Update app.py

app.py

@@ -9,28 +9,32 @@ prompt = "Type and press Enter"
 
 
 def record_text(audio_file):
-    r = sr.Recognizer()
+    audio_file = open(audio_file, "rb") 
+    transcript = openai.Audio.transcribe("whisper-1", audio_file) 
+    text = transcript['text']
+    return text
+    # r = sr.Recognizer()
     
-    sound = audio_file
-    sound_type = sound.split(".")
-    if sound_type[-1] == 'mp3':
-        input_file = sound
-        output_file = "con_sound.wav"
+    # sound = audio_file
+    # sound_type = sound.split(".")
+    # if sound_type[-1] == 'mp3':
+    #     input_file = sound
+    #     output_file = "con_sound.wav"
         
-        # convert mp3 file to wav file 
-        sound = AudioSegment.from_mp3(input_file) 
-        sound.export(output_file, format="wav")
-        sound = "con_sound.wav"
+    #     # convert mp3 file to wav file 
+    #     sound = AudioSegment.from_mp3(input_file) 
+    #     sound.export(output_file, format="wav")
+    #     sound = "con_sound.wav"
     
-    MyText = ""
-    with sr.AudioFile(sound) as source:
-        r.adjust_for_ambient_noise(source)
-        print("Converting audio file to text..")
-        audio2 = r.record(source, duration=None)  # Use record instead of listen
+    # MyText = ""
+    # with sr.AudioFile(sound) as source:
+    #     r.adjust_for_ambient_noise(source)
+    #     print("Converting audio file to text..")
+    #     audio2 = r.record(source, duration=None)  # Use record instead of listen
         
-        MyText = r.recognize_google(audio2, language="en-US", key=None, show_all=False)
-        MyText = MyText.lower()
-    return (MyText)
+    #     MyText = r.recognize_google(audio2, language="en-US", key=None, show_all=False)
+    #     MyText = MyText.lower()
+    # return (MyText)
 
 
 def api_calling(audio_file, prompt, api_key):