fix: 播放音乐时，引导词卡顿

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

@@ -362,9 +362,7 @@ class TTSProviderBase(ABC):
         return audio_datas
 
     def _process_before_stop_play_files(self):
-        for tts_file, text in self.before_stop_play_files:
+        for audio_datas, text in self.before_stop_play_files:
-            if tts_file and os.path.exists(tts_file):
-                audio_datas = self._process_audio_file(tts_file)
             self.tts_audio_queue.put((SentenceType.MIDDLE, audio_datas, text))
         self.before_stop_play_files.clear()
         self.tts_audio_queue.put((SentenceType.LAST, [], None))

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

@@ -1,3 +1,4 @@
+import os
 import uuid
 import json
 import queue
@@ -245,8 +246,11 @@ class TTSProvider(TTSProviderBase):
                     logger.bind(tag=TAG).info(
                         f"添加音频文件到待播放列表: {message.content_file}"
                     )
+                    if message.content_file and os.path.exists(message.content_file):
+                        # 先处理文件音频数据
+                        file_audio = self._process_audio_file(message.content_file)
                         self.before_stop_play_files.append(
-                        (message.content_file, message.content_detail)
+                            (file_audio, message.content_detail)
                         )
 
                 if message.sentence_type == SentenceType.LAST:

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

@@ -1,3 +1,4 @@
+import os
 import queue
 import asyncio
 import traceback
@@ -63,8 +64,11 @@ class TTSProvider(TTSProviderBase):
                     logger.bind(tag=TAG).info(
                         f"添加音频文件到待播放列表: {message.content_file}"
                     )
+                    if message.content_file and os.path.exists(message.content_file):
+                        # 先处理文件音频数据
+                        file_audio = self._process_audio_file(message.content_file)
                         self.before_stop_play_files.append(
-                        (message.content_file, message.content_detail)
+                            (file_audio, message.content_detail)
                         )
 
                 if message.sentence_type == SentenceType.LAST: