update:优化唤醒词缓存文件

* update:增加私有唤醒答复文件

* update:优化唤醒词缓存文件

.gitignore

@@ -145,6 +145,7 @@ tmp
 .history
 .DS_Store
 main/xiaozhi-server/data
+main/xiaozhi-server/config/assets/wakeup_words.*
 main/manager-web/node_modules
 .config.yaml
 .secrets.yaml

main/xiaozhi-server/config.yaml

@@ -57,6 +57,14 @@ delete_audio: true
 close_connection_no_voice_time: 120
 # TTS请求超时时间(秒)
 tts_timeout: 10
+# 开启唤醒词加速
+enable_wakeup_words_response_cache: true
+# 开场是否回复唤醒词
+enable_greeting: true
+# 说完话是否开启提示音
+enable_stop_tts_notify: false
+# 说完话是否开启提示音，音效地址
+stop_tts_notify_voice: "config/assets/tts_notify.mp3"
 
 CMD_exit:
   - "退出"
@@ -514,3 +522,16 @@ module_test:
     - "你好，请介绍一下你自己"
     - "What's the weather like today?"
     - "请用100字概括量子计算的基本原理和应用前景"
+
+# 唤醒词，用于识别唤醒词还是讲话内容
+wakeup_words:
+  - "你好小智"
+  - "你好小志"
+  - "小爱同学"
+  - "你好小鑫"
+  - "你好小新"
+  - "小美同学"
+  - "小龙小龙"
+  - "喵喵同学"
+  - "小滨小滨"
+  - "小冰小冰"

main/xiaozhi-server/core/connection.py

@@ -9,7 +9,7 @@ import traceback
 import threading
 import websockets
 from typing import Dict, Any
-import plugins_func.loadplugins
+from plugins_func.loadplugins import auto_import_modules
 from config.logger import setup_logging
 from core.utils.dialogue import Message, Dialogue
 from core.handle.textHandle import handleTextMessage
@@ -25,6 +25,8 @@ from core.utils.auth_code_gen import AuthCodeGenerator
 
 TAG = __name__
 
+auto_import_modules('plugins_func.functions')
+
 
 class TTSException(RuntimeError):
     pass
@@ -109,11 +111,15 @@ class ConnectionHandler:
 
             # 进行认证
             await self.auth.authenticate(self.headers)
-
             device_id = self.headers.get("device-id", None)
-            self.memory.init_memory(device_id, self.llm)
-            self.intent.set_llm(self.llm)
 
+            # 认证通过,继续处理
+            self.websocket = ws
+            self.session_id = str(uuid.uuid4())
+
+            self.welcome_msg = self.config["xiaozhi"]
+            self.welcome_msg["session_id"] = self.session_id
+            await self.websocket.send(json.dumps(self.welcome_msg))
             # Load private configuration if device_id is provided
             bUsePrivateConfig = self.config.get("use_private_config", False)
             self.logger.bind(tag=TAG).info(f"bUsePrivateConfig: {bUsePrivateConfig}, device_id: {device_id}")
@@ -141,17 +147,8 @@ class ConnectionHandler:
                     self.private_config = None
                     raise
 
-            # 认证通过,继续处理
-            self.websocket = ws
-            self.session_id = str(uuid.uuid4())
-
-            self.welcome_msg = self.config["xiaozhi"]
-            self.welcome_msg["session_id"] = self.session_id
-            await self.websocket.send(json.dumps(self.welcome_msg))
-
             # 异步初始化
-            await self.loop.run_in_executor(None, self._initialize_components)
+            self.executor.submit(self._initialize_components)
-
             # tts 消化线程
             tts_priority = threading.Thread(target=self._tts_priority_thread, daemon=True)
             tts_priority.start()
@@ -187,16 +184,26 @@ class ConnectionHandler:
             await handleAudioMessage(self, message)
 
     def _initialize_components(self):
+        """加载插件"""
+        self.func_handler = FunctionHandler(self)
+
+        """加载提示词"""
         self.prompt = self.config["prompt"]
         if self.private_config:
             self.prompt = self.private_config.private_config.get("prompt", self.prompt)
-
-        self.client_ip_info = get_ip_info(self.client_ip)
-        self.logger.bind(tag=TAG).info(f"Client ip info: {self.client_ip_info}")
-        self.prompt = self.prompt + f"\n我在:{self.client_ip_info}"
         self.dialogue.put(Message(role="system", content=self.prompt))
 
-        self.func_handler = FunctionHandler(self)
+        """加载记忆"""
+        device_id = self.headers.get("device-id", None)
+        self.memory.init_memory(device_id, self.llm)
+        self.intent.set_llm(self.llm)
+
+        """加载位置信息"""
+        self.client_ip_info = get_ip_info(self.client_ip)
+        if self.client_ip_info is not None and "city" in self.client_ip_info:
+            self.logger.bind(tag=TAG).info(f"Client ip info: {self.client_ip_info}")
+            self.prompt = self.prompt + f"\nuser location:{self.client_ip_info}"
+            self.dialogue.update_system_message(self.prompt)
 
     def change_system_prompt(self, prompt):
         self.prompt = prompt

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

@@ -1,8 +1,72 @@
 import json
 from config.logger import setup_logging
+from core.handle.sendAudioHandle import send_stt_message
+from core.utils.util import remove_punctuation_and_length
+import shutil
+import asyncio
+import os
+import random
+import time
 
 logger = setup_logging()
 
+WAKEUP_CONFIG = {"dir": "config/assets/", "file_name": "wakeup_words", "create_time": time.time(), "refresh_time": 10,
+                 "words": ["很高兴见到你", "你好啊", "我们又见面了", "最近可好?", "很高兴再次和你谈话", "在干嘛"]}
+
 
 async def handleHelloMessage(conn):
     await conn.websocket.send(json.dumps(conn.welcome_msg))
+
+
+async def checkWakeupWords(conn, text):
+    enable_wakeup_words_response_cache = conn.config["enable_wakeup_words_response_cache"]
+    """是否开启唤醒词加速"""
+    if not enable_wakeup_words_response_cache:
+        return False
+    """检查是否是唤醒词"""
+    _, text = remove_punctuation_and_length(text)
+    if text in conn.config.get("wakeup_words"):
+        await send_stt_message(conn, text)
+        conn.tts_first_text_index = 0
+        conn.tts_last_text_index = 0
+        conn.llm_finish_task = True
+
+        file = getWakeupWordFile(WAKEUP_CONFIG["file_name"])
+        if file is None:
+            asyncio.create_task(wakeupWordsResponse(conn))
+            return False
+        opus_packets, duration = conn.tts.audio_to_opus_data(file)
+        conn.audio_play_queue.put((opus_packets, text, 0))
+        if time.time() - WAKEUP_CONFIG["create_time"] > WAKEUP_CONFIG["refresh_time"]:
+            asyncio.create_task(wakeupWordsResponse(conn))
+        return True
+    return False
+
+
+def getWakeupWordFile(file_name):
+    for file in os.listdir(WAKEUP_CONFIG["dir"]):
+        if "my_"+file_name in file:
+            return f"config/assets/{file}"
+
+    """查找config/assets/目录下名称为wakeup_words的文件"""
+    for file in os.listdir(WAKEUP_CONFIG["dir"]):
+        if file_name in file:
+            return f"config/assets/{file}"
+    return None
+
+
+async def wakeupWordsResponse(conn):
+    """唤醒词响应"""
+    wakeup_word = random.choice(WAKEUP_CONFIG["words"])
+    result = conn.llm.response_no_stream(conn.config["prompt"], wakeup_word)
+    tts_file = await asyncio.to_thread(conn.tts.to_tts, result)
+    if tts_file is not None and os.path.exists(tts_file):
+        file_type = os.path.splitext(tts_file)[1]
+        if file_type:
+            file_type = file_type.lstrip('.')
+        old_file = getWakeupWordFile("my_" +WAKEUP_CONFIG["file_name"])
+        if old_file is not None:
+            os.remove(old_file)
+        """将文件挪到"wakeup_words.mp3"""
+        shutil.move(tts_file, WAKEUP_CONFIG["dir"] + "my_" +WAKEUP_CONFIG["file_name"] + "." + file_type)
+        WAKEUP_CONFIG["create_time"] = time.time()

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

@@ -2,6 +2,7 @@ from config.logger import setup_logging
 import json
 import uuid
 from core.handle.sendAudioHandle import send_stt_message
+from core.handle.helloHandle import checkWakeupWords
 from core.utils.util import remove_punctuation_and_length
 
 TAG = __name__
@@ -12,6 +13,10 @@ async def handle_user_intent(conn, text):
     # 检查是否有明确的退出命令
     if await check_direct_exit(conn, text):
         return True
+    # 检查是否是唤醒词
+    if await checkWakeupWords(conn, text):
+        return True
+
     if conn.use_function_call_mode:
         # 使用支持function calling的聊天方法,不再进行意图分析
         return False
@@ -35,6 +40,7 @@ async def check_direct_exit(conn, text):
     return False
 
 
+
 async def analyze_intent_with_llm(conn, text):
     """使用LLM分析用户意图"""
     if not hasattr(conn, 'intent') or not conn.intent:

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

@@ -7,12 +7,26 @@ from core.utils.util import remove_punctuation_and_length, get_string_no_punctua
 TAG = __name__
 logger = setup_logging()
 
+
 async def sendAudioMessage(conn, audios, text, text_index=0):
     # 发送句子开始消息
     if text_index == conn.tts_first_text_index:
         logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
     await send_tts_message(conn, "sentence_start", text)
 
+    # 播放音频
+    await sendAudio(conn, audios)
+
+    await send_tts_message(conn, "sentence_end", text)
+
+    # 发送结束消息（如果是最后一个文本）
+    if conn.llm_finish_task and text_index == conn.tts_last_text_index:
+        await send_tts_message(conn, 'stop', None)
+        if conn.close_after_chat:
+            await conn.close()
+
+# 播放音频
+async def sendAudio(conn, audios):
     # 流控参数优化
     original_frame_duration = 60  # 原始帧时长（毫秒）
     adjusted_frame_duration = int(original_frame_duration * 0.8)  # 缩短20%
@@ -42,13 +56,6 @@ async def sendAudioMessage(conn, audios, text, text_index=0):
     if compensation > 0:
         await asyncio.sleep(compensation)
 
-    await send_tts_message(conn, "sentence_end", text)
-
-    # 发送结束消息（如果是最后一个文本）
-    if conn.llm_finish_task and text_index == conn.tts_last_text_index:
-        await send_tts_message(conn, 'stop', None)
-        if conn.close_after_chat:
-            await conn.close()
 
 async def send_tts_message(conn, state, text=None):
     """发送 TTS 状态消息"""
@@ -60,10 +67,20 @@ async def send_tts_message(conn, state, text=None):
     if text is not None:
         message["text"] = text
 
-    await conn.websocket.send(json.dumps(message))
+    # TTS播放结束
     if state == "stop":
+        # 播放提示音
+        tts_notify = conn.config.get("enable_stop_tts_notify", False)
+        if tts_notify:
+            stop_tts_notify_voice = conn.config.get("stop_tts_notify_voice", "config/assets/tts_notify.mp3")
+            audios, duration = conn.tts.audio_to_opus_data(stop_tts_notify_voice)
+            await sendAudio(conn, audios)
+        # 清除服务端讲话状态
         conn.clearSpeakStatus()
 
+    # 发送消息到客户端
+    await conn.websocket.send(json.dumps(message))
+
 
 async def send_stt_message(conn, text):
     """发送 STT 状态消息"""

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

@@ -2,7 +2,9 @@ from config.logger import setup_logging
 import json
 from core.handle.abortHandle import handleAbortMessage
 from core.handle.helloHandle import handleHelloMessage
+from core.utils.util import remove_punctuation_and_length
 from core.handle.receiveAudioHandle import startToChat, handleAudioMessage
+from core.handle.sendAudioHandle import send_stt_message, send_tts_message
 from core.handle.iotHandle import handleIotDescriptors, handleIotStatus
 
 TAG = __name__
@@ -38,7 +40,21 @@ async def handleTextMessage(conn, message):
                 conn.client_have_voice = False
                 conn.asr_audio.clear()
                 if "text" in msg_json:
-                    await startToChat(conn, msg_json["text"])
+                    text = msg_json["text"]
+                    _, text = remove_punctuation_and_length(text)
+
+                    # 识别是否是唤醒词
+                    is_wakeup_words = text in conn.config.get("wakeup_words")
+                    # 是否开启唤醒词回复
+                    enable_greeting = conn.config.get("enable_greeting", True)
+
+                    if is_wakeup_words and not enable_greeting:
+                        # 如果是唤醒词，且关闭了唤醒词回复，就不用回答
+                        await send_stt_message(conn, text)
+                        await send_tts_message(conn, "stop", None)
+                    else:
+                        # 否则需要LLM对文字内容进行答复
+                        await startToChat(conn, text)
         elif msg_json["type"] == "iot":
             if "descriptors" in msg_json:
                 await handleIotDescriptors(conn, msg_json["descriptors"])

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

@@ -36,7 +36,7 @@ class TTSProviderBase(ABC):
 
             return tmp_file
         except Exception as e:
-            logger.bind(tag=TAG).info(f"Failed to generate TTS file: {e}")
+            logger.bind(tag=TAG).error(f"Failed to generate TTS file: {e}")
             return None
 
     @abstractmethod

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

@@ -73,9 +73,7 @@ def get_ip_info(ip_addr):
         resp = requests.get(url).json()
 
         ip_info = {
-            "city": resp.get("cityName"),
+            "city": resp.get("cityName")
-            "region": resp.get("regionName"), 
-            "country": resp.get("countryName")
         }
         return ip_info
     except Exception as e:

main/xiaozhi-server/plugins_func/loadplugins.py

@@ -23,5 +23,3 @@ def auto_import_modules(package_name):
         full_module_name = f"{package_name}.{module_name}"
         importlib.import_module(full_module_name)
         #logger.bind(tag=TAG).info(f"模块 '{full_module_name}' 已加载")
-
-auto_import_modules('plugins_func.functions')