From 7e5a2b4549fbd22e9727deac192fdd31179fa575 Mon Sep 17 00:00:00 2001
From: Sakura-RanChen <1908198662@qq.com>
Date: Fri, 4 Jul 2025 11:27:49 +0800
Subject: [PATCH] =?UTF-8?q?fix:=20=E6=92=AD=E6=94=BE=E9=9F=B3=E4=B9=90?=
 =?UTF-8?q?=E6=97=B6=EF=BC=8C=E5=BC=95=E5=AF=BC=E8=AF=8D=E5=8D=A1=E9=A1=BF?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 main/xiaozhi-server/core/providers/tts/base.py         |  6 ++----
 .../core/providers/tts/huoshan_double_stream.py        | 10 +++++++---
 main/xiaozhi-server/core/providers/tts/linkerai.py     | 10 +++++++---
 3 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/main/xiaozhi-server/core/providers/tts/base.py b/main/xiaozhi-server/core/providers/tts/base.py
index 223cb807..d196b8f9 100644
--- a/main/xiaozhi-server/core/providers/tts/base.py
+++ b/main/xiaozhi-server/core/providers/tts/base.py
@@ -362,10 +362,8 @@ class TTSProviderBase(ABC):
         return audio_datas
 
     def _process_before_stop_play_files(self):
-        for tts_file, 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))
+        for audio_datas, text in self.before_stop_play_files:
+            self.tts_audio_queue.put((SentenceType.MIDDLE, audio_datas, text))
         self.before_stop_play_files.clear()
         self.tts_audio_queue.put((SentenceType.LAST, [], None))
 
diff --git a/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py b/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
index 3fe6294e..6f8fcca5 100644
--- a/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
+++ b/main/xiaozhi-server/core/providers/tts/huoshan_double_stream.py
@@ -1,3 +1,4 @@
+import os
 import uuid
 import json
 import queue
@@ -245,9 +246,12 @@ class TTSProvider(TTSProviderBase):
                     logger.bind(tag=TAG).info(
                         f"添加音频文件到待播放列表: {message.content_file}"
                     )
-                    self.before_stop_play_files.append(
-                        (message.content_file, message.content_detail)
-                    )
+                    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(
+                            (file_audio, message.content_detail)
+                        )
 
                 if message.sentence_type == SentenceType.LAST:
                     try:
diff --git a/main/xiaozhi-server/core/providers/tts/linkerai.py b/main/xiaozhi-server/core/providers/tts/linkerai.py
index ee108540..1046b972 100644
--- a/main/xiaozhi-server/core/providers/tts/linkerai.py
+++ b/main/xiaozhi-server/core/providers/tts/linkerai.py
@@ -1,3 +1,4 @@
+import os
 import queue
 import asyncio
 import traceback
@@ -63,9 +64,12 @@ class TTSProvider(TTSProviderBase):
                     logger.bind(tag=TAG).info(
                         f"添加音频文件到待播放列表: {message.content_file}"
                     )
-                    self.before_stop_play_files.append(
-                        (message.content_file, message.content_detail)
-                    )
+                    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(
+                            (file_audio, message.content_detail)
+                        )
 
                 if message.sentence_type == SentenceType.LAST:
                     # 处理剩余的文本