diff --git a/paddlespeech/server/utils/audio_handler.py b/paddlespeech/server/utils/audio_handler.py
index 43b73d6eb..add04156d 100644
--- a/paddlespeech/server/utils/audio_handler.py
+++ b/paddlespeech/server/utils/audio_handler.py
@@ -160,7 +160,7 @@ class ASRWsAudioHandler:
                 separators=(',', ': '))
             await ws.send(audio_info)
             msg = await ws.recv()
-            logger.debug("client receive msg={}".format(msg))
+            logger.info("client receive msg={}".format(msg))
 
             # 3. send chunk audio data to engine
             for chunk_data in self.read_wave(wavfile_path):
@@ -170,7 +170,7 @@ class ASRWsAudioHandler:
 
                 if self.punc_server and len(msg["result"]) > 0:
                     msg["result"] = self.punc_server.run(msg["result"])
-                logger.debug("client receive msg={}".format(msg))
+                logger.info("client receive msg={}".format(msg))
 
             # 4. we must send finished signal to the server
             audio_info = json.dumps(
@@ -317,7 +317,7 @@ class TTSWsHandler:
             start_request = json.dumps({"task": "tts", "signal": "start"})
             await ws.send(start_request)
             msg = await ws.recv()
-            logger.debug(f"client receive msg={msg}")
+            logger.info(f"client receive msg={msg}")
             msg = json.loads(msg)
             session = msg["session"]