diff --git a/voice/azure/azure_voice.py b/voice/azure/azure_voice.py
index 3d9b860..57ea30c 100644
--- a/voice/azure/azure_voice.py
+++ b/voice/azure/azure_voice.py
@@ -54,7 +54,7 @@ class AzureVoice(Voice):
         return reply
 
     def textToVoice(self, text):
-        fileName = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.wav'
+        fileName = TmpDir().path() + 'reply-' + str(int(time.time())) + '.wav'
         audio_config = speechsdk.AudioConfig(filename=fileName)
         speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=self.speech_config, audio_config=audio_config)
         result = speech_synthesizer.speak_text(text)
diff --git a/voice/baidu/baidu_voice.py b/voice/baidu/baidu_voice.py
index bc0c448..8a17728 100644
--- a/voice/baidu/baidu_voice.py
+++ b/voice/baidu/baidu_voice.py
@@ -80,7 +80,7 @@ class BaiduVoice(Voice):
         result = self.client.synthesis(text, self.lang, self.ctp, {
             'spd': self.spd, 'pit': self.pit, 'vol': self.vol, 'per': self.per})
         if not isinstance(result, dict):
-            fileName = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
+            fileName = TmpDir().path() + 'reply-' + str(int(time.time())) + '.mp3'
             with open(fileName, 'wb') as f:
                 f.write(result)
             logger.info(
diff --git a/voice/google/google_voice.py b/voice/google/google_voice.py
index 901cc99..3a0537f 100644
--- a/voice/google/google_voice.py
+++ b/voice/google/google_voice.py
@@ -34,7 +34,7 @@ class GoogleVoice(Voice):
             return reply
     def textToVoice(self, text):
         try:
-            mp3File = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.mp3'
+            mp3File = TmpDir().path() + 'reply-' + str(int(time.time())) + '.mp3'
             tts = gTTS(text=text, lang='zh')
             tts.save(mp3File)            
             logger.info(
diff --git a/voice/pytts/pytts_voice.py b/voice/pytts/pytts_voice.py
index 3b136e0..2e9cdc0 100644
--- a/voice/pytts/pytts_voice.py
+++ b/voice/pytts/pytts_voice.py
@@ -25,7 +25,7 @@ class PyttsVoice(Voice):
 
     def textToVoice(self, text):
         try:
-            wavFile = TmpDir().path() + '语音回复_' + str(int(time.time())) + '.wav'
+            wavFile = TmpDir().path() + 'reply-' + str(int(time.time())) + '.wav'
             self.engine.save_to_file(text, wavFile)
             self.engine.runAndWait()
             logger.info(