Merge branch 'newsnow' into add_local_tts_change_voice

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

@@ -43,7 +43,6 @@ class TTSProviderBase(ABC):
         self.tts_text_buff = []
         self.punctuations = (
             "。",
-            ".",
             "？",
             "?",
             "！",
@@ -59,7 +58,6 @@ class TTSProviderBase(ABC):
             "、",
             ",",
             "。",
-            ".",
             "？",
             "?",
             "！",
@@ -171,7 +169,7 @@ class TTSProviderBase(ABC):
             )
         )
         # 对于单句的文本，进行分段处理
-        segments = re.split(r'([。！？!?；;\n])', content_detail)
+        segments = re.split(r"([。！？!?；;\n])", content_detail)
         for seg in segments:
             self.tts_text_queue.put(
                 TTSMessageDTO(

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

@@ -37,7 +37,9 @@ class TTSProvider(TTSProviderBase):
         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)
+        model_key_msg = check_model_key("TTS", self.access_token)
+        if model_key_msg:
+            logger.bind(tag=TAG).error(model_key_msg)
 
     async def text_to_speak(self, text, output_file):
         request_json = {

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

@@ -94,8 +94,9 @@ class TTSProvider(TTSProviderBase):
         self.format = config.get("response_format", "wav")
         self.audio_file_type = config.get("response_format", "wav")
         self.api_key = config.get("api_key", "YOUR_API_KEY")
-        have_key = check_model_key("FishSpeech TTS", self.api_key)
-        if not have_key:
+        model_key_msg = check_model_key("FishSpeech TTS", self.api_key)
+        if model_key_msg:
+            logger.bind(tag=TAG).error(model_key_msg)
             return
         self.normalize = str(config.get("normalize", True)).lower() in (
             "true",

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

@@ -12,6 +12,8 @@ from core.utils.util import check_model_key
 from core.providers.tts.base import TTSProviderBase
 from core.handle.abortHandle import handleAbortMessage
 from core.providers.tts.dto.dto import SentenceType, ContentType, InterfaceType
+from asyncio import Task
+
 
 TAG = __name__
 logger = setup_logging()
@@ -141,6 +143,7 @@ class TTSProvider(TTSProviderBase):
         super().__init__(config, delete_audio_file)
         self.ws = None
         self.interface_type = InterfaceType.DUAL_STREAM
+        self._monitor_task = None  # 监听任务引用
         self.appId = config.get("appid")
         self.access_token = config.get("access_token")
         self.cluster = config.get("cluster")
@@ -157,7 +160,9 @@ class TTSProvider(TTSProviderBase):
         self.opus_encoder = opus_encoder_utils.OpusEncoderUtils(
             sample_rate=16000, channels=1, frame_size_ms=60
         )
-        check_model_key("TTS", self.access_token)
+        model_key_msg = check_model_key("TTS", self.access_token)
+        if model_key_msg:
+            logger.bind(tag=TAG).error(model_key_msg)
 
     async def open_audio_channels(self, conn):
         try:
@@ -202,6 +207,10 @@ class TTSProvider(TTSProviderBase):
                 if message.sentence_type == SentenceType.FIRST:
                     # 初始化参数
                     try:
+                        if not getattr(self.conn, "sentence_id", None): 
+                            self.conn.sentence_id = uuid.uuid4().hex
+                            logger.bind(tag=TAG).info(f"自动生成新的 会话ID: {self.conn.sentence_id}")
+
                         logger.bind(tag=TAG).info("开始启动TTS会话...")
                         future = asyncio.run_coroutine_threadsafe(
                             self.start_session(self.conn.sentence_id),
@@ -264,10 +273,9 @@ class TTSProvider(TTSProviderBase):
         try:
             # 建立新连接
             if self.ws is None:
-                await handleAbortMessage(self.conn)
-                logger.bind(tag=TAG).error(f"WebSocket连接不存在，终止发送文本")
+                logger.bind(tag=TAG).warning(f"WebSocket连接不存在，终止发送文本")
                 return
-            
+
             #  过滤Markdown
             filtered_text = MarkdownCleaner.clean_markdown(text)
 
@@ -287,6 +295,25 @@ class TTSProvider(TTSProviderBase):
     async def start_session(self, session_id):
         logger.bind(tag=TAG).info(f"开始会话～～{session_id}")
         try:
+            task = self._monitor_task
+            if (
+                task is not None
+                and isinstance(task, Task)
+                and not task.done()
+            ):
+                logger.bind(tag=TAG).info("等待上一个监听任务结束...")
+                if self.ws is not None:
+                    logger.bind(tag=TAG).info("强制关闭上一个WebSocket连接以唤醒监听任务...")
+                    try:
+                        await self.ws.close()
+                    except Exception as e:
+                        logger.bind(tag=TAG).warning(f"关闭上一个ws异常: {e}")
+                    self.ws = None
+                try:
+                    await asyncio.wait_for(task, timeout=8)
+                except Exception as e:
+                    logger.bind(tag=TAG).warning(f"等待监听任务异常: {e}")
+                self._monitor_task = None
             # 建立新连接
             await self._ensure_connection()
 
@@ -457,6 +484,8 @@ class TTSProvider(TTSProviderBase):
                 except:
                     pass
                 self.ws = None
+            # 监听任务退出时清理引用
+            self._monitor_task = None
 
     async def send_event(
         self,

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

@@ -166,7 +166,9 @@ class TTSProvider(TTSProviderBase):
                 ) as resp:
 
                     if resp.status != 200:
-                        logger.error(f"TTS请求失败: {resp.status}, {await resp.text()}")
+                        logger.bind(tag=TAG).error(
+                            f"TTS请求失败: {resp.status}, {await resp.text()}"
+                        )
                         self.tts_audio_queue.put((SentenceType.LAST, [], None))
                         return
 
@@ -229,7 +231,7 @@ class TTSProvider(TTSProviderBase):
                         self._process_before_stop_play_files()
 
         except Exception as e:
-            logger.error(f"TTS请求异常: {e}")
+            logger.bind(tag=TAG).error(f"TTS请求异常: {e}")
             self.tts_audio_queue.put((SentenceType.LAST, [], None))
 
     def to_tts(self, text: str) -> list:
@@ -263,7 +265,7 @@ class TTSProvider(TTSProviderBase):
                 self.api_url, params=params, headers=headers, timeout=5
             ) as response:
                 if response.status_code != 200:
-                    logger.error(
+                    logger.bind(tag=TAG).error(
                         f"TTS请求失败: {response.status_code}, {response.text}"
                     )
                     return []
@@ -299,5 +301,5 @@ class TTSProvider(TTSProviderBase):
                 return opus_datas
 
         except Exception as e:
-            logger.error(f"TTS请求异常: {e}")
+            logger.bind(tag=TAG).error(f"TTS请求异常: {e}")
             return []

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

@@ -25,7 +25,9 @@ class TTSProvider(TTSProviderBase):
         self.speed = float(speed) if speed else 1.0
 
         self.output_file = config.get("output_dir", "tmp/")
-        check_model_key("TTS", self.api_key)
+        model_key_msg = check_model_key("TTS", self.api_key)
+        if model_key_msg:
+            logger.bind(tag=TAG).error(model_key_msg)
 
     async def text_to_speak(self, text, output_file):
         headers = {