diff --git a/main/xiaozhi-server/core/handle/intentHandler.py b/main/xiaozhi-server/core/handle/intentHandler.py
index ccff094c..81911f55 100644
--- a/main/xiaozhi-server/core/handle/intentHandler.py
+++ b/main/xiaozhi-server/core/handle/intentHandler.py
@@ -13,6 +13,16 @@ TAG = __name__
 
 
 async def handle_user_intent(conn, text):
+    # 预处理输入文本，处理可能的JSON格式
+    try:
+        if text.strip().startswith('{') and text.strip().endswith('}'):
+            parsed_data = json.loads(text)
+            if isinstance(parsed_data, dict) and "content" in parsed_data:
+                text = parsed_data["content"]  # 提取content用于意图分析
+                conn.current_speaker = parsed_data.get("speaker")  # 保留说话人信息
+    except (json.JSONDecodeError, TypeError):
+        pass
+
     # 检查是否有明确的退出命令
     filtered_text = remove_punctuation_and_length(text)[1]
     if await check_direct_exit(conn, filtered_text):
diff --git a/main/xiaozhi-server/core/handle/sendAudioHandle.py b/main/xiaozhi-server/core/handle/sendAudioHandle.py
index 486e6d90..730a71a7 100644
--- a/main/xiaozhi-server/core/handle/sendAudioHandle.py
+++ b/main/xiaozhi-server/core/handle/sendAudioHandle.py
@@ -146,6 +146,9 @@ async def send_stt_message(conn, text):
             if isinstance(parsed_data, dict) and "content" in parsed_data:
                 # 如果是包含说话人信息的JSON格式，只显示content部分
                 display_text = parsed_data["content"]
+                # 保存说话人信息到conn对象
+                if "speaker" in parsed_data:
+                    conn.current_speaker = parsed_data["speaker"]
     except (json.JSONDecodeError, TypeError):
         # 如果不是JSON格式，直接使用原始文本
         display_text = text