合并main分支

.github/ISSUE_TEMPLATE/bug_report.md

@@ -9,26 +9,24 @@ assignees: ''
 ## 🐛 问题描述
 <!-- 清晰简洁地描述问题是什么 -->
 
-## 🔍 复现步骤
-<!-- 详细描述复现问题的步骤 -->
+## 🖥️ 环境信息
+- 部署方式: 全模块部署 还是 单Server部署
+- 版本号: 例如 0.3.x
+
+## 🔍 告诉我们，应该怎么复现这个问题
+<!-- 这个很重要，方便我们快速定位 -->
 1. 打开 '...'
 2. 点击 '...'
 3. 滚动到 '...'
 4. 看到错误
 
-## 🤔 预期行为
+## 🤔 你原本希望是怎么样的
 <!-- 简要描述预期的正确行为 -->
 
-## 😯 截图
+## 😯 提供一些截图
 <!-- 如果适用，添加问题的截图 -->
-
-## 🖥️ 环境信息
-- 操作系统: [例如 Windows 10]
-- 浏览器: [例如 Chrome 89]
-- 项目版本: [例如 1.0.0]
-- Python版本: [例如 3.9.13]
-- Jdk版本：[例如 java 21.0.5 2024-10-15 LTS]
-- Nodejs版本：[例如 v20.14.0]
+1. 比如日志截图，越多越好
+2. 比如界面反应
 
 ## 📋 其他信息
 <!-- 在此添加关于此问题的任何其他上下文信息 -->

.github/workflows/docker-image.yml

@@ -58,7 +58,7 @@ jobs:
           file: Dockerfile-server
           push: true
           tags: |
-            ${{ env.IS_VERSION == 'true' && format('ghcr.io/{0}:server_{1}\nghcr.io/{0}:server_latest', github.repository, env.VERSION) || format('ghcr.io/{0}:server_latest', github.repository) }}
+            ${{ 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,linux/arm64
 
       # 构建 manager-api 镜像
@@ -69,5 +69,5 @@ jobs:
           file: Dockerfile-web
           push: true
           tags: |
-            ${{ env.IS_VERSION == 'true' && format('ghcr.io/{0}:web_{1}\nghcr.io/{0}:web_latest', github.repository, env.VERSION) || format('ghcr.io/{0}:web_latest', github.repository) }}
+            ${{ 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,linux/arm64

.gitignore

@@ -162,9 +162,14 @@ main/xiaozhi-server/models/sherpa-onnx*
 /main/xiaozhi-server/asr-models/iic/SenseVoiceSmall/
 /models/SenseVoiceSmall/model.pt
 my_wakeup_words.mp3
+!main/xiaozhi-server/config/assets/bind_code.wav
+!main/xiaozhi-server/config/assets/bind_not_found.wav
+!main/xiaozhi-server/config/assets/bind_code/*.wav
+!main/xiaozhi-server/config/assets/max_output_size.wav
 main/manager-api/.vscode
 # Ignore webpack cache directory
 main/manager-web/.webpack_cache/
 main/xiaozhi-server/mysql
 uploadfile
 *.json
+.vscode

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

@@ -1,18 +1,22 @@
-from config.logger import setup_logging
 import time
+import copy
 from core.utils.util import remove_punctuation_and_length
 from core.handle.sendAudioHandle import send_stt_message
 from core.handle.intentHandler import handle_user_intent
+from core.utils.output_counter import check_device_output_limit
+from core.handle.reportHandle import enqueue_asr_report
+from core.utils.util import audio_to_data
 
 TAG = __name__
-logger = setup_logging()
 
 
 async def handleAudioMessage(conn, audio):
-    if not conn.asr_server_receive:
-        logger.bind(tag=TAG).debug(f"前期数据处理中，暂停接收")
+    if conn.vad is None:
         return
-    if conn.client_listen_mode == "auto":
+    if not conn.asr_server_receive:
+        conn.logger.bind(tag=TAG).debug(f"前期数据处理中，暂停接收")
+        return
+    if conn.client_listen_mode == "auto" or conn.client_listen_mode == "realtime":
         have_voice = conn.vad.is_vad(conn, audio)
     else:
         have_voice = conn.client_have_voice
@@ -35,12 +39,13 @@ async def handleAudioMessage(conn, audio):
         if len(conn.asr_audio) < 15:
             conn.asr_server_receive = True
         else:
-            text, file_path = await conn.asr.speech_to_text(
-                conn.asr_audio, conn.session_id
-            )
-            logger.bind(tag=TAG).info(f"识别文本: {text}")
+            text, _ = await conn.asr.speech_to_text(conn.asr_audio, conn.session_id)
+            conn.logger.bind(tag=TAG).info(f"识别文本: {text}")
             text_len, _ = remove_punctuation_and_length(text)
             if text_len > 0:
+                # 使用自定义模块进行上报
+                enqueue_asr_report(conn, text, copy.deepcopy(conn.asr_audio))
+
                 await startToChat(conn, text)
             else:
                 conn.asr_server_receive = True
@@ -49,6 +54,18 @@ async def handleAudioMessage(conn, audio):
 
 
 async def startToChat(conn, text):
+    if conn.need_bind:
+        await check_bind_device(conn)
+        return
+
+    # 如果当日的输出字数大于限定的字数
+    if conn.max_output_size > 0:
+        if check_device_output_limit(
+            conn.headers.get("device-id"), conn.max_output_size
+        ):
+            await max_out_size(conn)
+            return
+
     # 首先进行意图分析
     intent_handled = await handle_user_intent(conn, text)
 
@@ -59,7 +76,7 @@ async def startToChat(conn, text):
 
     # 意图未被处理，继续常规聊天流程
     await send_stt_message(conn, text)
-    if conn.use_function_call_mode:
+    if conn.intent_type == "function_call":
         # 使用支持function calling的聊天方法
         conn.executor.submit(conn.chat_with_function_calling, text)
     else:
@@ -71,8 +88,8 @@ async def no_voice_close_connect(conn):
         conn.client_no_voice_last_time = time.time() * 1000
     else:
         no_voice_time = time.time() * 1000 - conn.client_no_voice_last_time
-        close_connection_no_voice_time = conn.config.get(
-            "close_connection_no_voice_time", 120
+        close_connection_no_voice_time = int(
+            conn.config.get("close_connection_no_voice_time", 120)
         )
         if (
             not conn.close_after_chat
@@ -81,7 +98,65 @@ async def no_voice_close_connect(conn):
             conn.close_after_chat = True
             conn.client_abort = False
             conn.asr_server_receive = False
-            prompt = (
-                "请你以“时间过得真快”未来头，用富有感情、依依不舍的话来结束这场对话吧。"
-            )
+            end_prompt = conn.config.get("end_prompt", {})
+            if end_prompt and end_prompt.get("enable", True) is False:
+                conn.logger.bind(tag=TAG).info("结束对话，无需发送结束提示语")
+                await conn.close()
+                return
+            prompt = end_prompt.get("prompt")
+            if not prompt:
+                prompt = "请你以“时间过得真快”未来头，用富有感情、依依不舍的话来结束这场对话吧。！"
             await startToChat(conn, prompt)
+
+
+async def max_out_size(conn):
+    text = "不好意思，我现在有点事情要忙，明天这个时候我们再聊，约好了哦！明天不见不散，拜拜！"
+    await send_stt_message(conn, text)
+    conn.tts_first_text_index = 0
+    conn.tts_last_text_index = 0
+    conn.llm_finish_task = True
+    file_path = "config/assets/max_output_size.wav"
+    opus_packets, _ = audio_to_data(file_path)
+    conn.audio_play_queue.put((opus_packets, text, 0))
+    conn.close_after_chat = True
+
+
+async def check_bind_device(conn):
+    if conn.bind_code:
+        # 确保bind_code是6位数字
+        if len(conn.bind_code) != 6:
+            conn.logger.bind(tag=TAG).error(f"无效的绑定码格式: {conn.bind_code}")
+            text = "绑定码格式错误，请检查配置。"
+            await send_stt_message(conn, text)
+            return
+
+        text = f"请登录控制面板，输入{conn.bind_code}，绑定设备。"
+        await send_stt_message(conn, text)
+        conn.tts_first_text_index = 0
+        conn.tts_last_text_index = 6
+        conn.llm_finish_task = True
+
+        # 播放提示音
+        music_path = "config/assets/bind_code.wav"
+        opus_packets, _ = audio_to_data(music_path)
+        conn.audio_play_queue.put((opus_packets, text, 0))
+
+        # 逐个播放数字
+        for i in range(6):  # 确保只播放6位数字
+            try:
+                digit = conn.bind_code[i]
+                num_path = f"config/assets/bind_code/{digit}.wav"
+                num_packets, _ = audio_to_data(num_path)
+                conn.audio_play_queue.put((num_packets, None, i + 1))
+            except Exception as e:
+                conn.logger.bind(tag=TAG).error(f"播放数字音频失败: {e}")
+                continue
+    else:
+        text = f"没有找到该设备的版本信息，请正确配置 OTA地址，然后重新编译固件。"
+        await send_stt_message(conn, text)
+        conn.tts_first_text_index = 0
+        conn.tts_last_text_index = 0
+        conn.llm_finish_task = True
+        music_path = "config/assets/bind_not_found.wav"
+        opus_packets, _ = audio_to_data(music_path)
+        conn.audio_play_queue.put((opus_packets, text, 0))

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

@@ -10,40 +10,62 @@ from pydub import AudioSegment
 from core.providers.tts.dto.dto import TTSMessageDTO, MsgType, SentenceType
 from core.utils.util import check_model_key
 from core.providers.tts.base import TTSProviderBase
+from config.logger import setup_logging
+
+TAG = __name__
+logger = setup_logging()
 
 
 class TTSProvider(TTSProviderBase):
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
-        self.appid = config.get("appid")
+        if config.get("appid"):
+            self.appid = int(config.get("appid"))
+        else:
+            self.appid = ""
         self.access_token = config.get("access_token")
         self.cluster = config.get("cluster")
-        self.voice = config.get("voice")
+
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice")
+
+        # 处理空字符串的情况
+        speed_ratio = config.get("speed_ratio", "1.0")
+        volume_ratio = config.get("volume_ratio", "1.0")
+        pitch_ratio = config.get("pitch_ratio", "1.0")
+
+        self.speed_ratio = float(speed_ratio) if speed_ratio else 1.0
+        self.volume_ratio = float(volume_ratio) if volume_ratio else 1.0
+        self.pitch_ratio = float(pitch_ratio) if pitch_ratio else 1.0
+
         self.api_url = config.get("api_url")
         self.authorization = config.get("authorization")
         self.header = {"Authorization": f"{self.authorization}{self.access_token}"}
         check_model_key("TTS", self.access_token)
 
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, u_id, text, is_last_text=False, is_first_text=False):
         tmp_file = self.generate_filename()
         request_json = {
             "app": {
                 "appid": f"{self.appid}",
-                "token": "access_token",
-                "cluster": self.cluster
-            },
-            "user": {
-                "uid": "1"
+                "token": self.access_token,
+                "cluster": self.cluster,
             },
+            "user": {"uid": "1"},
             "audio": {
                 "voice_type": self.voice,
                 "encoding": "wav",
-                "speed_ratio": 1.0,
-                "volume_ratio": 1.0,
-                "pitch_ratio": 1.0,
+                "speed_ratio": self.speed_ratio,
+                "volume_ratio": self.volume_ratio,
+                "pitch_ratio": self.pitch_ratio,
             },
             "request": {
                 "reqid": str(uuid.uuid4()),
@@ -51,18 +73,22 @@ class TTSProvider(TTSProviderBase):
                 "text_type": "plain",
                 "operation": "query",
                 "with_frontend": 1,
-                "frontend_type": "unitTson"
-            }
+                "frontend_type": "unitTson",
+            },
         }
 
         try:
-            resp = requests.post(self.api_url, json.dumps(request_json), headers=self.header)
+            resp = requests.post(
+                self.api_url, json.dumps(request_json), headers=self.header
+            )
             if "data" in resp.json():
                 data = resp.json()["data"]
                 file_to_save = open(tmp_file, "wb")
                 file_to_save.write(base64.b64decode(data))
             else:
-                raise Exception(f"{__name__} status_code: {resp.status_code} response: {resp.content}")
+                raise Exception(
+                    f"{__name__} status_code: {resp.status_code} response: {resp.content}"
+                )
         except Exception as e:
             raise Exception(f"{__name__} error: {e}")
         # 使用 pydub 读取临时文件

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

@@ -16,7 +16,10 @@ class TTSProvider(TTSProviderBase):
         self.appid = config.get("appid")
         self.secret_id = config.get("secret_id")
         self.secret_key = config.get("secret_key")
-        self.voice = config.get("voice")
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = int(config.get("voice"))
         self.api_url = "https://tts.tencentcloudapi.com"  # 正确的API端点
         self.region = config.get("region")
         self.output_file = config.get("output_dir")
@@ -25,35 +28,36 @@ class TTSProvider(TTSProviderBase):
         """生成鉴权请求头"""
         # 获取当前UTC时间戳
         timestamp = int(time.time())
-        
+
         # 使用UTC时间计算日期
-        utc_date = datetime.fromtimestamp(timestamp, tz=timezone.utc).strftime('%Y-%m-%d')
-        
+        utc_date = datetime.fromtimestamp(timestamp, tz=timezone.utc).strftime(
+            "%Y-%m-%d"
+        )
+
         # 服务名称必须是 "tts"
         service = "tts"
-        
+
         # 拼接凭证范围
         credential_scope = f"{utc_date}/{service}/tc3_request"
-        
+
         # 使用TC3-HMAC-SHA256签名方法
         algorithm = "TC3-HMAC-SHA256"
-        
+
         # 构建规范请求字符串
         http_request_method = "POST"
         canonical_uri = "/"
         canonical_querystring = ""
-        
+
         # 请求头必须包含host和content-type，且按字典序排列
         canonical_headers = (
-            f"content-type:application/json\n"
-            f"host:tts.tencentcloudapi.com\n"
+            f"content-type:application/json\n" f"host:tts.tencentcloudapi.com\n"
         )
         signed_headers = "content-type;host"
-        
+
         # 请求体哈希值
         payload = json.dumps(request_body)
-        payload_hash = hashlib.sha256(payload.encode('utf-8')).hexdigest()
-        
+        payload_hash = hashlib.sha256(payload.encode("utf-8")).hexdigest()
+
         # 构建规范请求字符串
         canonical_request = (
             f"{http_request_method}\n"
@@ -63,10 +67,12 @@ class TTSProvider(TTSProviderBase):
             f"{signed_headers}\n"
             f"{payload_hash}"
         )
-        
+
         # 计算规范请求的哈希值
-        hashed_canonical_request = hashlib.sha256(canonical_request.encode('utf-8')).hexdigest()
-        
+        hashed_canonical_request = hashlib.sha256(
+            canonical_request.encode("utf-8")
+        ).hexdigest()
+
         # 构建待签名字符串
         string_to_sign = (
             f"{algorithm}\n"
@@ -74,19 +80,19 @@ class TTSProvider(TTSProviderBase):
             f"{credential_scope}\n"
             f"{hashed_canonical_request}"
         )
-        
+
         # 计算签名密钥
-        secret_date = self._hmac_sha256(f"TC3{self.secret_key}".encode('utf-8'), utc_date)
+        secret_date = self._hmac_sha256(
+            f"TC3{self.secret_key}".encode("utf-8"), utc_date
+        )
         secret_service = self._hmac_sha256(secret_date, service)
         secret_signing = self._hmac_sha256(secret_service, "tc3_request")
-        
+
         # 计算签名
         signature = hmac.new(
-            secret_signing, 
-            string_to_sign.encode('utf-8'), 
-            hashlib.sha256
+            secret_signing, string_to_sign.encode("utf-8"), hashlib.sha256
         ).hexdigest()
-        
+
         # 构建授权头
         authorization = (
             f"{algorithm} "
@@ -94,7 +100,7 @@ class TTSProvider(TTSProviderBase):
             f"SignedHeaders={signed_headers}, "
             f"Signature={signature}"
         )
-        
+
         # 构建请求头
         headers = {
             "Content-Type": "application/json",
@@ -104,19 +110,22 @@ class TTSProvider(TTSProviderBase):
             "X-TC-Timestamp": str(timestamp),
             "X-TC-Version": "2019-08-23",
             "X-TC-Region": self.region,
-            "X-TC-Language": "zh-CN"
+            "X-TC-Language": "zh-CN",
         }
-        
+
         return headers
-    
+
     def _hmac_sha256(self, key, msg):
         """HMAC-SHA256加密"""
         if isinstance(msg, str):
-            msg = msg.encode('utf-8')
+            msg = msg.encode("utf-8")
         return hmac.new(key, msg, hashlib.sha256).digest()
 
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         # 构建请求体
@@ -129,19 +138,23 @@ class TTSProvider(TTSProviderBase):
         try:
             # 获取请求头（每次请求都重新生成，以确保时间戳和签名是最新的）
             headers = self._get_auth_headers(request_json)
-            
+
             # 发送请求
-            resp = requests.post(self.api_url, json.dumps(request_json), headers=headers)
-            
+            resp = requests.post(
+                self.api_url, json.dumps(request_json), headers=headers
+            )
+
             # 检查响应
             if resp.status_code == 200:
                 response_data = resp.json()
-                
+
                 # 检查是否成功
                 if response_data.get("Response", {}).get("Error") is not None:
                     error_info = response_data["Response"]["Error"]
-                    raise Exception(f"API返回错误: {error_info['Code']}: {error_info['Message']}")
-                
+                    raise Exception(
+                        f"API返回错误: {error_info['Code']}: {error_info['Message']}"
+                    )
+
                 # 提取音频数据
                 audio_data = response_data["Response"].get("Audio")
                 if audio_data:
@@ -151,6 +164,8 @@ class TTSProvider(TTSProviderBase):
                 else:
                     raise Exception(f"{__name__}: 没有返回音频数据: {response_data}")
             else:
-                raise Exception(f"{__name__} status_code: {resp.status_code} response: {resp.content}")
+                raise Exception(
+                    f"{__name__} status_code: {resp.status_code} response: {resp.content}"
+                )
         except Exception as e:
-            raise Exception(f"{__name__} error: {e}")
+            raise Exception(f"{__name__} error: {e}")

main/xiaozhi-server/plugins_func/functions/play_music.py

@@ -12,9 +12,9 @@ from core.providers.tts.dto.dto import TTSMessageDTO, MsgType
 from core.utils import p3
 from core.handle.sendAudioHandle import send_stt_message
 from plugins_func.register import register_function, ToolType, ActionResponse, Action
+from core.utils.dialogue import Message
 
 TAG = __name__
-logger = setup_logging()
 
 MUSIC_CACHE = {}
 
@@ -22,13 +22,13 @@ play_music_function_desc = {
     "type": "function",
     "function": {
         "name": "play_music",
-        "description": "唱歌、听歌、播放音乐方法。比如用户说播放音乐，参数为：random，比如用户说播放两只老虎，参数为：两只老虎",
+        "description": "唱歌、听歌、播放音乐的方法。",
         "parameters": {
             "type": "object",
             "properties": {
                 "song_name": {
                     "type": "string",
-                    "description": "歌曲名称，如果没有指定具体歌名则为'random'",
+                    "description": "歌曲名称，如果用户没有指定具体歌名则为'random', 明确指定的时返回音乐的名字 示例: ```用户:播放两只老虎\n参数：两只老虎``` ```用户:播放音乐 \n参数：random ```",
                 }
             },
             "required": ["song_name"],
@@ -46,7 +46,7 @@ def play_music(conn, song_name: str):
 
         # 检查事件循环状态
         if not conn.loop.is_running():
-            logger.bind(tag=TAG).error("事件循环未运行，无法提交任务")
+            conn.logger.bind(tag=TAG).error("事件循环未运行，无法提交任务")
             return ActionResponse(
                 action=Action.RESPONSE, result="系统繁忙", response="请稍后再试"
             )
@@ -60,9 +60,9 @@ def play_music(conn, song_name: str):
         def handle_done(f):
             try:
                 f.result()  # 可在此处理成功逻辑
-                logger.bind(tag=TAG).info("播放完成")
+                conn.logger.bind(tag=TAG).info("播放完成")
             except Exception as e:
-                logger.bind(tag=TAG).error(f"播放失败: {e}")
+                conn.logger.bind(tag=TAG).error(f"播放失败: {e}")
 
         future.add_done_callback(handle_done)
 
@@ -70,7 +70,7 @@ def play_music(conn, song_name: str):
             action=Action.NONE, result="指令已接收", response="正在为您播放音乐"
         )
     except Exception as e:
-        logger.bind(tag=TAG).error(f"处理音乐意图错误: {e}")
+        conn.logger.bind(tag=TAG).error(f"处理音乐意图错误: {e}")
         return ActionResponse(
             action=Action.RESPONSE, result=str(e), response="播放音乐时出错了"
         )
@@ -151,7 +151,7 @@ async def handle_music_command(conn, text):
 
     """处理音乐播放指令"""
     clean_text = re.sub(r"[^\w\s]", "", text).strip()
-    logger.bind(tag=TAG).debug(f"检查是否是音乐命令: {clean_text}")
+    conn.logger.bind(tag=TAG).debug(f"检查是否是音乐命令: {clean_text}")
 
     # 尝试匹配具体歌名
     if os.path.exists(MUSIC_CACHE["music_dir"]):
@@ -166,7 +166,7 @@ async def handle_music_command(conn, text):
         if potential_song:
             best_match = _find_best_match(potential_song, MUSIC_CACHE["music_files"])
             if best_match:
-                logger.bind(tag=TAG).info(f"找到最匹配的歌曲: {best_match}")
+                conn.logger.bind(tag=TAG).info(f"找到最匹配的歌曲: {best_match}")
                 await play_local_music(conn, specific_file=best_match)
                 return True
     # 检查是否是通用播放音乐命令
@@ -174,12 +174,31 @@ async def handle_music_command(conn, text):
     return True
 
 
+def _get_random_play_prompt(song_name):
+    """生成随机播放引导语"""
+    # 移除文件扩展名
+    clean_name = os.path.splitext(song_name)[0]
+    prompts = [
+        f"正在为您播放，{clean_name}",
+        f"请欣赏歌曲，{clean_name}",
+        f"即将为您播放，{clean_name}",
+        f"为您带来，{clean_name}",
+        f"让我们聆听，{clean_name}",
+        f"接下来请欣赏，{clean_name}",
+        f"为您献上，{clean_name}",
+    ]
+    # 直接使用random.choice，不设置seed
+    return random.choice(prompts)
+
+
 async def play_local_music(conn, specific_file=None):
     global MUSIC_CACHE
     """播放本地音乐文件"""
     try:
         if not os.path.exists(MUSIC_CACHE["music_dir"]):
-            logger.bind(tag=TAG).error(f"音乐目录不存在: " + MUSIC_CACHE["music_dir"])
+            conn.logger.bind(tag=TAG).error(
+                f"音乐目录不存在: " + MUSIC_CACHE["music_dir"]
+            )
             return
 
         # 确保路径正确性
@@ -188,23 +207,33 @@ async def play_local_music(conn, specific_file=None):
             music_path = os.path.join(MUSIC_CACHE["music_dir"], specific_file)
         else:
             if not MUSIC_CACHE["music_files"]:
-                logger.bind(tag=TAG).error("未找到MP3音乐文件")
+                conn.logger.bind(tag=TAG).error("未找到MP3音乐文件")
                 return
             selected_music = random.choice(MUSIC_CACHE["music_files"])
             music_path = os.path.join(MUSIC_CACHE["music_dir"], selected_music)
 
         if not os.path.exists(music_path):
-            logger.bind(tag=TAG).error(f"选定的音乐文件不存在: {music_path}")
+            conn.logger.bind(tag=TAG).error(f"选定的音乐文件不存在: {music_path}")
             return
-        text = f"正在播放{selected_music}"
+        text = _get_random_play_prompt(selected_music)
         await send_stt_message(conn, text)
+        conn.dialogue.put(Message(role="assistant", content=text))
         conn.tts_first_text_index = 0
         conn.tts_last_text_index = 0
+
+        tts_file = await asyncio.to_thread(conn.tts.to_tts, text)
+        if tts_file is not None and os.path.exists(tts_file):
+            conn.tts_last_text_index = 1
+            opus_packets, _ = conn.tts.audio_to_opus_data(tts_file)
+            conn.audio_play_queue.put((opus_packets, None, 0))
+            os.remove(tts_file)
+
         conn.llm_finish_task = True
+
         if music_path.endswith(".p3"):
-            opus_packets, duration = p3.decode_opus_from_file(music_path)
+            opus_packets, _ = p3.decode_opus_from_file(music_path)
         else:
-            opus_packets, duration = conn.tts.audio_to_opus_data(music_path)
+            opus_packets, _ = conn.tts.audio_to_opus_data(music_path)
         conn.tts.tts_audio_queue.put(
             TTSMessageDTO(
                 u_id=conn.u_id,
@@ -226,5 +255,5 @@ async def play_local_music(conn, specific_file=None):
         )
 
     except Exception as e:
-        logger.bind(tag=TAG).error(f"播放音乐失败: {str(e)}")
-        logger.bind(tag=TAG).error(f"详细错误: {traceback.format_exc()}")
+        conn.logger.bind(tag=TAG).error(f"播放音乐失败: {str(e)}")
+        conn.logger.bind(tag=TAG).error(f"详细错误: {traceback.format_exc()}")