Update app.py

app.py

@@ -1,79 +1,37 @@
-import speech_recognition as sr
-from gtts import gTTS
-import playsound
-import os
-import pyttsx3
-import openai
-
-# Initialize OpenAI API
-openai.api_key = "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"
-
-# Initialize text-to-speech engine
-engine = pyttsx3.init()
-
-def speak(text):
-    """Convert text to speech and play it."""
-    try:
-        tts = gTTS(text=text, lang='en')
-        filename = "temp.mp3"
-        tts.save(filename)
-        playsound.playsound(filename)
-        os.remove(filename)
-    except Exception as e:
-        print(f"Error in TTS (gTTS): {e}")
-        engine.say(text)
-        engine.runAndWait()
-
-def listen():
-    """Capture voice input and convert it to text."""
-    recognizer = sr.Recognizer()
-    with sr.Microphone() as source:
-        print("Listening...")
-        try:
-            audio = recognizer.listen(source, timeout=5, phrase_time_limit=10)
-            text = recognizer.recognize_google(audio)
-            print(f"User said: {text}")
-            return text
-        except sr.UnknownValueError:
-            print("Sorry, I did not understand that.")
-            return None
-        except sr.RequestError as e:
-            print(f"Error with the speech recognition service: {e}")
-            return None
-
-def generate_response(prompt):
-    """Generate a response using OpenAI's GPT model."""
-    try:
-        response = openai.Completion.create(
-            engine="text-davinci-003",
-            prompt=prompt,
-            max_tokens=150
-        )
-        return response.choices[0].text.strip()
-    except Exception as e:
-        print(f"Error generating response: {e}")
-        return "I'm sorry, I cannot process that right now."
-
-def main():
-    """Main function to run the AI Voice Agent."""
-    print("AI Voice Agent is running. Say 'exit' to stop.")
-    speak("Hello, I am your AI Voice Agent. How can I help you today?")
-    
-    while True:
-        # Listen for user input
-        user_input = listen()
-        if not user_input:
-            continue
-        
-        # Exit condition
-        if user_input.lower() in ["exit", "quit", "stop"]:
-            speak("Goodbye! Have a nice day.")
-            break
-        
-        # Generate and speak the response
-        response = generate_response(user_input)
-        print(f"AI: {response}")
-        speak(response)
-
-if __name__ == "__main__":
-    main()
+import gradio as gr
+import openai
+import speech_recognition as sr
+
+# Set your OpenAI API key here
+openai.api_key = "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"
+
+def speech_to_text(audio):
+    recognizer = sr.Recognizer()
+    with sr.AudioFile(audio.name) as source:
+        audio_data = recognizer.record(source)
+    try:
+        text = recognizer.recognize_google(audio_data)
+        return text
+    except sr.UnknownValueError:
+        return "Sorry, I could not understand the audio."
+    except sr.RequestError:
+        return "Could not request results from Google Speech Recognition service."
+
+def text_to_ai_response(text):
+    response = openai.Completion.create(
+      engine="text-davinci-003",
+      prompt=text,
+      max_tokens=200
+    )
+    return response.choices[0].text.strip()
+
+# Interface for Gradio
+interface = gr.Interface(
+    fn=lambda audio: text_to_ai_response(speech_to_text(audio)),
+    inputs="audio",  # Correct input type
+    outputs="text",  # Correct output type
+    title="Voice AI Agent",
+    description="An AI-powered voice assistant powered by OpenAI and Gradio."
+)
+
+interface.launch()