From 5c261528d026cc1489b030c58406ad172c7affd1 Mon Sep 17 00:00:00 2001
From: hrz <1710360675@qq.com>
Date: Sat, 13 Dec 2025 23:10:40 +0800
Subject: [PATCH] =?UTF-8?q?update:=E5=B8=B8=E7=94=A8=E9=9F=B3=E9=A2=91?=
 =?UTF-8?q?=E5=A2=9E=E5=8A=A0=E7=BC=93=E5=AD=98=EF=BC=8C=E6=8A=B5=E5=BE=A1?=
 =?UTF-8?q?=E9=AB=98=E5=B9=B6=E5=8F=91=E6=9C=AA=E6=8E=88=E6=9D=83=E8=AE=BE?=
 =?UTF-8?q?=E5=A4=87=E8=AE=BF=E9=97=AE?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .../xiaozhi-server/core/handle/helloHandle.py |  2 +-
 .../xiaozhi-server/core/utils/cache/config.py |  4 ++++
 main/xiaozhi-server/core/utils/util.py        | 24 +++++++++++++++++--
 3 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/main/xiaozhi-server/core/handle/helloHandle.py b/main/xiaozhi-server/core/handle/helloHandle.py
index efe66b59..a4220d5a 100644
--- a/main/xiaozhi-server/core/handle/helloHandle.py
+++ b/main/xiaozhi-server/core/handle/helloHandle.py
@@ -101,7 +101,7 @@ async def checkWakeupWords(conn, text):
         }
 
     # 获取音频数据
-    opus_packets = await audio_to_data(response.get("file_path"))
+    opus_packets = await audio_to_data(response.get("file_path"), use_cache=False)
     # 播放唤醒词回复
     conn.client_abort = False
 
diff --git a/main/xiaozhi-server/core/utils/cache/config.py b/main/xiaozhi-server/core/utils/cache/config.py
index 248c2af7..f85e40bb 100644
--- a/main/xiaozhi-server/core/utils/cache/config.py
+++ b/main/xiaozhi-server/core/utils/cache/config.py
@@ -19,6 +19,7 @@ class CacheType(Enum):
     CONFIG = "config"
     DEVICE_PROMPT = "device_prompt"
     VOICEPRINT_HEALTH = "voiceprint_health"  # 声纹识别健康检查
+    AUDIO_DATA = "audio_data"  # 音频数据缓存
 
 
 @dataclass
@@ -58,5 +59,8 @@ class CacheConfig:
             CacheType.VOICEPRINT_HEALTH: cls(
                 strategy=CacheStrategy.TTL, ttl=600, max_size=100  # 10分钟过期
             ),
+            CacheType.AUDIO_DATA: cls(
+                strategy=CacheStrategy.TTL, ttl=600, max_size=100  # 10分钟过期
+            ),
         }
         return configs.get(cache_type, cls())
diff --git a/main/xiaozhi-server/core/utils/util.py b/main/xiaozhi-server/core/utils/util.py
index 2baedf68..4547ad8f 100644
--- a/main/xiaozhi-server/core/utils/util.py
+++ b/main/xiaozhi-server/core/utils/util.py
@@ -269,13 +269,27 @@ def audio_to_data_stream(
     pcm_to_data_stream(raw_data, is_opus, callback)
 
 
-async def audio_to_data(audio_file_path: str, is_opus: bool = True) -> list[bytes]:
+async def audio_to_data(
+    audio_file_path: str, is_opus: bool = True, use_cache: bool = True
+) -> list[bytes]:
     """
     将音频文件转换为Opus/PCM编码的帧列表
     Args:
         audio_file_path: 音频文件路径
         is_opus: 是否进行Opus编码
+        use_cache: 是否使用缓存
     """
+    from core.utils.cache.manager import cache_manager
+    from core.utils.cache.config import CacheType
+
+    # 生成缓存键，包含文件路径和编码类型
+    cache_key = f"{audio_file_path}:{is_opus}"
+
+    # 尝试从缓存获取结果
+    if use_cache:
+        cached_result = cache_manager.get(CacheType.AUDIO_DATA, cache_key)
+        if cached_result is not None:
+            return cached_result
 
     def _sync_audio_to_data():
         # 获取文件后缀名
@@ -324,7 +338,13 @@ async def audio_to_data(audio_file_path: str, is_opus: bool = True) -> list[byte
 
     loop = asyncio.get_running_loop()
     # 在单独的线程中执行同步的音频处理操作
-    return await loop.run_in_executor(None, _sync_audio_to_data)
+    result = await loop.run_in_executor(None, _sync_audio_to_data)
+
+    # 将结果存入缓存，使用配置中定义的TTL（10分钟）
+    if use_cache:
+        cache_manager.set(CacheType.AUDIO_DATA, cache_key, result)
+
+    return result
 
 
 def audio_bytes_to_data_stream(