diff --git a/main/xiaozhi-server/core/providers/tts/base.py b/main/xiaozhi-server/core/providers/tts/base.py
index f34158d1..b83f6f06 100644
--- a/main/xiaozhi-server/core/providers/tts/base.py
+++ b/main/xiaozhi-server/core/providers/tts/base.py
@@ -30,13 +30,15 @@ class TTSProviderBase(ABC):
                     asyncio.run(self.text_to_speak(text, tmp_file))
                 except Exception as e:
                     logger.bind(tag=TAG).error(f"语音生成失败: {text}，错误: {e}")
+                if not os.path.exists(tmp_file):
                     max_repeat_time -= 1
                     if max_repeat_time > 0:
                         logger.bind(tag=TAG).error(f"再试{max_repeat_time}次")
-                        asyncio.sleep(max_repeat_time / 10)
 
             if max_repeat_time > 0:
-                logger.bind(tag=TAG).info(f"语音生成成功: {text}:{tmp_file}，重试{5 - max_repeat_time}次")
+                logger.bind(tag=TAG).info(
+                    f"语音生成成功: {text}:{tmp_file}，重试{5 - max_repeat_time}次"
+                )
 
             return tmp_file
         except Exception as e:
@@ -52,9 +54,11 @@ class TTSProviderBase(ABC):
         # 获取文件后缀名
         file_type = os.path.splitext(audio_file_path)[1]
         if file_type:
-            file_type = file_type.lstrip('.')
+            file_type = file_type.lstrip(".")
         # 读取音频文件，-nostdin 参数：不要从标准输入读取数据，否则FFmpeg会阻塞
-        audio = AudioSegment.from_file(audio_file_path, format=file_type, parameters=["-nostdin"])
+        audio = AudioSegment.from_file(
+            audio_file_path, format=file_type, parameters=["-nostdin"]
+        )
 
         # 转换为单声道/16kHz采样率/16位小端编码（确保与编码器匹配）
         audio = audio.set_channels(1).set_frame_rate(16000).set_sample_width(2)
@@ -76,11 +80,11 @@ class TTSProviderBase(ABC):
         # 按帧处理所有音频数据（包括最后一帧可能补零）
         for i in range(0, len(raw_data), frame_size * 2):  # 16bit=2bytes/sample
             # 获取当前帧的二进制数据
-            chunk = raw_data[i:i + frame_size * 2]
+            chunk = raw_data[i : i + frame_size * 2]
 
             # 如果最后一帧不足，补零
             if len(chunk) < frame_size * 2:
-                chunk += b'\x00' * (frame_size * 2 - len(chunk))
+                chunk += b"\x00" * (frame_size * 2 - len(chunk))
 
             # 转换为numpy数组处理
             np_frame = np.frombuffer(chunk, dtype=np.int16)