fixed:设置sentence_start成延迟发送，要不然跟语音无法对应

config.yaml

@@ -53,6 +53,7 @@ LLM:
     url: https://api.deepseek.com
     api_key: 你的deepseek api key
   ChatGLMLLM:
+    # glm-4-flash 是免费的，但是还是需要注册填写api_key的
     # 可在这里找到你的api key https://bigmodel.cn/usercenter/proj-mgmt/apikeys
     model_name: glm-4-flash
     url: https://open.bigmodel.cn/api/paas/v4/

core/handle/audioHandle.py

@@ -35,11 +35,13 @@ async def handleAudioMessage(conn, audio):
         conn.asr_audio.clear()
         conn.reset_vad_states()
 
+
 async def startToChat(conn, text):
     # 异步发送 stt 信息
-    asyncio.create_task(
+    stt_task = asyncio.create_task(
         schedule_with_interrupt(0, send_stt_message(conn, text))
     )
+    conn.scheduled_tasks.append(stt_task)
     conn.executor.submit(conn.chat, text)
 
 
@@ -52,7 +54,10 @@ async def sendAudioMessage(conn, audios, duration, text):
         conn.tts_start_speak_time = time.time()
 
     # 发送 sentence_start（每个音频文件之前发送一次）
-    await send_tts_message(conn, "sentence_start", text)
+    sentence_task = asyncio.create_task(
+        schedule_with_interrupt(base_delay, send_tts_message(conn, "sentence_start", text))
+    )
+    conn.scheduled_tasks.append(sentence_task)
 
     conn.tts_duration += duration
 
@@ -60,10 +65,6 @@ async def sendAudioMessage(conn, audios, duration, text):
     for idx, opus_packet in enumerate(audios):
         await conn.websocket.send(opus_packet)
 
-        # 每个音频文件发送结束时，发送 sentence_end
-        if idx == len(audios) - 1:
-            await send_tts_message(conn, "sentence_end", text)
-
     if conn.llm_finish_task and text == conn.tts_last_text:
         stop_duration = conn.tts_duration - (time.time() - conn.tts_start_speak_time)
         stop_task = asyncio.create_task(
@@ -71,6 +72,7 @@ async def sendAudioMessage(conn, audios, duration, text):
         )
         conn.scheduled_tasks.append(stop_task)
 
+
 async def send_tts_message(conn, state, text=None):
     """发送 TTS 状态消息"""
     message = {
@@ -85,6 +87,7 @@ async def send_tts_message(conn, state, text=None):
     if state == "stop":
         conn.clearSpeakStatus()
 
+
 async def send_stt_message(conn, text):
     """发送 STT 状态消息"""
     stt_text = get_string_no_punctuation_or_emoji(text)

core/utils/llm.py

@@ -12,6 +12,13 @@ logger = logging.getLogger(__name__)
 
 
 class LLM(ABC):
+    def __init__(self, config):
+        api_key = config.get("api_key")
+        # 如果api_key包含中文“你”
+        if "你" in api_key:
+            logger.error("你还没配置LLM的密钥，请在配置文件中配置密钥，否则无法正常工作")
+        pass
+
     @abstractmethod
     def response(self, session_id, dialogue):
         """LLM response generator"""
@@ -20,6 +27,7 @@ class LLM(ABC):
 
 class DeepSeekLLM(LLM):
     def __init__(self, config):
+        super().__init__(config)
         self.model_name = config.get("model_name")
         self.api_key = config.get("api_key")
         self.base_url = config.get("url")
@@ -46,6 +54,7 @@ class DeepSeekLLM(LLM):
 
 class ChatGLMLLM(LLM):
     def __init__(self, config):
+        super().__init__(config)
         self.model_name = config.get("model_name")
         self.api_key = config.get("api_key")
         self.base_url = config.get("url")
@@ -70,6 +79,7 @@ class ChatGLMLLM(LLM):
 
 class AliLLM(LLM):
     def __init__(self, config):
+        super().__init__(config)
         self.model_name = config.get("model_name")
         self.api_key = config.get("api_key")
         self.base_url = config.get("base_url")
@@ -94,6 +104,7 @@ class AliLLM(LLM):
 
 class DifyLLM(LLM):
     def __init__(self, config):
+        super().__init__(config)
         self.api_key = config["api_key"]
         self.base_url = config.get("base_url", "https://api.dify.ai/v1").rstrip('/')