fix: fix some error by cache queue

server.py

@@ -129,25 +129,28 @@ async def fetch_audio_data(session, pair_data, voice, speed):
         "speed": speed,
         "return_type": "base64"
     }
-    
-    try:
-        async with session.post(url, json=payload) as response:
-            if response.status != 200:
-                logger.error(f"TTS API error: {response.status} - {await response.text()}")
+    for i in range(3):
+        try:
+            async with session.post(url, json=payload) as response:
+                if response.status != 200:
+                    logger.error(f"TTS API error: {response.status} - {await response.text()}")
+                    return None
+                data = await response.json()
+                audio_base64 = data.get("audio_base64")
+                if not audio_base64:
+                    logger.error(f"No audio data returned for pair")
+                    return None
+                return {
+                    "audio_base64": audio_base64,
+                    "sentences": pair_data["sentences"],
+                    "indices": pair_data["indices"]
+                }
+        except Exception as e:
+            logger.error(f"Error fetching audio: {e}")
+            if i == 2:
                 return None
-            data = await response.json()
-            audio_base64 = data.get("audio_base64")
-            if not audio_base64:
-                logger.error(f"No audio data returned for pair")
-                return None
-            return {
-                "audio_base64": audio_base64,
-                "sentences": pair_data["sentences"],
-                "indices": pair_data["indices"]
-            }
-    except Exception as e:
-        logger.error(f"Error fetching audio: {e}")
-        return None
+            await asyncio.sleep(0.5)
+            continue
 
 async def text_to_speech(text, voice="zf_xiaoxiao", speed=1.5):
     """异步将文本转换为语音，返回每两句话的音频数据和时间戳"""