diff --git a/py/speech.py b/py/speech.py
index c557f7a..2f85b05 100644
--- a/py/speech.py
+++ b/py/speech.py
@@ -2,12 +2,10 @@ import speech_recognition as sr
 
 recognizer = sr.Recognizer()
 with sr.Microphone() as source:
-    print("Speak something...")
+    print("Say something...")
     audio = recognizer.listen(source)
     try:
-        text = recognizer.recognize_google(audio)
-        print("You said: {}".format(text))
+        text = recognizer.recognize_sphinx(audio)
+        print("Sphinx recognized: {}".format(text))
     except sr.UnknownValueError:
         print("Could not understand audio.")
-    except sr.RequestError as e:
-        print("Error with API: {}".format(e))