xiaozhi-server/core/providers/asr/fun_local.py

@@ -64,39 +64,21 @@ class ASRProvider(ASRProviderBase):
             )
 
     async def speech_to_text(
-        self, opus_data: List[bytes], session_id: str, audio_format="opus"
+        self, opus_data: List[bytes], session_id: str, audio_format="opus", artifacts=None
     ) -> Tuple[Optional[str], Optional[str]]:
         """语音转文本主处理逻辑"""
-        file_path = None
         retry_count = 0
-
+        
         while retry_count < MAX_RETRIES:
             try:
-                # 合并所有opus数据包
+                if artifacts is None:
-                if audio_format == "pcm":
+                    return "", None
-                    pcm_data = opus_data
-                else:
-                    pcm_data = self.decode_opus(opus_data)
-
-                combined_pcm_data = b"".join(pcm_data)
-
-                # 检查磁盘空间
-                if not self.delete_audio_file:
-                    free_space = shutil.disk_usage(self.output_dir).free
-                    if free_space < len(combined_pcm_data) * 2:  # 预留2倍空间
-                        raise OSError("磁盘空间不足")
-
-                # 判断是否保存为WAV文件
-                if self.delete_audio_file:
-                    pass
-                else:
-                    file_path = self.save_audio_to_file(pcm_data, session_id)
 
                 # 语音识别 - 使用线程池避免阻塞事件循环
                 start_time = time.time()
                 result = await asyncio.to_thread(
                     self.model.generate,
-                    input=combined_pcm_data,
+                    input=artifacts.pcm_bytes,
                     cache={},
                     language="auto",
                     use_itn=True,
@@ -107,7 +89,7 @@ class ASRProvider(ASRProviderBase):
                     f"语音识别耗时: {time.time() - start_time:.3f}s | 结果: {text['content']}"
                 )
 
-                return text, file_path
+                return text, artifacts.file_path
 
             except OSError as e:
                 retry_count += 1
@@ -115,7 +97,7 @@ class ASRProvider(ASRProviderBase):
                     logger.bind(tag=TAG).error(
                         f"语音识别失败（已重试{retry_count}次）: {e}", exc_info=True
                     )
-                    return "", file_path
+                    return "", None
                 logger.bind(tag=TAG).warning(
                     f"语音识别失败，正在重试（{retry_count}/{MAX_RETRIES}）: {e}"
                 )
@@ -123,15 +105,4 @@ class ASRProvider(ASRProviderBase):
 
             except Exception as e:
                 logger.bind(tag=TAG).error(f"语音识别失败: {e}", exc_info=True)
-                return "", file_path
+                return "", None
-
-            finally:
-                # 文件清理逻辑
-                if self.delete_audio_file and file_path and os.path.exists(file_path):
-                    try:
-                        os.remove(file_path)
-                        logger.bind(tag=TAG).debug(f"已删除临时音频文件: {file_path}")
-                    except Exception as e:
-                        logger.bind(tag=TAG).error(
-                            f"文件删除失败: {file_path} | 错误: {e}"
-                        )

main/xiaozhi-server/core/providers/asr/fun_server.py

@@ -101,7 +101,7 @@ class ASRProvider(ASRProviderBase):
         logger.bind(tag=TAG).debug(f"Sent end message: {end_message}")
 
     async def speech_to_text(
-        self, opus_data: List[bytes], session_id: str, audio_format="opus"
+        self, opus_data: List[bytes], session_id: str, audio_format="opus", artifacts=None
     ) -> Tuple[Optional[str], Optional[str]]:
         """
         Convert speech data to text using FunASR.
@@ -109,18 +109,9 @@ class ASRProvider(ASRProviderBase):
         :param session_id: Unique session identifier.
         :return: Tuple containing recognized text and optional timestamp.
         """
-        file_path = None
+        
-        if audio_format == "pcm":
+        if artifacts is None:
-            pcm_data = opus_data
+            return "", None
-        else:
-            pcm_data = self.decode_opus(opus_data)
-        combined_pcm_data = b"".join(pcm_data)
-
-        # 判断是否保存为WAV文件
-        if self.delete_audio_file:
-            pass
-        else:
-            file_path = self.save_audio_to_file(pcm_data, session_id)
         auth_header = {"Authorization": "Bearer; {}".format(self.api_key)}
         async with websockets.connect(
             self.uri,
@@ -132,7 +123,7 @@ class ASRProvider(ASRProviderBase):
             try:
                 # Use asyncio to handle WebSocket communication
                 send_task = asyncio.create_task(
-                    self._send_data(ws, combined_pcm_data, session_id)
+                    self._send_data(ws, artifacts.pcm_bytes, session_id)
                 )
                 receive_task = asyncio.create_task(self._receive_responses(ws))
 
@@ -161,14 +152,14 @@ class ASRProvider(ASRProviderBase):
                 result = lang_tag_filter(result)
                 return (
                     result,
-                    file_path,
+                    artifacts.file_path,
                 )  # Return the recognized text and timestamp (if any)
 
             except websockets.exceptions.ConnectionClosed as e:
                 logger.bind(tag=TAG).error(f"WebSocket connection closed: {e}")
-                return "", file_path
+                return "", artifacts.file_path
             except Exception as e:
                 logger.bind(tag=TAG).error(
                     f"Error during speech-to-text conversion: {e}", exc_info=True
                 )
-                return "", file_path
+                return "", artifacts.file_path

main/xiaozhi-server/core/providers/asr/openai.py

@@ -21,20 +21,16 @@ class ASRProvider(ASRProviderBase):
 
         os.makedirs(self.output_dir, exist_ok=True)
 
-    async def speech_to_text(self, opus_data: List[bytes], session_id: str, audio_format="opus") -> Tuple[Optional[str], Optional[str]]:
+    def requires_file(self) -> bool:
+        return True
+
+    async def speech_to_text(self, opus_data: List[bytes], session_id: str, audio_format="opus", artifacts=None) -> Tuple[Optional[str], Optional[str]]:
         file_path = None
         try:
-            start_time = time.time()
+            if artifacts is None:
-            if audio_format == "pcm":
+                return "", None
-                pcm_data = opus_data
+            file_path = artifacts.file_path
-            else:
+                
-                pcm_data = self.decode_opus(opus_data)
-            file_path = self.save_audio_to_file(pcm_data, session_id)
-
-            logger.bind(tag=TAG).debug(
-                f"音频文件保存耗时: {time.time() - start_time:.3f}s | 路径: {file_path}"
-            )
-
             logger.bind(tag=TAG).info(f"file path: {file_path}")
             headers = {
                 "Authorization": f"Bearer {self.api_key}",
@@ -71,12 +67,4 @@ class ASRProvider(ASRProviderBase):
         except Exception as e:
             logger.bind(tag=TAG).error(f"语音识别失败: {e}")
             return "", None
-        finally:
-            # 文件清理逻辑
-            if self.delete_audio_file and file_path and os.path.exists(file_path):
-                try:
-                    os.remove(file_path)
-                    logger.bind(tag=TAG).debug(f"已删除临时音频文件: {file_path}")
-                except Exception as e:
-                    logger.bind(tag=TAG).error(f"文件删除失败: {file_path} | 错误: {e}")
         

main/xiaozhi-server/core/providers/asr/qwen3_asr_flash.py

@@ -1,5 +1,4 @@
 import os
-import tempfile
 from typing import Optional, Tuple, List
 import dashscope
 from config.logger import setup_logging
@@ -35,56 +34,25 @@ class ASRProvider(ASRProviderBase):
         # 确保输出目录存在
         os.makedirs(self.output_dir, exist_ok=True)
 
-    def _prepare_audio_file(self, pcm_data: bytes) -> str:
+    def prefers_temp_file(self) -> bool:
-        """将PCM数据转换为WAV文件并返回文件路径"""
+        return True
-        try:
+
-            import wave
+    def requires_file(self) -> bool:
-            
+        return True
-            # 创建临时WAV文件
-            with tempfile.NamedTemporaryFile(suffix='.wav', delete=False) as temp_file:
-                temp_path = temp_file.name
-                
-            # 写入WAV格式
-            with wave.open(temp_path, 'wb') as wav_file:
-                wav_file.setnchannels(1)      # 单声道
-                wav_file.setsampwidth(2)      # 16位
-                wav_file.setframerate(16000)  # 16kHz采样率
-                wav_file.writeframes(pcm_data)
-                
-            return temp_path
-            
-        except Exception as e:
-            logger.bind(tag=tag).error(f"音频文件准备失败: {e}")
-            return None
 
     async def speech_to_text(
-        self, opus_data: List[bytes], session_id: str, audio_format="opus"
+        self, opus_data: List[bytes], session_id: str, audio_format="opus", artifacts=None
     ) -> Tuple[Optional[str], Optional[str]]:
         """将语音数据转换为文本"""
         temp_file_path = None
         file_path = None
-        
         try:
-            # 解码音频数据
+            if artifacts is None:
-            if audio_format == "pcm":
-                pcm_data = opus_data
-            else:
-                pcm_data = self.decode_opus(opus_data)
-            
-            combined_pcm_data = b"".join(pcm_data)
-            if len(combined_pcm_data) == 0:
-                logger.bind(tag=tag).warning("音频数据为空")
                 return "", None
-            
+            temp_file_path = artifacts.temp_path
-            # 准备音频文件
+            file_path = artifacts.file_path
-            temp_file_path = self._prepare_audio_file(combined_pcm_data)
             if not temp_file_path:
-                return "", None
+                return "", file_path
-            
-            # 保存音频文件（如果需要）
-            if not self.delete_audio_file:
-                file_path = self.save_audio_to_file(pcm_data, session_id)
-            
             # 构造请求消息
             messages = [
                 {
@@ -141,11 +109,3 @@ class ASRProvider(ASRProviderBase):
         except Exception as e:
             logger.bind(tag=tag).error(f"语音识别失败: {e}")
             return "", file_path
-            
-        finally:
-            # 清理临时文件
-            if temp_file_path and os.path.exists(temp_file_path):
-                try:
-                    os.unlink(temp_file_path)
-                except Exception as e:
-                    logger.bind(tag=tag).warning(f"清理临时文件失败: {e}")

main/xiaozhi-server/core/providers/asr/sherpa_onnx_local.py

@@ -120,24 +120,19 @@ class ASRProvider(ASRProviderBase):
             samples_float32 = samples_float32 / 32768
             return samples_float32, f.getframerate()
 
+    def requires_file(self) -> bool:
+        return True
+
     async def speech_to_text(
-        self, opus_data: List[bytes], session_id: str, audio_format="opus"
+        self, opus_data: List[bytes], session_id: str, audio_format="opus", artifacts=None
     ) -> Tuple[Optional[str], Optional[str]]:
         """语音转文本主处理逻辑"""
         file_path = None
         try:
-            # 保存音频文件
+            if artifacts is None:
-            start_time = time.time()
+                return "", None
-            if audio_format == "pcm":
+            file_path = artifacts.file_path
-                pcm_data = opus_data
-            else:
-                pcm_data = self.decode_opus(opus_data)
-            file_path = self.save_audio_to_file(pcm_data, session_id)
-            logger.bind(tag=TAG).debug(
-                f"音频文件保存耗时: {time.time() - start_time:.3f}s | 路径: {file_path}"
-            )
 
-            # 语音识别
             start_time = time.time()
             s = self.model.create_stream()
             samples, sample_rate = self.read_wave(file_path)
@@ -153,11 +148,3 @@ class ASRProvider(ASRProviderBase):
         except Exception as e:
             logger.bind(tag=TAG).error(f"语音识别失败: {e}", exc_info=True)
             return "", file_path
-        finally:
-            # 文件清理逻辑
-            if self.delete_audio_file and file_path and os.path.exists(file_path):
-                try:
-                    os.remove(file_path)
-                    logger.bind(tag=TAG).debug(f"已删除临时音频文件: {file_path}")
-                except Exception as e:
-                    logger.bind(tag=TAG).error(f"文件删除失败: {file_path} | 错误: {e}")

main/xiaozhi-server/core/providers/asr/tencent.py

@@ -32,35 +32,24 @@ class ASRProvider(ASRProviderBase):
         os.makedirs(self.output_dir, exist_ok=True)
 
     async def speech_to_text(
-        self, opus_data: List[bytes], session_id: str, audio_format="opus"
+        self, opus_data: List[bytes], session_id: str, audio_format="opus", artifacts=None
     ) -> Tuple[Optional[str], Optional[str]]:
         """将语音数据转换为文本"""
         if not opus_data:
             logger.bind(tag=TAG).warning("音频数据为空！")
             return None, None
 
-        file_path = None
         try:
             # 检查配置是否已设置
             if not self.secret_id or not self.secret_key:
                 logger.bind(tag=TAG).error("腾讯云语音识别配置未设置，无法进行识别")
-                return None, file_path
+                return None, None
 
-            # 将Opus音频数据解码为PCM
+            if artifacts is None:
-            if audio_format == "pcm":
+                return "", None
-                pcm_data = opus_data
-            else:
-                pcm_data = self.decode_opus(opus_data)
-            combined_pcm_data = b"".join(pcm_data)
-
-            # 判断是否保存为WAV文件
-            if self.delete_audio_file:
-                pass
-            else:
-                self.save_audio_to_file(pcm_data, session_id)
 
             # 将音频数据转换为Base64编码
-            base64_audio = base64.b64encode(combined_pcm_data).decode("utf-8")
+            base64_audio = base64.b64encode(artifacts.pcm_bytes).decode("utf-8")
 
             # 构建请求体
             request_body = self._build_request_body(base64_audio)
@@ -77,11 +66,11 @@ class ASRProvider(ASRProviderBase):
                     f"腾讯云语音识别耗时: {time.time() - start_time:.3f}s | 结果: {result}"
                 )
 
-            return result, file_path
+            return result, artifacts.file_path
 
         except Exception as e:
             logger.bind(tag=TAG).error(f"处理音频时发生错误！{e}", exc_info=True)
-            return None, file_path
+            return None, None
 
     def _build_request_body(self, base64_audio: str) -> str:
         """构建请求体"""

main/xiaozhi-server/core/providers/asr/vosk.py

@@ -44,36 +44,21 @@ class ASRProvider(ASRProviderBase):
             raise
 
     async def speech_to_text(
-        self, audio_data: List[bytes], session_id: str, audio_format: str = "opus"
+        self, opus_data: List[bytes], session_id: str, audio_format="opus", artifacts=None
     ) -> Tuple[Optional[str], Optional[str]]:
         """将语音数据转换为文本"""
-        file_path = None
         try:
             # 检查模型是否加载成功
             if not self.model:
                 logger.bind(tag=TAG).error("VOSK模型未加载，无法进行识别")
                 return "", None
-
+            
-            # 解码音频（如果原始格式是Opus）
+            if artifacts is None:
-            if audio_format == "pcm":
-                pcm_data = audio_data
-            else:
-                pcm_data = self.decode_opus(audio_data)
-                
-            if not pcm_data:
-                logger.bind(tag=TAG).warning("解码后的PCM数据为空，无法进行识别")
                 return "", None
-                
+            if not artifacts.pcm_bytes:
-            # 合并PCM数据
-            combined_pcm_data = b"".join(pcm_data)
-            if len(combined_pcm_data) == 0:
                 logger.bind(tag=TAG).warning("合并后的PCM数据为空")
                 return "", None
 
-            # 判断是否保存为WAV文件
-            if not self.delete_audio_file:
-                file_path = self.save_audio_to_file(pcm_data, session_id)
-
             start_time = time.time()
             
             
@@ -81,8 +66,8 @@ class ASRProvider(ASRProviderBase):
             chunk_size = 2000
             text_result = ""
             
-            for i in range(0, len(combined_pcm_data), chunk_size):
+            for i in range(0, len(artifacts.pcm_bytes), chunk_size):
-                chunk = combined_pcm_data[i:i+chunk_size]
+                chunk = artifacts.pcm_bytes[i:i+chunk_size]
                 if self.recognizer.AcceptWaveform(chunk):
                     result = json.loads(self.recognizer.Result())
                     text = result.get('text', '')
@@ -99,16 +84,8 @@ class ASRProvider(ASRProviderBase):
                 f"VOSK语音识别耗时: {time.time() - start_time:.3f}s | 结果: {text_result.strip()}"
             )
             
-            return text_result.strip(), file_path
+            return text_result.strip(), artifacts.file_path
             
         except Exception as e:
             logger.bind(tag=TAG).error(f"VOSK语音识别失败: {e}")
             return "", None
-        finally:
-            # 文件清理逻辑
-            if self.delete_audio_file and file_path and os.path.exists(file_path):
-                try:
-                    os.remove(file_path)
-                    logger.bind(tag=TAG).debug(f"已删除临时音频文件: {file_path}")
-                except Exception as e:
-                    logger.bind(tag=TAG).error(f"文件删除失败: {file_path} | 错误: {e}")

main/xiaozhi-server/core/providers/asr/xunfei_stream.py

@@ -101,11 +101,6 @@ class ASRProvider(ASRProviderBase):
         # 先调用父类方法处理基础逻辑
         await super().receive_audio(conn, audio, audio_have_voice)
 
-        # 存储音频数据用于声纹识别
-        if not hasattr(conn, "asr_audio_for_voiceprint"):
-            conn.asr_audio_for_voiceprint = []
-        conn.asr_audio_for_voiceprint.append(audio)
-
         # 如果本次有声音，且之前没有建立连接
         if audio_have_voice and self.asr_ws is None and not self.is_processing:
             try:
@@ -232,13 +227,8 @@ class ASRProvider(ASRProviderBase):
 
                     if status == 2:
                         if conn.client_listen_mode == "manual":
-                            audio_data = getattr(conn, 'asr_audio_for_voiceprint', [])
+                            logger.bind(tag=TAG).debug("收到最终识别结果，触发处理")
-                            if len(audio_data) > 0:
+                            await self.handle_voice_stop(conn, conn.asr_audio)
-                                logger.bind(tag=TAG).debug("收到最终识别结果，触发处理")
-                                await self.handle_voice_stop(conn, audio_data)
-                                # 清理音频缓存
-                                conn.asr_audio.clear()
-                        conn.reset_vad_states()
                         break
 
                 except asyncio.TimeoutError:
@@ -262,13 +252,7 @@ class ASRProvider(ASRProviderBase):
         finally:
             # 清理连接资源
             await self._cleanup()
-
+            conn.reset_audio_states()
-            # 清理连接的音频缓存
-            if conn:
-                if hasattr(conn, "asr_audio_for_voiceprint"):
-                    conn.asr_audio_for_voiceprint = []
-                if hasattr(conn, "asr_audio"):
-                    conn.asr_audio = []
 
     async def handle_voice_stop(self, conn, asr_audio_task: List[bytes]):
         """处理语音停止，发送最后一帧并处理识别结果"""
@@ -334,7 +318,7 @@ class ASRProvider(ASRProviderBase):
 
         logger.bind(tag=TAG).debug("ASR会话清理完成")
 
-    async def speech_to_text(self, opus_data, session_id, audio_format):
+    async def speech_to_text(self, opus_data, session_id, audio_format, artifacts=None):
         """获取识别结果"""
         result = self.text
         self.text = ""
@@ -363,10 +347,3 @@ class ASRProvider(ASRProviderBase):
             except Exception as e:
                 logger.bind(tag=TAG).debug(f"释放Xunfei decoder资源时出错: {e}")
 
-        # 清理所有连接的音频缓冲区
-        if hasattr(self, "_connections"):
-            for conn in self._connections.values():
-                if hasattr(conn, "asr_audio_for_voiceprint"):
-                    conn.asr_audio_for_voiceprint = []
-                if hasattr(conn, "asr_audio"):
-                    conn.asr_audio = []

main/xiaozhi-server/core/providers/tts/alibl_stream.py

@@ -41,8 +41,6 @@ class TTSProvider(TTSProviderBase):
 
         # 音频参数配置
         self.format = config.get("format", "pcm")
-        sample_rate = config.get("sample_rate", "24000")
-        self.sample_rate = int(sample_rate) if sample_rate else 24000
 
         volume = config.get("volume", "50")
         self.volume = int(volume) if volume else 50
@@ -60,11 +58,6 @@ class TTSProvider(TTSProviderBase):
             "X-DashScope-DataInspection": "enable",
         }
 
-        # 创建Opus编码器
-        self.opus_encoder = opus_encoder_utils.OpusEncoderUtils(
-            sample_rate=self.sample_rate, channels=1, frame_size_ms=60
-        )
-
     async def _ensure_connection(self):
         """确保WebSocket连接可用，支持60秒内连接复用"""
         try:
@@ -245,7 +238,7 @@ class TTSProvider(TTSProviderBase):
                         "text_type": "PlainText",
                         "voice": self.voice,
                         "format": self.format,
-                        "sample_rate": self.sample_rate,
+                        "sample_rate": self.conn.sample_rate,
                         "volume": self.volume,
                         "rate": self.rate,
                         "pitch": self.pitch,
@@ -429,7 +422,7 @@ class TTSProvider(TTSProviderBase):
                                 "text_type": "PlainText",
                                 "voice": self.voice,
                                 "format": self.format,
-                                "sample_rate": self.sample_rate,
+                                "sample_rate": self.conn.sample_rate,
                                 "volume": self.volume,
                                 "rate": self.rate,
                                 "pitch": self.pitch,

main/xiaozhi-server/core/providers/tts/aliyun.py

@@ -95,8 +95,6 @@ class TTSProvider(TTSProviderBase):
         self.appkey = config.get("appkey")
         self.format = config.get("format", "wav")
         self.audio_file_type = config.get("format", "wav")
-        sample_rate = config.get("sample_rate", "16000")
-        self.sample_rate = int(sample_rate) if sample_rate else 16000
 
         if config.get("private_voice"):
             self.voice = config.get("private_voice")
@@ -172,7 +170,7 @@ class TTSProvider(TTSProviderBase):
             "token": self.token,
             "text": text,
             "format": self.format,
-            "sample_rate": self.sample_rate,
+            "sample_rate": self.conn.sample_rate,
             "voice": self.voice,
             "volume": self.volume,
             "speech_rate": self.speech_rate,

main/xiaozhi-server/core/providers/tts/aliyun_stream.py

@@ -99,10 +99,6 @@ class TTSProvider(TTSProviderBase):
         self.format = config.get("format", "pcm")
         self.audio_file_type = config.get("format", "pcm")
 
-        # 采样率配置
-        sample_rate = config.get("sample_rate", "16000")
-        self.sample_rate = int(sample_rate) if sample_rate else 16000
-
         # 音色配置 - CosyVoice大模型音色
         if config.get("private_voice"):
             self.voice = config.get("private_voice")
@@ -134,11 +130,6 @@ class TTSProvider(TTSProviderBase):
         # 专属tts设置
         self.task_id = uuid.uuid4().hex
 
-        # 创建Opus编码器
-        self.opus_encoder = opus_encoder_utils.OpusEncoderUtils(
-            sample_rate=16000, channels=1, frame_size_ms=60
-        )
-
         # Token管理
         if self.access_key_id and self.access_key_secret:
             self._refresh_token()
@@ -344,7 +335,7 @@ class TTSProvider(TTSProviderBase):
                 "payload": {
                     "voice": self.voice,
                     "format": self.format,
-                    "sample_rate": self.sample_rate,
+                    "sample_rate": self.conn.sample_rate,
                     "volume": self.volume,
                     "speech_rate": self.speech_rate,
                     "pitch_rate": self.pitch_rate,
@@ -508,7 +499,7 @@ class TTSProvider(TTSProviderBase):
                         "payload": {
                             "voice": self.voice,
                             "format": self.format,
-                            "sample_rate": self.sample_rate,
+                            "sample_rate": self.conn.sample_rate,
                             "volume": self.volume,
                             "speech_rate": self.speech_rate,
                             "pitch_rate": self.pitch_rate,

main/xiaozhi-server/core/providers/tts/base.py

@@ -1,17 +1,18 @@
 import os
 import re
-import time
 import uuid
 import queue
 import asyncio
 import threading
 import traceback
+
 from core.utils import p3
 from datetime import datetime
 from core.utils import textUtils
 from typing import Callable, Any
 from abc import ABC, abstractmethod
 from config.logger import setup_logging
+from core.utils import opus_encoder_utils
 from core.utils.tts import MarkdownCleaner
 from core.utils.output_counter import add_device_output
 from core.handle.reportHandle import enqueue_tts_report
@@ -97,6 +98,8 @@ class TTSProviderBase(ABC):
                             file_type=self.audio_file_type,
                             is_opus=True,
                             callback=opus_handler,
+                            sample_rate=self.conn.sample_rate,
+                            opus_encoder=self.opus_encoder,
                         )
                         break
                     else:
@@ -138,7 +141,7 @@ class TTSProviderBase(ABC):
                     logger.bind(tag=TAG).error(
                         f"语音生成失败: {text}，请检查网络或服务是否正常"
                     )
-                    self.tts_audio_queue.put((SentenceType.FIRST, None, text))
+                self.tts_audio_queue.put((SentenceType.FIRST, None, text))
                 self._process_audio_file_stream(tmp_file, callback=opus_handler)
             except Exception as e:
                 logger.bind(tag=TAG).error(f"Failed to generate TTS file: {e}")
@@ -158,7 +161,8 @@ class TTSProviderBase(ABC):
                             audio_bytes,
                             file_type=self.audio_file_type,
                             is_opus=True,
-                            callback=lambda data: audio_datas.append(data)
+                            callback=lambda data: audio_datas.append(data),
+                            sample_rate=self.conn.sample_rate,
                         )
                         return audio_datas
                     else:
@@ -214,13 +218,13 @@ class TTSProviderBase(ABC):
         self, audio_file_path, callback: Callable[[Any], Any] = None
     ):
         """音频文件转换为PCM编码"""
-        return audio_to_data_stream(audio_file_path, is_opus=False, callback=callback)
+        return audio_to_data_stream(audio_file_path, is_opus=False, callback=callback, sample_rate=self.conn.sample_rate, opus_encoder=None)
 
     def audio_to_opus_data_stream(
         self, audio_file_path, callback: Callable[[Any], Any] = None
     ):
         """音频文件转换为Opus编码"""
-        return audio_to_data_stream(audio_file_path, is_opus=True, callback=callback)
+        return audio_to_data_stream(audio_file_path, is_opus=True, callback=callback, sample_rate=self.conn.sample_rate, opus_encoder=self.opus_encoder)
 
     def tts_one_sentence(
         self,
@@ -252,6 +256,13 @@ class TTSProviderBase(ABC):
 
     async def open_audio_channels(self, conn):
         self.conn = conn
+
+        # 根据conn的sample_rate创建编码器，如果子类已经创建则不覆盖（IndexTTS接口返回为24kHZ-待重采样处理）
+        if not hasattr(self, 'opus_encoder') or self.opus_encoder is None:
+            self.opus_encoder = opus_encoder_utils.OpusEncoderUtils(
+                sample_rate=conn.sample_rate, channels=1, frame_size_ms=60
+            )
+
         # tts 消化线程
         self.tts_priority_thread = threading.Thread(
             target=self.tts_text_priority_thread, daemon=True

main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py

@@ -154,16 +154,29 @@ class TTSProvider(TTSProviderBase):
             self.voice = config.get("private_voice")
         else:
             self.voice = config.get("speaker")
-        speech_rate = config.get("speech_rate", "0")
+
-        loudness_rate = config.get("loudness_rate", "0")
+        # 默认 audio_params 配置
-        pitch = config.get("pitch", "0")
+        default_audio_params = {
-        self.speech_rate = int(speech_rate) if speech_rate else 0
+            "speech_rate": 0,
-        self.loudness_rate = int(loudness_rate) if loudness_rate else 0
+            "loudness_rate": 0
-        self.pitch = int(pitch) if pitch else 0
+        }
-        # 多情感音色参数
+
-        self.emotion = config.get("emotion", "neutral")  
+        # 默认 additions 配置
-        emotion_scale = config.get("emotion_scale", "4")
+        default_additions = {
-        self.emotion_scale = int(emotion_scale) if emotion_scale else 4
+            "aigc_metadata": {},
+            "cache_config": {},
+            "post_process": {
+                "pitch": 0
+            }
+        }
+
+        # 默认 mix_speaker 配置
+        default_mix_speaker = {}
+
+        # 合并用户配置
+        self.audio_params = {**default_audio_params, **config.get("audio_params", {})}
+        self.additions = {**default_additions, **config.get("additions", {})}
+        self.mix_speaker = {**default_mix_speaker, **config.get("mix_speaker", {})}
 
         self.ws_url = config.get("ws_url")
         self.authorization = config.get("authorization")
@@ -171,9 +184,7 @@ class TTSProvider(TTSProviderBase):
         enable_ws_reuse_value = config.get("enable_ws_reuse", True)
         self.enable_ws_reuse = False if str(enable_ws_reuse_value).lower() == 'false' else True
         self.tts_text = ""
-        self.opus_encoder = opus_encoder_utils.OpusEncoderUtils(
+
-            sample_rate=16000, channels=1, frame_size_ms=60
-        )
         model_key_msg = check_model_key("TTS", self.access_token)
         if model_key_msg:
             logger.bind(tag=TAG).error(model_key_msg)
@@ -181,6 +192,8 @@ class TTSProvider(TTSProviderBase):
     async def open_audio_channels(self, conn):
         try:
             await super().open_audio_channels(conn)
+            # 更新 audio_params 中的采样率为实际的 conn.sample_rate
+            self.audio_params["sample_rate"] = conn.sample_rate
         except Exception as e:
             logger.bind(tag=TAG).error(f"Failed to open audio channels: {str(e)}")
             self.ws = None
@@ -646,20 +659,18 @@ class TTSProvider(TTSProviderBase):
         text="",
         speaker="",
         audio_format="pcm",
-        audio_sample_rate=16000,
     ):
-        audio_params = {
+        # 构建 req_params
-            "format": audio_format,
+        req_params = {
-            "sample_rate": audio_sample_rate,
+            "text": text,
-            "speech_rate": self.speech_rate,
+            "speaker": speaker,
-            "loudness_rate": self.loudness_rate
+            "audio_params": {**self.audio_params, "format": audio_format},
+            "additions": json.dumps(self.additions)
         }
-
+        
-        # 如果是多情感音色,添加情感参数
+        # 如果有 mix_speaker 配置，添加到 req_params
-        if '_emo_' in self.voice:
+        if self.mix_speaker:
-            if self.emotion:
+            req_params["mix_speaker"] = self.mix_speaker
-                audio_params["emotion"] = self.emotion
-                audio_params["emotion_scale"] = self.emotion_scale
 
         return str.encode(
             json.dumps(
@@ -667,17 +678,7 @@ class TTSProvider(TTSProviderBase):
                     "user": {"uid": uid},
                     "event": event,
                     "namespace": "BidirectionalTTS",
-                    "req_params": {
+                    "req_params": req_params
-                        "text": text,
-                        "speaker": speaker,
-                        "audio_params": audio_params,
-                        "additions": json.dumps({
-                            "post_process": {
-                                "pitch": self.pitch
-                            }
-                        })
-                    },
-
                 }
             )
         )

main/xiaozhi-server/core/providers/tts/index_stream.py

@@ -174,6 +174,20 @@ class TTSProvider(TTSProviderBase):
             logger.bind(tag=TAG).error(f"TTS请求异常: {e}")
             self.tts_audio_queue.put((SentenceType.LAST, [], None))
 
+    def audio_to_pcm_data_stream(
+        self, audio_file_path, callback=None
+    ):
+        """音频文件转换为PCM编码，使用24kHz采样率"""
+        from core.utils.util import audio_to_data_stream
+        return audio_to_data_stream(audio_file_path, is_opus=False, callback=callback, sample_rate=24000, opus_encoder=None)
+
+    def audio_to_opus_data_stream(
+        self, audio_file_path, callback=None
+    ):
+        """音频文件转换为Opus编码，使用24kHz采样率和自己的编码器"""
+        from core.utils.util import audio_to_data_stream
+        return audio_to_data_stream(audio_file_path, is_opus=True, callback=callback, sample_rate=24000, opus_encoder=self.opus_encoder)
+
     async def close(self):
         """资源清理"""
         await super().close()

main/xiaozhi-server/core/providers/tts/linkerai.py

@@ -25,11 +25,6 @@ class TTSProvider(TTSProviderBase):
         self.audio_format = "pcm"
         self.before_stop_play_files = []
 
-        # 创建Opus编码器
-        self.opus_encoder = opus_encoder_utils.OpusEncoderUtils(
-            sample_rate=16000, channels=1, frame_size_ms=60
-        )
-
         # PCM缓冲区
         self.pcm_buffer = bytearray()
 
@@ -127,7 +122,7 @@ class TTSProvider(TTSProviderBase):
             "spk_id": self.voice,
             "frame_durition": 60,
             "stream": "true",
-            "target_sr": 16000,
+            "target_sr": self.conn.sample_rate,
             "audio_format": "pcm",
             "instruct_text": "请生成一段自然流畅的语音",
         }
@@ -136,7 +131,7 @@ class TTSProvider(TTSProviderBase):
             "Content-Type": "application/json",
         }
 
-        # 一帧 PCM 所需字节数：60 ms × 16 kHz × 1 ch × 2 B = 1 920
+        # 一帧 PCM 所需字节数：60 ms × sample_rate × 1 ch × 2 B
         frame_bytes = int(
             self.opus_encoder.sample_rate
             * self.opus_encoder.channels  # 1
@@ -213,7 +208,7 @@ class TTSProvider(TTSProviderBase):
             "spk_id": self.voice,
             "frame_duration": 60,
             "stream": False,
-            "target_sr": 16000,
+            "target_sr": self.conn.sample_rate,
             "audio_format": self.audio_format,
             "instruct_text": "请生成一段自然流畅的语音",
         }

main/xiaozhi-server/core/providers/tts/minimax_httpstream.py

@@ -64,13 +64,17 @@ class TTSProvider(TTSProviderBase):
         }
         self.audio_file_type = defult_audio_setting.get("format", "pcm")
 
-        self.opus_encoder = opus_encoder_utils.OpusEncoderUtils(
-            sample_rate=24000, channels=1, frame_size_ms=60
-        )
-
         # PCM缓冲区
         self.pcm_buffer = bytearray()
 
+    async def open_audio_channels(self, conn):
+        """初始化音频通道,并根据conn.sample_rate更新配置"""
+        # 调用父类方法
+        await super().open_audio_channels(conn)
+
+        # 更新audio_setting中的采样率为实际的conn.sample_rate
+        self.audio_setting["sample_rate"] = conn.sample_rate
+
     def tts_text_priority_thread(self):
         """流式文本处理线程"""
         while not self.conn.stop_event.is_set():
@@ -212,6 +216,18 @@ class TTSProvider(TTSProviderBase):
 
                             try:
                                 data = json.loads(json_str)
+
+                                # 检查业务层错误
+                                base_resp = data.get("base_resp", {})
+                                status_code = base_resp.get("status_code", 0)
+                                if status_code != 0:
+                                    status_msg = base_resp.get("status_msg", "未知错误")
+                                    logger.bind(tag=TAG).error(
+                                        f"TTS请求失败, 错误码:{status_code}, 错误消息:{status_msg}"
+                                    )
+                                    self.tts_audio_queue.put((SentenceType.LAST, [], None))
+                                    return
+
                                 status = data.get("data", {}).get("status", 1)
                                 audio_hex = data.get("data", {}).get("audio")
 

main/xiaozhi-server/core/providers/tts/paddle_speech.py

@@ -25,10 +25,7 @@ class TTSProvider(TTSProviderBase):
             self.spk_id = int(config.get("private_voice"))
         else:
             self.spk_id = int(config.get("spk_id", "0"))
-            
+
-        sample_rate = config.get("sample_rate", 24000)
-        self.sample_rate = float(sample_rate) if sample_rate else 24000
-        
         speed = config.get("speed", 1.0)
         self.speed = float(speed) if speed else 1.0
         

main/xiaozhi-server/core/providers/tts/siliconflow.py

@@ -13,7 +13,6 @@ class TTSProvider(TTSProviderBase):
             self.voice = config.get("voice")
         self.response_format = config.get("response_format", "mp3")
         self.audio_file_type = config.get("response_format", "mp3")
-        self.sample_rate = config.get("sample_rate")
         self.speed = float(config.get("speed", 1.0))
         self.gain = config.get("gain")
 

main/xiaozhi-server/core/providers/tts/xunfei_stream.py

@@ -91,9 +91,6 @@ class TTSProvider(TTSProviderBase):
         # 音频编码配置
         self.format = config.get("format", "raw")
 
-        sample_rate = config.get("sample_rate", "24000")
-        self.sample_rate = int(sample_rate) if sample_rate else 24000
-
         # 口语化配置
         self.oral_level = config.get("oral_level", "mid")
 
@@ -113,11 +110,6 @@ class TTSProvider(TTSProviderBase):
         # 序列号管理
         self.text_seq = 0
 
-        # 创建Opus编码器
-        self.opus_encoder = opus_encoder_utils.OpusEncoderUtils(
-            sample_rate=self.sample_rate, channels=1, frame_size_ms=60
-        )
-
         # 验证必需参数
         if not all([self.app_id, self.api_key, self.api_secret]):
             raise ValueError("讯飞TTS需要配置app_id、api_key和api_secret")
@@ -507,7 +499,7 @@ class TTSProvider(TTSProviderBase):
                     "rhy": 0,
                     "audio": {
                         "encoding": self.format,
-                        "sample_rate": self.sample_rate,
+                        "sample_rate": self.conn.sample_rate,
                         "channels": 1,
                         "bit_depth": 16,
                         "frame_size": 0

main/xiaozhi-server/core/utils/util.py

@@ -227,7 +227,7 @@ def extract_json_from_string(input_string):
 
 
 def audio_to_data_stream(
-    audio_file_path, is_opus=True, callback: Callable[[Any], Any] = None
+    audio_file_path, is_opus=True, callback: Callable[[Any], Any] = None, sample_rate=16000, opus_encoder=None
 ) -> None:
     # 获取文件后缀名
     file_type = os.path.splitext(audio_file_path)[1]
@@ -238,12 +238,12 @@ def audio_to_data_stream(
         audio_file_path, format=file_type, parameters=["-nostdin"]
     )
 
-    # 转换为单声道/16kHz采样率/16位小端编码（确保与编码器匹配）
+    # 转换为单声道/指定采样率/16位小端编码（确保与编码器匹配）
-    audio = audio.set_channels(1).set_frame_rate(16000).set_sample_width(2)
+    audio = audio.set_channels(1).set_frame_rate(sample_rate).set_sample_width(2)
 
     # 获取原始PCM数据（16位小端）
     raw_data = audio.raw_data
-    pcm_to_data_stream(raw_data, is_opus, callback)
+    pcm_to_data_stream(raw_data, is_opus, callback, sample_rate, opus_encoder)
 
 
 async def audio_to_data(
@@ -325,7 +325,7 @@ async def audio_to_data(
 
 
 def audio_bytes_to_data_stream(
-    audio_bytes, file_type, is_opus, callback: Callable[[Any], Any]
+    audio_bytes, file_type, is_opus, callback: Callable[[Any], Any], sample_rate=16000, opus_encoder=None
 ) -> None:
     """
     直接用音频二进制数据转为opus/pcm数据，支持wav、mp3、p3
@@ -338,18 +338,30 @@ def audio_bytes_to_data_stream(
         audio = AudioSegment.from_file(
             BytesIO(audio_bytes), format=file_type, parameters=["-nostdin"]
         )
-        audio = audio.set_channels(1).set_frame_rate(16000).set_sample_width(2)
+        audio = audio.set_channels(1).set_frame_rate(sample_rate).set_sample_width(2)
         raw_data = audio.raw_data
-        pcm_to_data_stream(raw_data, is_opus, callback)
+        pcm_to_data_stream(raw_data, is_opus, callback, sample_rate, opus_encoder)
 
 
-def pcm_to_data_stream(raw_data, is_opus=True, callback: Callable[[Any], Any] = None):
+def pcm_to_data_stream(raw_data, is_opus=True, callback: Callable[[Any], Any] = None, sample_rate=16000, opus_encoder=None):
-    # 初始化Opus编码器
+    """
-    encoder = opuslib_next.Encoder(16000, 1, opuslib_next.APPLICATION_AUDIO)
+    将PCM数据流式编码为Opus或直接输出PCM
+
+    Args:
+        raw_data: PCM原始数据
+        is_opus: 是否编码为Opus
+        callback: 回调函数
+        sample_rate: 采样率
+        opus_encoder: OpusEncoderUtils对象(推荐提供以保持编码器状态连续)
+    """
+    using_temp_encoder = False
+    if is_opus and opus_encoder is None:
+        encoder = opuslib_next.Encoder(sample_rate, 1, opuslib_next.APPLICATION_AUDIO)
+        using_temp_encoder = True
 
     # 编码参数
     frame_duration = 60  # 60ms per frame
-    frame_size = int(16000 * frame_duration / 1000)  # 960 samples/frame
+    frame_size = int(sample_rate * frame_duration / 1000)  # samples/frame
 
     # 按帧处理所有音频数据（包括最后一帧可能补零）
     for i in range(0, len(raw_data), frame_size * 2):  # 16bit=2bytes/sample
@@ -361,12 +373,17 @@ def pcm_to_data_stream(raw_data, is_opus=True, callback: Callable[[Any], Any] =
             chunk += b"\x00" * (frame_size * 2 - len(chunk))
 
         if is_opus:
-            # 转换为numpy数组处理
+            if using_temp_encoder:
-            np_frame = np.frombuffer(chunk, dtype=np.int16)
+                # 使用临时编码器（仅用于独立音频场景）
-            # 编码Opus数据
+                np_frame = np.frombuffer(chunk, dtype=np.int16)
-            frame_data = encoder.encode(np_frame.tobytes(), frame_size)
+                frame_data = encoder.encode(np_frame.tobytes(), frame_size)
-            callback(frame_data)
+                callback(frame_data)
+            else:
+                # 使用外部编码器（TTS流式场景,保持状态连续）
+                is_last = (i + frame_size * 2 >= len(raw_data))
+                opus_encoder.encode_pcm_to_opus_stream(chunk, end_of_stream=is_last, callback=callback)
         else:
+            # PCM模式,直接输出
             frame_data = chunk if isinstance(chunk, bytes) else bytes(chunk)
             callback(frame_data)
 

main/xiaozhi-server/test/js/app.js

@@ -1,9 +1,10 @@
 // 主应用入口
-import { log } from './utils/logger.js';
+import { checkOpusLoaded, initOpusEncoder } from './core/audio/opus-codec.js?v=0127';
-import { checkOpusLoaded, initOpusEncoder } from './core/audio/opus-codec.js';
+import { getAudioPlayer } from './core/audio/player.js?v=0127';
-import { uiController } from './ui/controller.js';
+import { checkMicrophoneAvailability, isHttpNonLocalhost } from './core/audio/recorder.js?v=0127';
-import { getAudioPlayer } from './core/audio/player.js';
+import { initMcpTools } from './core/mcp/tools.js?v=0127';
-import { initMcpTools } from './core/mcp/tools.js';
+import { uiController } from './ui/controller.js?v=0127';
+import { log } from './utils/logger.js?v=0127';
 
 // 应用类
 class App {
@@ -16,30 +17,24 @@ class App {
     // 初始化应用
     async init() {
         log('正在初始化应用...', 'info');
-
         // 初始化UI控制器
         this.uiController = uiController;
         this.uiController.init();
-
         // 检查Opus库
         checkOpusLoaded();
-
         // 初始化Opus编码器
         initOpusEncoder();
-
         // 初始化音频播放器
         this.audioPlayer = getAudioPlayer();
         await this.audioPlayer.start();
-
         // 初始化MCP工具
         initMcpTools();
-
+        // 检查麦克风可用性
+        await this.checkMicrophoneAvailability();
         // 初始化Live2D
         await this.initLive2D();
-
         // 关闭加载loading
         this.setModelLoadingStatus(false);
-
         log('应用初始化完成', 'success');
     }
 
@@ -50,21 +45,17 @@ class App {
             if (typeof window.Live2DManager === 'undefined') {
                 throw new Error('Live2DManager未加载，请检查脚本引入顺序');
             }
-
             this.live2dManager = new window.Live2DManager();
             await this.live2dManager.initializeLive2D();
-
             // 更新UI状态
             const live2dStatus = document.getElementById('live2dStatus');
             if (live2dStatus) {
                 live2dStatus.textContent = '● 已加载';
                 live2dStatus.className = 'status loaded';
             }
-
             log('Live2D初始化完成', 'success');
         } catch (error) {
             log(`Live2D初始化失败: ${error.message}`, 'error');
-
             // 更新UI状态
             const live2dStatus = document.getElementById('live2dStatus');
             if (live2dStatus) {
@@ -81,18 +72,41 @@ class App {
             modelLoading.style.display = isLoading ? 'flex' : 'none';
         }
     }
+
+    /**
+     * 检查麦克风可用性
+     * 在应用初始化时调用，检查麦克风是否可用并更新UI状态
+     */
+    async checkMicrophoneAvailability() {
+        try {
+            const isAvailable = await checkMicrophoneAvailability();
+            const isHttp = isHttpNonLocalhost();
+            // 保存可用性状态到全局变量
+            window.microphoneAvailable = isAvailable;
+            window.isHttpNonLocalhost = isHttp;
+            // 更新UI
+            if (this.uiController) {
+                this.uiController.updateMicrophoneAvailability(isAvailable, isHttp);
+            }
+            log(`麦克风可用性检查完成: ${isAvailable ? '可用' : '不可用'}`, isAvailable ? 'success' : 'warning');
+        } catch (error) {
+            log(`检查麦克风可用性失败: ${error.message}`, 'error');
+            // 默认设置为不可用
+            window.microphoneAvailable = false;
+            window.isHttpNonLocalhost = isHttpNonLocalhost();
+            if (this.uiController) {
+                this.uiController.updateMicrophoneAvailability(false, window.isHttpNonLocalhost);
+            }
+        }
+    }
 }
 
 // 创建并启动应用
 const app = new App();
-
 // 将应用实例暴露到全局，供其他模块访问
 window.chatApp = app;
-
 document.addEventListener('DOMContentLoaded', () => {
     // 初始化应用
     app.init();
 });
-
-
 export default app;

main/xiaozhi-server/test/js/core/audio/opus-codec.js

@@ -1,4 +1,4 @@
-import { log } from '../../utils/logger.js';
+import { log } from '../../utils/logger.js?v=0127';
 
 
 // 检查Opus库是否已加载

main/xiaozhi-server/test/js/core/audio/player.js

@@ -1,7 +1,7 @@
 // 音频播放模块
-import { log } from '../../utils/logger.js';
+import BlockingQueue from '../../utils/blocking-queue.js?v=0127';
-import BlockingQueue from '../../utils/blocking-queue.js';
+import { log } from '../../utils/logger.js?v=0127';
-import { createStreamingContext } from './stream-context.js';
+import { createStreamingContext } from './stream-context.js?v=0127';
 
 // 音频播放器类
 export class AudioPlayer {

main/xiaozhi-server/test/js/core/audio/recorder.js

@@ -1,9 +1,9 @@
-// 音频录制模块
+// Audio recording module
-import { log } from '../../utils/logger.js';
+import { log } from '../../utils/logger.js?v=0127';
-import { initOpusEncoder } from './opus-codec.js';
+import { initOpusEncoder } from './opus-codec.js?v=0127';
-import { getAudioPlayer } from './player.js';
+import { getAudioPlayer } from './player.js?v=0127';
 
-// 音频录制器类
+// Audio recorder class
 export class AudioRecorder {
     constructor() {
         this.isRecording = false;
@@ -19,25 +19,23 @@ export class AudioRecorder {
         this.visualizationRequest = null;
         this.recordingTimer = null;
         this.websocket = null;
-
+        // Callback functions
-        // 回调函数
         this.onRecordingStart = null;
         this.onRecordingStop = null;
         this.onVisualizerUpdate = null;
     }
 
-    // 设置WebSocket实例
+    // Set WebSocket instance
     setWebSocket(ws) {
         this.websocket = ws;
     }
 
-    // 获取AudioContext实例
+    // Get AudioContext instance
     getAudioContext() {
-        const audioPlayer = getAudioPlayer();
+        return getAudioPlayer().getAudioContext();
-        return audioPlayer.getAudioContext();
     }
 
-    // 初始化编码器
+    // Initialize encoder
     initEncoder() {
         if (!this.opusEncoder) {
             this.opusEncoder = initOpusEncoder();
@@ -45,7 +43,7 @@ export class AudioRecorder {
         return this.opusEncoder;
     }
 
-    // PCM处理器代码
+    // PCM processor code
     getAudioProcessorCode() {
         return `
             class AudioRecorderProcessor extends AudioWorkletProcessor {
@@ -56,166 +54,132 @@ export class AudioRecorder {
                     this.buffer = new Int16Array(this.frameSize);
                     this.bufferIndex = 0;
                     this.isRecording = false;
-
                     this.port.onmessage = (event) => {
                         if (event.data.command === 'start') {
                             this.isRecording = true;
                             this.port.postMessage({ type: 'status', status: 'started' });
                         } else if (event.data.command === 'stop') {
                             this.isRecording = false;
-
                             if (this.bufferIndex > 0) {
                                 const finalBuffer = this.buffer.slice(0, this.bufferIndex);
-                                this.port.postMessage({
+                                this.port.postMessage({ type: 'buffer', buffer: finalBuffer });
-                                    type: 'buffer',
-                                    buffer: finalBuffer
-                                });
                                 this.bufferIndex = 0;
                             }
-
                             this.port.postMessage({ type: 'status', status: 'stopped' });
                         }
                     };
                 }
-
                 process(inputs, outputs, parameters) {
                     if (!this.isRecording) return true;
-
                     const input = inputs[0][0];
                     if (!input) return true;
-
                     for (let i = 0; i < input.length; i++) {
                         if (this.bufferIndex >= this.frameSize) {
-                            this.port.postMessage({
+                            this.port.postMessage({ type: 'buffer', buffer: this.buffer.slice(0) });
-                                type: 'buffer',
-                                buffer: this.buffer.slice(0)
-                            });
                             this.bufferIndex = 0;
                         }
-
                         this.buffer[this.bufferIndex++] = Math.max(-32768, Math.min(32767, Math.floor(input[i] * 32767)));
                     }
-
                     return true;
                 }
             }
-
             registerProcessor('audio-recorder-processor', AudioRecorderProcessor);
         `;
     }
 
-    // 创建音频处理器
+    // Create audio processor
     async createAudioProcessor() {
         this.audioContext = this.getAudioContext();
-
         try {
             if (this.audioContext.audioWorklet) {
                 const blob = new Blob([this.getAudioProcessorCode()], { type: 'application/javascript' });
                 const url = URL.createObjectURL(blob);
                 await this.audioContext.audioWorklet.addModule(url);
                 URL.revokeObjectURL(url);
-
                 const audioProcessor = new AudioWorkletNode(this.audioContext, 'audio-recorder-processor');
-
                 audioProcessor.port.onmessage = (event) => {
                     if (event.data.type === 'buffer') {
                         this.processPCMBuffer(event.data.buffer);
                     }
                 };
-
                 log('使用AudioWorklet处理音频', 'success');
-
                 const silent = this.audioContext.createGain();
                 silent.gain.value = 0;
                 audioProcessor.connect(silent);
                 silent.connect(this.audioContext.destination);
                 return { node: audioProcessor, type: 'worklet' };
             } else {
-                log('AudioWorklet不可用，使用ScriptProcessorNode作为回退方案', 'warning');
+                log('AudioWorklet不可用，使用ScriptProcessorNode作为后备方案', 'warning');
                 return this.createScriptProcessor();
             }
         } catch (error) {
-            log(`创建音频处理器失败: ${error.message}，尝试回退方案`, 'error');
+            log(`创建音频处理器失败: ${error.message}，尝试后备方案`, 'error');
             return this.createScriptProcessor();
         }
     }
 
-    // 创建ScriptProcessor作为回退
+    // Create ScriptProcessor as fallback
     createScriptProcessor() {
         try {
             const frameSize = 4096;
             const scriptProcessor = this.audioContext.createScriptProcessor(frameSize, 1, 1);
-
             scriptProcessor.onaudioprocess = (event) => {
                 if (!this.isRecording) return;
-
                 const input = event.inputBuffer.getChannelData(0);
                 const buffer = new Int16Array(input.length);
-
                 for (let i = 0; i < input.length; i++) {
                     buffer[i] = Math.max(-32768, Math.min(32767, Math.floor(input[i] * 32767)));
                 }
-
                 this.processPCMBuffer(buffer);
             };
-
             const silent = this.audioContext.createGain();
             silent.gain.value = 0;
             scriptProcessor.connect(silent);
             silent.connect(this.audioContext.destination);
-
+            log('使用ScriptProcessorNode作为后备方案成功', 'warning');
-            log('使用ScriptProcessorNode作为回退方案成功', 'warning');
             return { node: scriptProcessor, type: 'processor' };
         } catch (fallbackError) {
-            log(`回退方案也失败: ${fallbackError.message}`, 'error');
+            log(`后备方案也失败: ${fallbackError.message}`, 'error');
             return null;
         }
     }
 
-    // 处理PCM缓冲数据
+    // Process PCM buffer data
     processPCMBuffer(buffer) {
         if (!this.isRecording) return;
-
         const newBuffer = new Int16Array(this.pcmDataBuffer.length + buffer.length);
         newBuffer.set(this.pcmDataBuffer);
         newBuffer.set(buffer, this.pcmDataBuffer.length);
         this.pcmDataBuffer = newBuffer;
-
         const samplesPerFrame = 960;
-
         while (this.pcmDataBuffer.length >= samplesPerFrame) {
             const frameData = this.pcmDataBuffer.slice(0, samplesPerFrame);
             this.pcmDataBuffer = this.pcmDataBuffer.slice(samplesPerFrame);
-
             this.encodeAndSendOpus(frameData);
         }
     }
 
-    // 编码并发送Opus数据
+    // Encode and send Opus data
     encodeAndSendOpus(pcmData = null) {
         if (!this.opusEncoder) {
             log('Opus编码器未初始化', 'error');
             return;
         }
-
         try {
             if (pcmData) {
                 const opusData = this.opusEncoder.encode(pcmData);
-
                 if (opusData && opusData.length > 0) {
                     this.audioBuffers.push(opusData.buffer);
                     this.totalAudioSize += opusData.length;
-
                     if (this.websocket && this.websocket.readyState === WebSocket.OPEN) {
                         try {
                             this.websocket.send(opusData.buffer);
-                            log(`发送Opus帧，大小：${opusData.length}字节`, 'debug');
                         } catch (error) {
                             log(`WebSocket发送错误: ${error.message}`, 'error');
                         }
                     }
                 } else {
-                    log('Opus编码失败，无有效数据返回', 'error');
+                    log('Opus编码失败，未返回有效数据', 'error');
                 }
             } else {
                 if (this.pcmDataBuffer.length > 0) {
@@ -235,96 +199,67 @@ export class AudioRecorder {
         }
     }
 
-    // 开始录音
+    // Start recording
     async start() {
         if (this.isRecording) return false;
-
         try {
-            // 检查是否有WebSocketHandler实例
+            // Check if WebSocketHandler instance exists
-            const { getWebSocketHandler } = await import('../network/websocket.js');
+            const { getWebSocketHandler } = await import('../network/websocket.js?v=0127');
             const wsHandler = getWebSocketHandler();
-
+            // If machine is speaking, send abort message
-            // 如果机器正在说话，发送打断消息
             if (wsHandler && wsHandler.isRemoteSpeaking && wsHandler.currentSessionId) {
-                const abortMessage = {
+                const abortMessage = { session_id: wsHandler.currentSessionId, type: 'abort', reason: 'wake_word_detected' };
-                    session_id: wsHandler.currentSessionId,
-                    type: 'abort',
-                    reason: 'wake_word_detected'
-                };
-
                 if (this.websocket && this.websocket.readyState === WebSocket.OPEN) {
                     this.websocket.send(JSON.stringify(abortMessage));
-                    log('发送打断消息', 'info');
+                    log('已发送中止消息', 'info');
                 }
             }
-
             if (!this.initEncoder()) {
-                log('无法启动录音: Opus编码器初始化失败', 'error');
+                log('无法开始录音: Opus编码器初始化失败', 'error');
                 return false;
             }
-
+            log('请至少录制1-2秒音频以确保收集足够的数据', 'info');
-            log('请至少录制1-2秒钟的音频，确保采集到足够数据', 'info');
+            const stream = await navigator.mediaDevices.getUserMedia({ audio: { echoCancellation: true, noiseSuppression: true, sampleRate: 16000, channelCount: 1 } });
-
-            const stream = await navigator.mediaDevices.getUserMedia({
-                audio: {
-                    echoCancellation: true,
-                    noiseSuppression: true,
-                    sampleRate: 16000,
-                    channelCount: 1
-                }
-            });
-
             this.audioContext = this.getAudioContext();
-
             if (this.audioContext.state === 'suspended') {
                 await this.audioContext.resume();
             }
-
             const processorResult = await this.createAudioProcessor();
             if (!processorResult) {
                 log('无法创建音频处理器', 'error');
                 return false;
             }
-
             this.audioProcessor = processorResult.node;
             this.audioProcessorType = processorResult.type;
-
             this.audioSource = this.audioContext.createMediaStreamSource(stream);
             this.analyser = this.audioContext.createAnalyser();
             this.analyser.fftSize = 2048;
-
             this.audioSource.connect(this.analyser);
             this.audioSource.connect(this.audioProcessor);
-
             this.pcmDataBuffer = new Int16Array();
             this.audioBuffers = [];
             this.totalAudioSize = 0;
             this.isRecording = true;
-
             if (this.audioProcessorType === 'worklet' && this.audioProcessor.port) {
                 this.audioProcessor.port.postMessage({ command: 'start' });
             }
-
+            // Send listening start message
-            // 发送监听开始消息
             if (this.websocket && this.websocket.readyState === WebSocket.OPEN) {
-                log(`发送录音开始消息`, 'info');
+                log(`已发送录音开始消息`, 'info');
             } else {
                 log('WebSocket未连接，无法发送开始消息', 'error');
                 return false;
             }
-
+            // Start visualization
-            // 开始可视化
             if (this.onVisualizerUpdate) {
                 const dataArray = new Uint8Array(this.analyser.frequencyBinCount);
                 this.startVisualization(dataArray);
             }
-
+            // Immediately notify recording start, update button state
-            // 立即通知录音开始，更新按钮状态
             if (this.onRecordingStart) {
                 this.onRecordingStart(0);
             }
-
+            // Start recording timer
-            // 启动录音计时器
             let recordingSeconds = 0;
             this.recordingTimer = setInterval(() => {
                 recordingSeconds += 0.1;
@@ -332,8 +267,7 @@ export class AudioRecorder {
                     this.onRecordingStart(recordingSeconds);
                 }
             }, 100);
-
+            log('已开始PCM直接录音', 'success');
-            log('开始PCM直接录音', 'success');
             return true;
         } catch (error) {
             log(`直接录音启动错误: ${error.message}`, 'error');
@@ -342,15 +276,12 @@ export class AudioRecorder {
         }
     }
 
-    // 开始可视化
+    // Start visualization
     startVisualization(dataArray) {
         const draw = () => {
             this.visualizationRequest = requestAnimationFrame(() => draw());
-
             if (!this.isRecording) return;
-
             this.analyser.getByteFrequencyData(dataArray);
-
             if (this.onVisualizerUpdate) {
                 this.onVisualizerUpdate(dataArray);
             }
@@ -358,52 +289,42 @@ export class AudioRecorder {
         draw();
     }
 
-    // 停止录音
+    // Stop recording
     stop() {
         if (!this.isRecording) return false;
-
         try {
             this.isRecording = false;
-
             if (this.audioProcessor) {
                 if (this.audioProcessorType === 'worklet' && this.audioProcessor.port) {
                     this.audioProcessor.port.postMessage({ command: 'stop' });
                 }
-
                 this.audioProcessor.disconnect();
                 this.audioProcessor = null;
             }
-
             if (this.audioSource) {
                 this.audioSource.disconnect();
                 this.audioSource = null;
             }
-
             if (this.visualizationRequest) {
                 cancelAnimationFrame(this.visualizationRequest);
                 this.visualizationRequest = null;
             }
-
             if (this.recordingTimer) {
                 clearInterval(this.recordingTimer);
                 this.recordingTimer = null;
             }
-
+            // Encode and send remaining data
-            // 编码并发送剩余的数据
             this.encodeAndSendOpus();
-
+            // Send end signal
-            // 发送结束信号
             if (this.websocket && this.websocket.readyState === WebSocket.OPEN) {
                 const emptyOpusFrame = new Uint8Array(0);
                 this.websocket.send(emptyOpusFrame);
                 log('已发送录音停止信号', 'info');
             }
-
             if (this.onRecordingStop) {
                 this.onRecordingStop();
             }
-
+            log('已停止PCM直接录音', 'success');
-            log('停止PCM直接录音', 'success');
             return true;
         } catch (error) {
             log(`直接录音停止错误: ${error.message}`, 'error');
@@ -411,13 +332,13 @@ export class AudioRecorder {
         }
     }
 
-    // 获取分析器
+    // Get analyser
     getAnalyser() {
         return this.analyser;
     }
 }
 
-// 创建单例
+// Create singleton instance
 let audioRecorderInstance = null;
 
 export function getAudioRecorder() {
@@ -426,3 +347,49 @@ export function getAudioRecorder() {
     }
     return audioRecorderInstance;
 }
+
+/**
+ * Check if microphone is available
+ * @returns {Promise<boolean>} Returns true if available, false if not available
+ */
+export async function checkMicrophoneAvailability() {
+    // Check if browser supports getUserMedia API
+    if (!navigator.mediaDevices || !navigator.mediaDevices.getUserMedia) {
+        log('浏览器不支持getUserMedia API', 'warning');
+        return false;
+    }
+    try {
+        // Try to access microphone
+        const stream = await navigator.mediaDevices.getUserMedia({ audio: { echoCancellation: true, noiseSuppression: true, sampleRate: 16000, channelCount: 1 } });
+        // Immediately stop all tracks to release microphone
+        stream.getTracks().forEach(track => track.stop());
+        log('麦克风可用性检查成功', 'success');
+        return true;
+    } catch (error) {
+        log(`麦克风不可用: ${error.message}`, 'warning');
+        return false;
+    }
+}
+
+/**
+ * Check if it is HTTP non-localhost access
+ * @returns {boolean} Returns true if it is HTTP non-localhost access
+ */
+export function isHttpNonLocalhost() {
+    const protocol = window.location.protocol;
+    const hostname = window.location.hostname;
+    // Check if it is HTTP protocol
+    if (protocol !== 'http:') {
+        return false;
+    }
+    // localhost and 127.0.0.1 can use microphone
+    if (hostname === 'localhost' || hostname === '127.0.0.1') {
+        return false;
+    }
+    // Private IP addresses can also use microphone (browser allows)
+    if (hostname.startsWith('192.168.') || hostname.startsWith('10.') || hostname.startsWith('172.')) {
+        return false;
+    }
+    // Other HTTP access is considered non-localhost
+    return true;
+}

main/xiaozhi-server/test/js/core/audio/stream-context.js

@@ -1,5 +1,5 @@
-import BlockingQueue from '../../utils/blocking-queue.js';
+import BlockingQueue from '../../utils/blocking-queue.js?v=0127';
-import { log } from '../../utils/logger.js';
+import { log } from '../../utils/logger.js?v=0127';
 
 // 音频流播放上下文类
 export class StreamingContext {

main/xiaozhi-server/test/js/core/mcp/tools.js

@@ -1,4 +1,4 @@
-import { log } from '../../utils/logger.js';
+import { log } from '../../utils/logger.js?v=0127';
 
 // ==========================================
 // MCP 工具管理逻辑
@@ -24,7 +24,6 @@ export function setWebSocket(ws) {
 export async function initMcpTools() {
     // 加载默认工具数据
     const defaultMcpTools = await fetch("js/config/default-mcp-tools.json").then(res => res.json());
-
     const savedTools = localStorage.getItem('mcpTools');
     if (savedTools) {
         try {
@@ -36,9 +35,11 @@ export async function initMcpTools() {
     } else {
         mcpTools = [...defaultMcpTools];
     }
-
     renderMcpTools();
-    setupMcpEventListeners();
+    // Only setup event listeners if DOM elements exist
+    if (document.getElementById('toggleMcpTools')) {
+        setupMcpEventListeners();
+    }
 }
 
 /**
@@ -47,21 +48,20 @@ export async function initMcpTools() {
 function renderMcpTools() {
     const container = document.getElementById('mcpToolsContainer');
     const countSpan = document.getElementById('mcpToolsCount');
-
+    if (!container) {
+        return; // Container not found, skip rendering
+    }
     if (countSpan) {
         countSpan.textContent = `${mcpTools.length} 个工具`;
     }
-
     if (mcpTools.length === 0) {
         container.innerHTML = '<div style="text-align: center; padding: 30px; color: #999;">暂无工具，点击下方按钮添加新工具</div>';
         return;
     }
-
     container.innerHTML = mcpTools.map((tool, index) => {
         const paramCount = tool.inputSchema.properties ? Object.keys(tool.inputSchema.properties).length : 0;
         const requiredCount = tool.inputSchema.required ? tool.inputSchema.required.length : 0;
         const hasMockResponse = tool.mockResponse && Object.keys(tool.mockResponse).length > 0;
-
         return `
             <div class="mcp-tool-card">
                 <div class="mcp-tool-header">
@@ -96,12 +96,13 @@ function renderMcpTools() {
  */
 function renderMcpProperties() {
     const container = document.getElementById('mcpPropertiesContainer');
-
+    if (!container) {
+        return; // Container not found, skip rendering
+    }
     if (mcpProperties.length === 0) {
         container.innerHTML = '<div style="text-align: center; padding: 20px; color: #999; font-size: 14px;">暂无参数，点击下方按钮添加参数</div>';
         return;
     }
-
     container.innerHTML = mcpProperties.map((prop, index) => `
         <div class="mcp-property-item">
             <div class="mcp-property-header">
@@ -161,12 +162,7 @@ function renderMcpProperties() {
  * 添加参数
  */
 function addMcpProperty() {
-    mcpProperties.push({
+    mcpProperties.push({ name: `param_${mcpProperties.length + 1}`, type: 'string', required: false, description: '' });
-        name: `param_${mcpProperties.length + 1}`,
-        type: 'string',
-        required: false,
-        description: ''
-    });
     renderMcpProperties();
 }
 
@@ -182,9 +178,7 @@ function updateMcpProperty(index, field, value) {
             return;
         }
     }
-
     mcpProperties[index][field] = value;
-
     if (field === 'type' && value !== 'integer' && value !== 'number') {
         delete mcpProperties[index].minimum;
         delete mcpProperties[index].maximum;
@@ -212,25 +206,24 @@ function setupMcpEventListeners() {
     const cancelBtn = document.getElementById('cancelMcpBtn');
     const form = document.getElementById('mcpToolForm');
     const addPropertyBtn = document.getElementById('addMcpPropertyBtn');
-
+    // Return early if required elements don't exist (e.g., in test environment)
+    if (!toggleBtn || !panel || !addBtn || !modal || !closeBtn || !cancelBtn || !form || !addPropertyBtn) {
+        return;
+    }
     toggleBtn.addEventListener('click', () => {
         const isExpanded = panel.classList.contains('expanded');
         panel.classList.toggle('expanded');
-        toggleBtn.textContent = isExpanded ? '展开' : '收起';
+        toggleBtn.textContent = isExpanded ? '收起' : '展开';
     });
-    
     // 确保面板默认展开
     panel.classList.add('expanded');
-
     addBtn.addEventListener('click', () => openMcpModal());
     closeBtn.addEventListener('click', closeMcpModal);
     cancelBtn.addEventListener('click', closeMcpModal);
     addPropertyBtn.addEventListener('click', addMcpProperty);
-
     modal.addEventListener('click', (e) => {
         if (e.target === modal) closeMcpModal();
     });
-
     form.addEventListener('submit', handleMcpSubmit);
 }
 
@@ -243,18 +236,15 @@ function openMcpModal(index = null) {
         alert('WebSocket 已连接，无法编辑工具');
         return;
     }
-
     mcpEditingIndex = index;
     const errorContainer = document.getElementById('mcpErrorContainer');
     errorContainer.innerHTML = '';
-
     if (index !== null) {
         document.getElementById('mcpModalTitle').textContent = '编辑工具';
         const tool = mcpTools[index];
         document.getElementById('mcpToolName').value = tool.name;
         document.getElementById('mcpToolDescription').value = tool.description;
         document.getElementById('mcpMockResponse').value = tool.mockResponse ? JSON.stringify(tool.mockResponse, null, 2) : '';
-
         mcpProperties = [];
         const schema = tool.inputSchema;
         if (schema.properties) {
@@ -275,7 +265,6 @@ function openMcpModal(index = null) {
         document.getElementById('mcpToolForm').reset();
         mcpProperties = [];
     }
-
     renderMcpProperties();
     document.getElementById('mcpToolModal').style.display = 'block';
 }
@@ -298,21 +287,15 @@ function handleMcpSubmit(e) {
     e.preventDefault();
     const errorContainer = document.getElementById('mcpErrorContainer');
     errorContainer.innerHTML = '';
-
     const name = document.getElementById('mcpToolName').value.trim();
     const description = document.getElementById('mcpToolDescription').value.trim();
     const mockResponseText = document.getElementById('mcpMockResponse').value.trim();
-
     // 检查名称重复
-    const isDuplicate = mcpTools.some((tool, index) =>
+    const isDuplicate = mcpTools.some((tool, index) => tool.name === name && index !== mcpEditingIndex);
-        tool.name === name && index !== mcpEditingIndex
-    );
-
     if (isDuplicate) {
         showMcpError('工具名称已存在，请使用不同的名称');
         return;
     }
-
     // 解析模拟返回结果
     let mockResponse = null;
     if (mockResponseText) {
@@ -323,21 +306,13 @@ function handleMcpSubmit(e) {
             return;
         }
     }
-
     // 构建 inputSchema
-    const inputSchema = {
+    const inputSchema = { type: "object", properties: {}, required: [] };
-        type: "object",
-        properties: {},
-        required: []
-    };
-
     mcpProperties.forEach(prop => {
         const propSchema = { type: prop.type };
-
         if (prop.description) {
             propSchema.description = prop.description;
         }
-
         if ((prop.type === 'integer' || prop.type === 'number')) {
             if (prop.minimum !== undefined && prop.minimum !== '') {
                 propSchema.minimum = prop.minimum;
@@ -346,20 +321,15 @@ function handleMcpSubmit(e) {
                 propSchema.maximum = prop.maximum;
             }
         }
-
         inputSchema.properties[prop.name] = propSchema;
-
         if (prop.required) {
             inputSchema.required.push(prop.name);
         }
     });
-
     if (inputSchema.required.length === 0) {
         delete inputSchema.required;
     }
-
     const tool = { name, description, inputSchema, mockResponse };
-
     if (mcpEditingIndex !== null) {
         mcpTools[mcpEditingIndex] = tool;
         log(`已更新工具: ${name}`, 'success');
@@ -367,7 +337,6 @@ function handleMcpSubmit(e) {
         mcpTools.push(tool);
         log(`已添加工具: ${name}`, 'success');
     }
-
     saveMcpTools();
     renderMcpTools();
     closeMcpModal();
@@ -417,11 +386,7 @@ function saveMcpTools() {
  * 获取工具列表
  */
 export function getMcpTools() {
-    return mcpTools.map(tool => ({
+    return mcpTools.map(tool => ({ name: tool.name, description: tool.description, inputSchema: tool.inputSchema }));
-        name: tool.name,
-        description: tool.description,
-        inputSchema: tool.inputSchema
-    }));
 }
 
 /**
@@ -429,20 +394,14 @@ export function getMcpTools() {
  */
 export function executeMcpTool(toolName, toolArgs) {
     const tool = mcpTools.find(t => t.name === toolName);
-
     if (!tool) {
         log(`未找到工具: ${toolName}`, 'error');
-        return {
+        return { success: false, error: `未知工具: ${toolName}` };
-            success: false,
-            error: `未知工具: ${toolName}`
-        };
     }
-
     // 如果有模拟返回结果，使用它
     if (tool.mockResponse) {
         // 替换模板变量
         let responseStr = JSON.stringify(tool.mockResponse);
-
         // 替换 ${paramName} 格式的变量
         if (toolArgs) {
             Object.keys(toolArgs).forEach(key => {
@@ -450,7 +409,6 @@ export function executeMcpTool(toolName, toolArgs) {
                 responseStr = responseStr.replace(regex, toolArgs[key]);
             });
         }
-
         try {
             const response = JSON.parse(responseStr);
             log(`工具 ${toolName} 执行成功，返回模拟结果: ${responseStr}`, 'success');
@@ -460,21 +418,10 @@ export function executeMcpTool(toolName, toolArgs) {
             return tool.mockResponse;
         }
     }
-
     // 没有模拟返回结果，返回默认成功消息
     log(`工具 ${toolName} 执行成功，返回默认结果`, 'success');
-    return {
+    return { success: true, message: `工具 ${toolName} 执行成功`, tool: toolName, arguments: toolArgs };
-        success: true,
-        message: `工具 ${toolName} 执行成功`,
-        tool: toolName,
-        arguments: toolArgs
-    };
 }
 
 // 暴露全局方法供 HTML 内联事件调用
-window.mcpModule = {
+window.mcpModule = { updateMcpProperty, deleteMcpProperty, editMcpTool, deleteMcpTool };
-    updateMcpProperty,
-    deleteMcpProperty,
-    editMcpTool,
-    deleteMcpTool
-};

main/xiaozhi-server/test/js/core/network/ota-connector.js

@@ -1,4 +1,4 @@
-import { log } from '../../utils/logger.js';
+import { log } from '../../utils/logger.js?v=0127';
 
 // WebSocket 连接
 export async function webSocketConnect(otaUrl, config) {

main/xiaozhi-server/test/js/core/network/websocket.js

@@ -1,11 +1,11 @@
 // WebSocket消息处理模块
-import { log } from '../../utils/logger.js';
+import { getConfig, saveConnectionUrls } from '../../config/manager.js?v=0127';
-import { webSocketConnect } from './ota-connector.js';
+import { uiController } from '../../ui/controller.js?v=0127';
-import { getConfig, saveConnectionUrls } from '../../config/manager.js';
+import { log } from '../../utils/logger.js?v=0127';
-import { getAudioPlayer } from '../audio/player.js';
+import { getAudioPlayer } from '../audio/player.js?v=0127';
-import { getAudioRecorder } from '../audio/recorder.js';
+import { getAudioRecorder } from '../audio/recorder.js?v=0127';
-import { getMcpTools, executeMcpTool, setWebSocket as setMcpWebSocket } from '../mcp/tools.js';
+import { executeMcpTool, getMcpTools, setWebSocket as setMcpWebSocket } from '../mcp/tools.js?v=0127';
-import { uiController } from '../../ui/controller.js'
+import { webSocketConnect } from './ota-connector.js?v=0127';
 
 // WebSocket处理器类
 export class WebSocketHandler {
@@ -101,10 +101,10 @@ export class WebSocketHandler {
                 }
 
                 // 触发Live2D情绪动作
-            if (message.emotion) {
+                if (message.emotion) {
-                console.log(`收到情绪消息: emotion=${message.emotion}, text=${message.text}`);
+                    console.log(`收到情绪消息: emotion=${message.emotion}, text=${message.text}`);
-                this.triggerLive2DEmotionAction(message.emotion);
+                    this.triggerLive2DEmotionAction(message.emotion);
-            }
+                }
             }
 
             // 只有当文本不仅仅是表情时，才添加到对话中
@@ -273,6 +273,26 @@ export class WebSocketHandler {
             this.websocket.send(replyMessage);
         } else if (payload.method === 'initialize') {
             log(`收到工具初始化请求: ${JSON.stringify(payload.params)}`, 'info');
+            const replyMessage = JSON.stringify({
+                "session_id": message.session_id || "",
+                "type": "mcp",
+                "payload": {
+                    "jsonrpc": "2.0",
+                    "id": payload.id,
+                    "result": {
+                        "protocolVersion": "2024-11-05",
+                        "capabilities": {
+                            "tools": {}
+                        },
+                        "serverInfo": {
+                            "name": "xiaozhi-web-test",
+                            "version": "2.1.0"
+                        }
+                    }
+                }
+            });
+            log(`回复初始化响应`, 'info');
+            this.websocket.send(replyMessage);
         } else {
             log(`未知的MCP方法: ${payload.method}`, 'warning');
         }
@@ -284,7 +304,6 @@ export class WebSocketHandler {
             let arrayBuffer;
             if (data instanceof ArrayBuffer) {
                 arrayBuffer = data;
-                log(`收到ArrayBuffer音频数据，大小: ${data.byteLength}字节`, 'debug');
             } else if (data instanceof Blob) {
                 arrayBuffer = await data.arrayBuffer();
                 log(`收到Blob音频数据，大小: ${arrayBuffer.byteLength}字节`, 'debug');
@@ -372,7 +391,7 @@ export class WebSocketHandler {
 
         this.websocket.onerror = (error) => {
             log(`WebSocket错误: ${error.message || '未知错误'}`, 'error');
-
+            uiController.addChatMessage(`⚠️ WebSocket错误: ${error.message || '未知错误'}`, false);
             if (this.onConnectionStateChange) {
                 this.onConnectionStateChange(false);
             }

main/xiaozhi-server/test/js/ui/controller.js

@@ -1,10 +1,10 @@
-// UI控制模块
+// UI controller module
-import { loadConfig, saveConfig } from '../config/manager.js';
+import { loadConfig, saveConfig } from '../config/manager.js?v=0127';
-import { getAudioRecorder } from '../core/audio/recorder.js';
+import { getAudioPlayer } from '../core/audio/player.js?v=0127';
-import { getWebSocketHandler } from '../core/network/websocket.js';
+import { getAudioRecorder } from '../core/audio/recorder.js?v=0127';
-import { getAudioPlayer } from '../core/audio/player.js';
+import { getWebSocketHandler } from '../core/network/websocket.js?v=0127';
 
-// UI控制器类
+// UI controller class
 class UIController {
     constructor() {
         this.isEditing = false;
@@ -14,7 +14,7 @@ class UIController {
         this.currentBackgroundIndex = 0;
         this.backgroundImages = ['1.png', '2.png', '3.png'];
 
-        // 绑定方法
+        // Bind methods
         this.init = this.init.bind(this);
         this.initEventListeners = this.initEventListeners.bind(this);
         this.updateDialButton = this.updateDialButton.bind(this);
@@ -25,7 +25,7 @@ class UIController {
         this.switchTab = this.switchTab.bind(this);
     }
 
-    // 初始化
+    // Initialize
     init() {
         console.log('UIController init started');
 
@@ -35,7 +35,7 @@ class UIController {
             this.initVisualizer();
         }
 
-        // 检查连接按钮在初始化时是否存在
+        // Check if connect button exists during initialization
         const connectBtn = document.getElementById('connectBtn');
         console.log('connectBtn during init:', connectBtn);
 
@@ -43,20 +43,20 @@ class UIController {
         this.startAudioStatsMonitor();
         loadConfig();
 
-        // 设置录音器回调
+        // Register recording callback
         const audioRecorder = getAudioRecorder();
         audioRecorder.onRecordingStart = (seconds) => {
             this.updateRecordButtonState(true, seconds);
         };
 
-        // 初始化状态显示
+        // Initialize status display
         this.updateConnectionUI(false);
         this.updateDialButton(false);
 
         console.log('UIController init completed');
     }
 
-    // 初始化可视化器
+    // Initialize visualizer
     initVisualizer() {
         if (this.visualizerCanvas) {
             this.visualizerCanvas.width = this.visualizerCanvas.clientWidth;
@@ -66,9 +66,9 @@ class UIController {
         }
     }
 
-    // 初始化事件监听器
+    // Initialize event listeners
     initEventListeners() {
-        // 设置按钮
+        // Settings button
         const settingsBtn = document.getElementById('settingsBtn');
         if (settingsBtn) {
             settingsBtn.addEventListener('click', () => {
@@ -76,13 +76,13 @@ class UIController {
             });
         }
 
-        // 背景切换按钮
+        // Background switch button
         const backgroundBtn = document.getElementById('backgroundBtn');
         if (backgroundBtn) {
             backgroundBtn.addEventListener('click', this.switchBackground);
         }
 
-        // 拨号按钮
+        // Dial button
         const dialBtn = document.getElementById('dialBtn');
         if (dialBtn) {
             dialBtn.addEventListener('click', () => {
@@ -92,40 +92,40 @@ class UIController {
                 if (isConnected) {
                     wsHandler.disconnect();
                     this.updateDialButton(false);
-                    this.addChatMessage('已断开连接，期待下次再见~😉', false);
+                    this.addChatMessage('Disconnected, see you next time~😊', false);
                 } else {
-                    // 检查OTA地址是否已填写
+                    // Check if OTA URL is filled
                     const otaUrlInput = document.getElementById('otaUrl');
                     if (!otaUrlInput || !otaUrlInput.value.trim()) {
-                        // 如果OTA地址未填写，显示设置弹窗并切换到设备配置页
+                        // If OTA URL is not filled, show settings modal and switch to device tab
                         this.showModal('settingsModal');
                         this.switchTab('device');
-                        this.addChatMessage('请先填写OTA服务器地址', false);
+                        this.addChatMessage('Please fill in OTA server URL', false);
                         return;
                     }
 
-                    // 执行连接操作
+                    // Start connection process
                     this.handleConnect();
                 }
             });
         }
 
-        // 录音按钮
+        // Record button
         const recordBtn = document.getElementById('recordBtn');
         if (recordBtn) {
             recordBtn.addEventListener('click', () => {
                 const audioRecorder = getAudioRecorder();
                 if (audioRecorder.isRecording) {
                     audioRecorder.stop();
-                    // 停止录音时移除录音样式
+                    // Restore record button to normal state
                     recordBtn.classList.remove('recording');
                     recordBtn.querySelector('.btn-text').textContent = '录音';
                 } else {
-                    // 先更新按钮状态为录音中
+                    // Update button state to recording
                     recordBtn.classList.add('recording');
                     recordBtn.querySelector('.btn-text').textContent = '录音中';
 
-                    // 延迟开始录音，确保按钮状态已更新
+                    // Start recording, update button state after delay
                     setTimeout(() => {
                         audioRecorder.start();
                     }, 100);
@@ -133,7 +133,7 @@ class UIController {
             });
         }
 
-        // 消息输入框事件
+        // Chat input event listener
         const chatIpt = document.getElementById('chatIpt');
         if (chatIpt) {
             const wsHandler = getWebSocketHandler();
@@ -148,7 +148,7 @@ class UIController {
             });
         }
 
-        // 关闭按钮
+        // Close button
         const closeButtons = document.querySelectorAll('.close-btn');
         closeButtons.forEach(btn => {
             btn.addEventListener('click', (e) => {
@@ -163,7 +163,7 @@ class UIController {
             });
         });
 
-        // 设置标签页切换
+        // Settings tab switch
         const tabBtns = document.querySelectorAll('.tab-btn');
         tabBtns.forEach(btn => {
             btn.addEventListener('click', (e) => {
@@ -171,7 +171,7 @@ class UIController {
             });
         });
 
-        // 点击模态框外部关闭
+        // Click modal background to close
         const modals = document.querySelectorAll('.modal');
         modals.forEach(modal => {
             modal.addEventListener('click', (e) => {
@@ -184,7 +184,7 @@ class UIController {
             });
         });
 
-        // 添加MCP工具按钮
+        // Add MCP tool button
         const addMCPToolBtn = document.getElementById('addMCPToolBtn');
         if (addMCPToolBtn) {
             addMCPToolBtn.addEventListener('click', (e) => {
@@ -193,10 +193,10 @@ class UIController {
             });
         }
 
-        // 连接按钮和取消按钮已被移除，功能已集成到拨号按钮中
+        // Connect button and send button are not removed, can be added to dial button later
     }
 
-    // 更新连接状态UI
+    // Update connection status UI
     updateConnectionUI(isConnected) {
         const connectionStatus = document.getElementById('connectionStatus');
         const statusDot = document.querySelector('.status-dot');
@@ -216,7 +216,7 @@ class UIController {
         }
     }
 
-    // 更新拨号按钮状态
+    // Update dial button state
     updateDialButton(isConnected) {
         const dialBtn = document.getElementById('dialBtn');
         const recordBtn = document.getElementById('recordBtn');
@@ -225,39 +225,44 @@ class UIController {
             if (isConnected) {
                 dialBtn.classList.add('dial-active');
                 dialBtn.querySelector('.btn-text').textContent = '挂断';
-                // 更新拨号按钮图标为挂断图标
+                // Update dial button icon to hang up icon
                 dialBtn.querySelector('svg').innerHTML = `
                     <path d="M12,9C10.4,9 9,10.4 9,12C9,13.6 10.4,15 12,15C13.6,15 15,13.6 15,12C15,10.4 13.6,9 12,9M12,17C9.2,17 7,14.8 7,12C7,9.2 9.2,7 12,7C14.8,7 17,9.2 17,12C17,14.8 14.8,17 12,17M12,4.5C7,4.5 2.7,7.6 1,12C2.7,16.4 7,19.5 12,19.5C17,19.5 21.3,16.4 23,12C21.3,7.6 17,4.5 12,4.5Z"/>
                 `;
             } else {
                 dialBtn.classList.remove('dial-active');
                 dialBtn.querySelector('.btn-text').textContent = '拨号';
-                // 恢复拨号按钮图标
+                // Restore dial button icon
                 dialBtn.querySelector('svg').innerHTML = `
                     <path d="M6.62,10.79C8.06,13.62 10.38,15.94 13.21,17.38L15.41,15.18C15.69,14.9 16.08,14.82 16.43,14.93C17.55,15.3 18.75,15.5 20,15.5A1,1 0 0,1 21,16.5V20A1,1 0 0,1 20,21A17,17 0 0,1 3,4A1,1 0 0,1 4,3H7.5A1,1 0 0,1 8.5,4C8.5,5.25 8.7,6.45 9.07,7.57C9.18,7.92 9.1,8.31 8.82,8.59L6.62,10.79Z"/>
                 `;
             }
         }
 
-        // 更新录音按钮状态
+        // Update record button state
         if (recordBtn) {
-            if (isConnected) {
+            const microphoneAvailable = window.microphoneAvailable !== false;
+            if (isConnected && microphoneAvailable) {
                 recordBtn.disabled = false;
                 recordBtn.title = '开始录音';
-                // 确保录音按钮恢复到正常状态
+                // Restore record button to normal state
                 recordBtn.querySelector('.btn-text').textContent = '录音';
                 recordBtn.classList.remove('recording');
             } else {
                 recordBtn.disabled = true;
-                recordBtn.title = '请先连接服务器';
+                if (!microphoneAvailable) {
-                // 确保录音按钮恢复到正常状态
+                    recordBtn.title = window.isHttpNonLocalhost ? '当前由于是http访问，无法录音，只能用文字交互' : '麦克风不可用';
+                } else {
+                    recordBtn.title = '请先连接服务器';
+                }
+                // Restore record button to normal state
                 recordBtn.querySelector('.btn-text').textContent = '录音';
                 recordBtn.classList.remove('recording');
             }
         }
     }
 
-    // 更新录音按钮状态
+    // Update record button state
     updateRecordButtonState(isRecording, seconds = 0) {
         const recordBtn = document.getElementById('recordBtn');
         if (recordBtn) {
@@ -268,11 +273,37 @@ class UIController {
                 recordBtn.querySelector('.btn-text').textContent = '录音';
                 recordBtn.classList.remove('recording');
             }
-            recordBtn.disabled = false;
+            // Only enable button when microphone is available
+            recordBtn.disabled = window.microphoneAvailable === false;
         }
     }
 
-    // 添加聊天消息
+    /**
+     * Update microphone availability state
+     * @param {boolean} isAvailable - Whether microphone is available
+     * @param {boolean} isHttpNonLocalhost - Whether it is HTTP non-localhost access
+     */
+    updateMicrophoneAvailability(isAvailable, isHttpNonLocalhost) {
+        const recordBtn = document.getElementById('recordBtn');
+        if (!recordBtn) return;
+        if (!isAvailable) {
+            // Disable record button
+            recordBtn.disabled = true;
+            // Update button text and title
+            recordBtn.querySelector('.btn-text').textContent = '录音';
+            recordBtn.title = isHttpNonLocalhost ? '当前由于是http访问，无法录音，只能用文字交互' : '麦克风不可用';
+
+        } else {
+            // If connected, enable record button
+            const wsHandler = getWebSocketHandler();
+            if (wsHandler && wsHandler.isConnected()) {
+                recordBtn.disabled = false;
+                recordBtn.title = '开始录音';
+            }
+        }
+    }
+
+    // Add chat message
     addChatMessage(content, isUser = false) {
         const chatStream = document.getElementById('chatStream');
         if (!chatStream) return;
@@ -282,11 +313,11 @@ class UIController {
         messageDiv.innerHTML = `<div class="message-bubble">${content}</div>`;
         chatStream.appendChild(messageDiv);
 
-        // 自动滚动到底部
+        // Scroll to bottom
         chatStream.scrollTop = chatStream.scrollHeight;
     }
 
-    // 切换背景
+    // Switch background
     switchBackground() {
         this.currentBackgroundIndex = (this.currentBackgroundIndex + 1) % this.backgroundImages.length;
         const backgroundContainer = document.querySelector('.background-container');
@@ -295,7 +326,7 @@ class UIController {
         }
     }
 
-    // 显示模态框
+    // Show modal
     showModal(modalId) {
         const modal = document.getElementById(modalId);
         if (modal) {
@@ -303,7 +334,7 @@ class UIController {
         }
     }
 
-    // 隐藏模态框
+    // Hide modal
     hideModal(modalId) {
         const modal = document.getElementById(modalId);
         if (modal) {
@@ -311,16 +342,16 @@ class UIController {
         }
     }
 
-    // 切换标签页
+    // Switch tab
     switchTab(tabName) {
-        // 移除所有标签页的active类
+        // Remove active class from all tabs
         const tabBtns = document.querySelectorAll('.tab-btn');
         const tabContents = document.querySelectorAll('.tab-content');
 
         tabBtns.forEach(btn => btn.classList.remove('active'));
         tabContents.forEach(content => content.classList.remove('active'));
 
-        // 激活选中的标签页
+        // Activate selected tab
         const activeTabBtn = document.querySelector(`[data-tab="${tabName}"]`);
         const activeTabContent = document.getElementById(`${tabName}Tab`);
 
@@ -330,24 +361,34 @@ class UIController {
         }
     }
 
-    // 连接成功后开始对话
+    // Start AI chat session after connection
     startAIChatSession() {
-        this.addChatMessage('连接成功，开始聊天吧~🙂', false);
+        this.addChatMessage('连接成功，开始聊天吧~😊', false);
-        // 开启录音
+        // Check microphone availability and show error messages if needed
-        const recordBtn = document.getElementById('recordBtn');
+        if (!window.microphoneAvailable) {
-        if (recordBtn) {
+            if (window.isHttpNonLocalhost) {
-            recordBtn.click();
+                this.addChatMessage('⚠️ 当前由于是http访问，无法录音，只能用文字交互', false);
+            } else {
+                this.addChatMessage('⚠️ 麦克风不可用，请检查权限设置，只能用文字交互', false);
+            }
+        }
+        // Start recording only if microphone is available
+        if (window.microphoneAvailable) {
+            const recordBtn = document.getElementById('recordBtn');
+            if (recordBtn) {
+                recordBtn.click();
+            }
         }
     }
 
-    // 处理连接按钮点击
+    // Handle connect button click
     async handleConnect() {
         console.log('handleConnect called');
 
-        // 确保切换到设备配置标签页
+        // Switch to device settings tab
         this.switchTab('device');
 
-        // 等待DOM更新
+        // Wait for DOM update
         await new Promise(resolve => setTimeout(resolve, 50));
 
         const otaUrlInput = document.getElementById('otaUrl');
@@ -362,7 +403,7 @@ class UIController {
         const otaUrl = otaUrlInput.value;
         console.log('otaUrl value:', otaUrl);
 
-        // 更新拨号按钮状态为连接中
+        // Update dial button state to connecting
         const dialBtn = document.getElementById('dialBtn');
         if (dialBtn) {
             dialBtn.classList.add('dial-active');
@@ -370,7 +411,7 @@ class UIController {
             dialBtn.disabled = true;
         }
 
-        // 显示连接中消息
+        // Show connecting message
         this.addChatMessage('正在连接服务器...', false);
 
         const chatIpt = document.getElementById('chatIpt');
@@ -380,41 +421,51 @@ class UIController {
 
         try {
 
-            // 获取WebSocket处理器
+            // Get WebSocket handler instance
             const wsHandler = getWebSocketHandler();
+
+            // Register connection state callback BEFORE connecting
+            wsHandler.onConnectionStateChange = (isConnected) => {
+                this.updateConnectionUI(isConnected);
+                this.updateDialButton(isConnected);
+            };
+
+            // Register chat message callback BEFORE connecting
+            wsHandler.onChatMessage = (text, isUser) => {
+                this.addChatMessage(text, isUser);
+            };
+
+            // Register record button state callback BEFORE connecting
+            wsHandler.onRecordButtonStateChange = (isRecording) => {
+                const recordBtn = document.getElementById('recordBtn');
+                if (recordBtn) {
+                    if (isRecording) {
+                        recordBtn.classList.add('recording');
+                        recordBtn.querySelector('.btn-text').textContent = '录音中';
+                    } else {
+                        recordBtn.classList.remove('recording');
+                        recordBtn.querySelector('.btn-text').textContent = '录音';
+                    }
+                }
+            };
+
             const isConnected = await wsHandler.connect();
 
             if (isConnected) {
+                // Check microphone availability (check again after connection)
+                const { checkMicrophoneAvailability } = await import('../core/audio/recorder.js?v=0127');
+                const micAvailable = await checkMicrophoneAvailability();
 
-                // 设置连接状态回调
+                if (!micAvailable) {
-                wsHandler.onConnectionStateChange = (isConnected) => {
+                    const isHttp = window.isHttpNonLocalhost;
-                    this.updateConnectionUI(isConnected);
+                    if (isHttp) {
-                    this.updateDialButton(isConnected);
+                        this.addChatMessage('⚠️ 当前由于是http访问，无法录音，只能用文字交互', false);
-                };
-
-                // 设置聊天消息回调
-                wsHandler.onChatMessage = (text, isUser) => {
-                    this.addChatMessage(text, isUser);
-                };
-
-                // 设置录音按钮状态回调
-                wsHandler.onRecordButtonStateChange = (isRecording) => {
-                    const recordBtn = document.getElementById('recordBtn');
-                    if (recordBtn) {
-                        if (isRecording) {
-                            recordBtn.classList.add('recording');
-                            recordBtn.querySelector('.btn-text').textContent = '录音中';
-                        } else {
-                            recordBtn.classList.remove('recording');
-                            recordBtn.querySelector('.btn-text').textContent = '录音';
-                        }
                     }
-                };
+                    // Update global state
+                    window.microphoneAvailable = false;
+                }
 
-                // 连接成功
+                // Update dial button state
-                this.addChatMessage('OTA连接成功，正在建立WebSocket连接...', false);
-
-                // 更新拨号按钮状态
                 const dialBtn = document.getElementById('dialBtn');
                 if (dialBtn) {
                     dialBtn.disabled = false;
@@ -434,14 +485,14 @@ class UIController {
                 name: error.name
             });
 
-            // 显示错误消息
+            // Show error message
             const errorMessage = error.message.includes('Cannot set properties of null')
-                ? '连接失败：请刷新页面重试'
+                ? '连接失败：请检查设备连接'
                 : `连接失败: ${error.message}`;
 
             this.addChatMessage(errorMessage, false);
 
-            // 恢复拨号按钮状态
+            // Restore dial button state
             const dialBtn = document.getElementById('dialBtn');
             if (dialBtn) {
                 dialBtn.disabled = false;
@@ -452,7 +503,7 @@ class UIController {
         }
     }
 
-    // 添加MCP工具
+    // Add MCP tool
     addMCPTool() {
         const mcpToolsList = document.getElementById('mcpToolsList');
         if (!mcpToolsList) return;
@@ -471,7 +522,7 @@ class UIController {
         mcpToolsList.appendChild(toolDiv);
     }
 
-    // 移除MCP工具
+    // Remove MCP tool
     removeMCPTool(toolId) {
         const toolElement = document.getElementById(toolId);
         if (toolElement) {
@@ -479,24 +530,24 @@ class UIController {
         }
     }
 
-    // 更新音频统计信息
+    // Update audio statistics display
     updateAudioStats() {
         const audioPlayer = getAudioPlayer();
         if (!audioPlayer) return;
 
         const stats = audioPlayer.getAudioStats();
-        // 这里可以添加音频统计的UI更新逻辑
+        // Here can add audio statistics UI update logic
     }
 
-    // 启动音频统计监控
+    // Start audio statistics monitor
     startAudioStatsMonitor() {
-        // 每100ms更新一次音频统计
+        // Update audio statistics every 100ms
         this.audioStatsTimer = setInterval(() => {
             this.updateAudioStats();
         }, 100);
     }
 
-    // 停止音频统计监控
+    // Stop audio statistics monitor
     stopAudioStatsMonitor() {
         if (this.audioStatsTimer) {
             clearInterval(this.audioStatsTimer);
@@ -504,7 +555,7 @@ class UIController {
         }
     }
 
-    // 绘制音频可视化效果
+    // Draw audio visualizer waveform
     drawVisualizer(dataArray) {
         if (!this.visualizerContext || !this.visualizerCanvas) return;
 
@@ -518,7 +569,7 @@ class UIController {
         for (let i = 0; i < dataArray.length; i++) {
             barHeight = dataArray[i] / 2;
 
-            // 创建渐变色：从紫色到蓝色到青色
+            // Create gradient color: from purple to blue to green
             const gradient = this.visualizerContext.createLinearGradient(0, 0, 0, this.visualizerCanvas.height);
             gradient.addColorStop(0, '#8e44ad');
             gradient.addColorStop(0.5, '#3498db');
@@ -530,21 +581,21 @@ class UIController {
         }
     }
 
-    // 更新会话状态UI
+    // Update session status UI
     updateSessionStatus(isSpeaking) {
-        // 这里可以添加会话状态的UI更新逻辑
+        // Here can add session status UI update logic
-        // 例如：更新Live2D角色的表情或状态指示器
+        // For example: update Live2D model's mouth movement status
     }
 
-    // 更新会话表情
+    // Update session emotion
     updateSessionEmotion(emoji) {
-        // 这里可以添加表情更新的逻辑
+        // Here can add emotion update logic
-        // 例如：在状态指示器中显示表情
+        // For example: display emoji in status indicator
     }
 }
 
-// 创建全局实例
+// Create singleton instance
 export const uiController = new UIController();
 
-// 导出类供其他模块使用
+// Export class for module usage
-export { UIController };
+export { UIController };

main/xiaozhi-server/test/test_page.html

@@ -5,7 +5,7 @@
     <meta charset="UTF-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
     <title>小智服务器测试页面</title>
-    <link rel="stylesheet" href="css/test_page.css">
+    <link rel="stylesheet" href="css/test_page.css?v=0127">
     <script>
         // 检测是否使用file://协议打开
         if (window.location.protocol === 'file:') {
@@ -143,7 +143,8 @@
                                 </div>
                                 <div class="config-item">
                                     <label for="deviceName">设备名称:</label>
-                                    <input type="text" id="deviceName" value="Web测试设备" maxlength="50" placeholder="deviceName">
+                                    <input type="text" id="deviceName" value="Web测试设备" maxlength="50"
+                                        placeholder="deviceName">
                                 </div>
                             </div>
                         </div>
@@ -237,23 +238,23 @@
     </div>
 
     <!-- 背景加载 -->
-    <script src="js/ui/background-load.js"></script>
+    <script src="js/ui/background-load.js?v=0127"></script>
 
     <!-- PIXI.js 2D渲染引擎 -->
-    <script src="js/live2d/pixi.js"></script>
+    <script src="js/live2d/pixi.js?v=0127"></script>
 
     <!-- Live2D Cubism 4.0 SDK -->
-    <script src="js/live2d/live2dcubismcore.min.js"></script>
+    <script src="js/live2d/live2dcubismcore.min.js?v=0127"></script>
-    <script src="js/live2d/cubism4.min.js"></script>
+    <script src="js/live2d/cubism4.min.js?v=0127"></script>
 
     <!-- Live2D 管理器 -->
-    <script src="js/live2d/live2d.js"></script>
+    <script src="js/live2d/live2d.js?v=0127"></script>
 
     <!-- Opus解码库 -->
-    <script src="js/utils/libopus.js"></script>
+    <script src="js/utils/libopus.js?v=0127"></script>
 
     <!-- 主应用入口 -->
-    <script type="module" src="js/app.js"></script>
+    <script type="module" src="js/app.js?v=0127"></script>
 
     <!-- 全局错误处理 -->
     <script>