Update app.py

app.py

@@ -2,9 +2,10 @@ import gradio as gr
 import openai
 from decouple import config
 from gtts import gTTS
-import io
+import os
 import pydub
-import config
+import io
+import config 
 
 openai.api_key = config.API_KEYS['openai']
 
@@ -18,18 +19,17 @@ def decipher(audio):
     global messages
 
     # Using openAI's speech to text model
-    transcript = openai.Audio.transcribe("whisper-1", audio)
+    audio_file = open(audio, "rb")
+    transcript = openai.Audio.transcribe("whisper-1", audio_file)
 
     messages.append({"role": "user", "content": transcript["text"]})
 
-    response = openai.Completion.create(
-        model="text-davinci-002",
-        prompt="Conversation:\n" + "\n".join([f"{m['role']}: {m['content']}" for m in messages]),
-        temperature=0.7,
-        max_tokens=1024,
+    response =  openai.ChatCompletion.create(
+        model="gpt-3.5-turbo",
+        messages=messages
     )
 
-    system_message = response.choices[0].text
+    system_message = response["choices"][0]["message"]["content"]
     messages.append({"role": "assistant", "content": system_message})
 
     # Convert the text to audio using gTTS
@@ -39,11 +39,10 @@ def decipher(audio):
 
     # Convert the audio to a playable format using pydub
     audio_data.seek(0)
-    audio = pydub.AudioSegment.from_file(io.BytesIO(audio_data.getvalue()))
+    audio = pydub.AudioSegment.from_file(audio_data, format="mp3")
 
-    # Play the audio using VLC
-    player = pydub.playback.play
-    player(audio)
+    # Play the audio using pydub.playback
+    pydub.playback.play(audio)
 
     chat_transcript = ""
     for message in messages:
@@ -53,12 +52,6 @@ def decipher(audio):
     return chat_transcript
 
 # Using Gradio's audio Interface 
-interface = gr.Interface(fn=decipher, inputs=gr.inputs.Audio(
-    type="filepath", label="Record a voice message"), 
-    outputs="text",
-    title="AI Assistant",
-    description="An AI assistant that can transcribe and respond to voice messages",
-    theme="compact")
-
-if __name__ == "__main__":
-    interface.launch()
+interface = gr.Interface(fn=decipher, inputs=gr.Audio(
+    source="microphone", type="filepath"), outputs="text")
+interface.launch(share=True)