Update app.py

app.py

@@ -10,15 +10,40 @@ prompt = "Type and press Enter"
 
 
 def record_text(audio_file,api_key):
-    # client = OpenAI(api_key = api_key)
-    # audio_file = open(audio_file, "rb") 
-    # transcript = client.audio.transcriptions.create(
-    #     model="whisper-1", 
-    #     file=audio_file,
-    #     response_format="text"
-    #     )
-    # return transcript
-    return(str(path.getsize(audio_file)/1000000)+'mb')
+    client = OpenAI(api_key = api_key)
+    input_file = audio_file
+    output_file = "converted_sound.mp3"
+    sound = AudioSegment.from_wav(input_file) 
+    sound.export(output_file, format="mp3")
+    audio_file = "converted_sound.mp3"
+    audio_file = open(audio_file, "rb") 
+    transcript = client.audio.transcriptions.create(
+        model="whisper-1", 
+        file=audio_file,
+        response_format="text"
+        )
+    return transcript
+    # return(str(path.getsize(audio_file)/1000000)+'mb')
+    # 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"
+    
+    # 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)
 
 
 def api_calling(audio_file, prompt, api_key):