diff --git a/README.md b/README.md
index 4ff7cea..54fbf83 100644
--- a/README.md
+++ b/README.md
@@ -73,7 +73,7 @@ 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
-pip3 install speech_recognition
+pip3 install SpeechRecognition
 --在MacOS中安装ffmpeg，brew install ffmpeg
 --在Windows中安装ffmpeg，下载ffmpeg.exe
 --在Linux中安装ffmpeg，apt-get install ffmpeg
diff --git a/voice/google/google_voice.py b/voice/google/google_voice.py
index 7af3880..97597b3 100644
--- a/voice/google/google_voice.py
+++ b/voice/google/google_voice.py
@@ -18,4 +18,9 @@ class GoogleVoice(Voice):
         subprocess.call('ffmpeg -i ' + voice_file + ' -acodec pcm_s16le -ac 1 -ar 16000 ' + new_file, shell=True)
         with speech_recognition.AudioFile(new_file) as source:
             audio = self.recognizer.record(source)
-        return self.recognizer.recognize_google(audio, language='zh-CN')
+        try:
+            return self.recognizer.recognize_google(audio, language='zh-CN')
+        except speech_recognition.UnknownValueError:
+            return "抱歉，我听不懂。"
+        except speech_recognition.RequestError as e:
+            return "抱歉，无法连接到 Google 语音识别服务；{0}".format(e)