fix: 文本重复发送

main/xiaozhi-server/core/connection.py

@@ -132,6 +132,8 @@ class ConnectionHandler:
 
         # tts相关变量
         self.sentence_id = None
+        # 处理TTS响应没有文本返回
+        self.tts_MessageText = ""
 
         # iot相关变量
         self.iot_descriptors = {}
@@ -785,8 +787,10 @@ class ConnectionHandler:
             if not bHasError:
                 # 如需要大模型先处理一轮，添加相关处理后的日志情况
                 if len(response_message) > 0:
+                    text_buff = "".join(response_message)
+                    self.tts_MessageText = text_buff
                     self.dialogue.put(
-                        Message(role="assistant", content="".join(response_message))
+                        Message(role="assistant", content=text_buff)
                     )
                 response_message.clear()
                 self.logger.bind(tag=TAG).debug(
@@ -809,8 +813,10 @@ class ConnectionHandler:
 
         # 存储对话内容
         if len(response_message) > 0:
+            text_buff = "".join(response_message)
+            self.tts_MessageText = text_buff
             self.dialogue.put(
-                Message(role="assistant", content="".join(response_message))
+                Message(role="assistant", content=text_buff)
             )
         if depth == 0:
             self.tts.tts_text_queue.put(

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

@@ -12,7 +12,7 @@ async def sendAudioMessage(conn, sentenceType, audios, text):
     conn.logger.bind(tag=TAG).info(f"发送音频消息: {sentenceType}, {text}")
 
     pre_buffer = False
-    if conn.tts.tts_audio_first_sentence and text is not None:
+    if conn.tts.tts_audio_first_sentence:
         conn.logger.bind(tag=TAG).info(f"发送第一段语音: {text}")
         conn.tts.tts_audio_first_sentence = False
         pre_buffer = True
@@ -73,7 +73,7 @@ async def send_tts_message(conn, state, text=None):
     """发送 TTS 状态消息"""
     message = {"type": "tts", "state": state, "session_id": conn.session_id}
     if text is not None:
-        message["text"] = text
+        message["text"] = textUtils.check_emoji(text)
 
     # TTS播放结束
     if state == "stop":

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

@@ -127,8 +127,6 @@ class TTSProvider(TTSProviderBase):
 
         # 专属tts设置
         self.message_id = ""
-        self.tts_text = ""
-        self.text_buffer = []
 
         # 创建Opus编码器
         self.opus_encoder = opus_encoder_utils.OpusEncoderUtils(
@@ -229,7 +227,6 @@ class TTSProvider(TTSProviderBase):
 
                         # aliyunStream独有的参数生成
                         self.message_id = str(uuid.uuid4().hex)
-                        self.text_buffer = []
 
                         logger.bind(tag=TAG).info("开始启动TTS会话...")
                         future = asyncio.run_coroutine_threadsafe(
@@ -250,7 +247,6 @@ class TTSProvider(TTSProviderBase):
                             logger.bind(tag=TAG).debug(
                                 f"开始发送TTS文本: {message.content_detail}"
                             )
-                            self.text_buffer.append(message.content_detail)
                             future = asyncio.run_coroutine_threadsafe(
                                 self.text_to_speak(message.content_detail, None),
                                 loop=self.conn.loop,
@@ -275,9 +271,6 @@ class TTSProvider(TTSProviderBase):
                 if message.sentence_type == SentenceType.LAST:
                     try:
                         logger.bind(tag=TAG).info("开始结束TTS会话...")
-                        self.tts_text = textUtils.get_string_no_punctuation_or_emoji(
-                            "".join(self.text_buffer).replace("\n", "")
-                        )
                         future = asyncio.run_coroutine_threadsafe(
                             self.finish_session(self.conn.sentence_id),
                             loop=self.conn.loop,
@@ -444,34 +437,35 @@ class TTSProvider(TTSProviderBase):
                             event_name = header.get("name")
                             if event_name == "SynthesisStarted":
                                 logger.bind(tag=TAG).debug("TTS合成已启动")
-                            elif event_name == "SentenceBegin":
-                                logger.bind(tag=TAG).debug(
-                                    f"句子语音生成开始: {self.tts_text}"
-                                )
-                                opus_datas_cache = []
                                 self.tts_audio_queue.put(
-                                    (SentenceType.FIRST, [], self.tts_text)
+                                    (SentenceType.FIRST, [], None)
                                 )
+                            elif event_name == "SentenceBegin":
+                                opus_datas_cache = []
                             elif event_name == "SentenceEnd":
-                                logger.bind(tag=TAG).info(
-                                    f"句子语音生成成功： {self.tts_text}"
-                                )
                                 if (
                                     not is_first_sentence
                                     or first_sentence_segment_count > 10
                                 ):
                                     # 发送缓存的数据
-                                    self.tts_audio_queue.put(
+                                    if self.conn.tts_MessageText:
-                                        (SentenceType.MIDDLE, opus_datas_cache, None)
+                                        logger.bind(tag=TAG).info(
-                                    )
+                                            f"句子语音生成成功： {self.conn.tts_MessageText}"
+                                        )
+                                        self.tts_audio_queue.put(
+                                            (SentenceType.MIDDLE, opus_datas_cache, self.conn.tts_MessageText)
+                                        )
+                                        self.conn.tts_MessageText = None
+                                    else:
+                                        self.tts_audio_queue.put(
+                                            (SentenceType.MIDDLE, opus_datas_cache, None)
+                                        )
                                 # 第一句话结束后，将标志设置为False
                                 is_first_sentence = False
                             elif event_name == "SynthesisCompleted":
                                 logger.bind(tag=TAG).debug(f"会话结束～～")
                                 self._process_before_stop_play_files()
                                 session_finished = True
-                                self.reuse_judgment = time.time()
-                                self.tts_text = ""
                                 break
                         except json.JSONDecodeError:
                             logger.bind(tag=TAG).warning("收到无效的JSON消息")

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

@@ -232,7 +232,6 @@ class TTSProvider(TTSProviderBase):
                             loop=self.conn.loop,
                         )
                         future.result()
-                        self.tts_audio_first_sentence = True
                         self.before_stop_play_files.clear()
                         logger.bind(tag=TAG).info("TTS会话启动成功")
                     except Exception as e:

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

@@ -52,7 +52,6 @@ class TTSProvider(TTSProviderBase):
                     self.processed_chars = 0
                     self.tts_text_buff = []
                     self.segment_count = 0
-                    self.tts_audio_first_sentence = True
                     self.before_stop_play_files.clear()
                 elif ContentType.TEXT == message.content_type:
                     self.tts_text_buff.append(message.content_detail)

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

@@ -24,6 +24,15 @@ EMOJI_MAP = {
     "😘": "kissy",
     "😏": "confident",
 }
+EMOJI_RANGES = [
+    (0x1F600, 0x1F64F),
+    (0x1F300, 0x1F5FF),
+    (0x1F680, 0x1F6FF),
+    (0x1F900, 0x1F9FF),
+    (0x1FA70, 0x1FAFF),
+    (0x2600, 0x26FF),
+    (0x2700, 0x27BF),
+]
 
 
 def get_string_no_punctuation_or_emoji(s):
@@ -65,18 +74,7 @@ def is_punctuation_or_emoji(char):
     }
     if char.isspace() or char in punctuation_set:
         return True
-    # 检查表情符号（保留原有逻辑）
+    return is_emoji(char)
-    code_point = ord(char)
-    emoji_ranges = [
-        (0x1F600, 0x1F64F),
-        (0x1F300, 0x1F5FF),
-        (0x1F680, 0x1F6FF),
-        (0x1F900, 0x1F9FF),
-        (0x1FA70, 0x1FAFF),
-        (0x2600, 0x26FF),
-        (0x2700, 0x27BF),
-    ]
-    return any(start <= code_point <= end for start, end in emoji_ranges)
 
 
 async def get_emotion(conn, text):
@@ -102,3 +100,14 @@ async def get_emotion(conn, text):
     except Exception as e:
         conn.logger.bind(tag=TAG).warning(f"发送情绪表情失败，错误:{e}")
     return
+
+
+def is_emoji(char):
+    """检查字符是否为emoji表情"""
+    code_point = ord(char)
+    return any(start <= code_point <= end for start, end in EMOJI_RANGES)
+
+
+def check_emoji(text):
+    """去除文本中的所有emoji表情"""
+    return ''.join(char for char in text if not is_emoji(char) and char != "\n")