diff --git a/README.md b/README.md
index 54fbf83..1676395 100644
--- a/README.md
+++ b/README.md
@@ -72,11 +72,11 @@ cd chatgpt-on-wechat/
 pip3 install itchat-uos==1.5.0.dev0
 pip3 install --upgrade openai
 
-如果使用google的语音识别，需要安装speech_recognition和依赖的ffmpeg
+如果使用google的语音识别，需要安装speech_recognition和依赖的ffmpeg和espeak
 pip3 install SpeechRecognition
---在MacOS中安装ffmpeg，brew install ffmpeg
+--在MacOS中安装ffmpeg，brew install ffmpeg espeak
 --在Windows中安装ffmpeg，下载ffmpeg.exe
---在Linux中安装ffmpeg，apt-get install ffmpeg
+--在Linux中安装ffmpeg，apt-get install ffmpeg espeak
 ```
 注：`itchat-uos`使用指定版本1.5.0.dev0，`openai`使用最新版本，需高于0.27.0。
 
diff --git a/channel/wechat/wechat_channel.py b/channel/wechat/wechat_channel.py
index b3d3658..3fdc94f 100644
--- a/channel/wechat/wechat_channel.py
+++ b/channel/wechat/wechat_channel.py
@@ -40,7 +40,6 @@ class WechatChannel(Channel):
     tmpFilePath = './tmp/'
 
     def __init__(self):
-        voices = self.engine.getProperty('voices')
         isExists = os.path.exists(self.tmpFilePath)
         if not isExists: 
             os.makedirs(self.tmpFilePath)