app.py

import gradio as gr
import openai
import whisper  # Ensure you have `openai-whisper` installed
import os
from gtts import gTTS
import tempfile
import groq

# Load Whisper model
model = whisper.load_model("base")

# OpenAI API Key (Replace with your own API key)
openai.api_key = "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"
groq_api_key = "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"

# Function to convert speech to text
def speech_to_text(audio_file):
    audio = whisper.load_audio(audio_file)
    audio = whisper.pad_or_trim(audio)
    mel = whisper.log_mel_spectrogram(audio).to(model.device)
    options = whisper.DecodingOptions(fp16=False)
    result = whisper.decode(model, mel, options)
    return result.text

# Function to get chatbot response
def chatbot_response(text):
    response = openai.ChatCompletion.create(
        model="gpt-4",
        messages=[{"role": "user", "content": text}]
    )
    return response["choices"][0]["message"]["content"]

# Function to generate audio response
def text_to_speech(text):
    tts = gTTS(text)
    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
    tts.save(temp_file.name)
    return temp_file.name

# Main function to process audio input
def process_audio(audio_file):
    text = speech_to_text(audio_file)
    response = chatbot_response(text)
    audio_response = text_to_speech(response)
    return response, audio_response

# Enhanced Gradio UI
def create_ui():
    with gr.Blocks(css="body { background-color: #f4f4f4; font-family: Arial, sans-serif; }") as demo:
        gr.Markdown("""
        # 🎙️ Audio-to-Audio Chatbot
        **Talk to the AI and get voice responses in real-time!**
        """)
        
        with gr.Row():
            audio_input = gr.Audio(source="microphone", type="filepath", label="🎤 Speak Here")
            submit_button = gr.Button("Send", variant="primary")
        
        with gr.Row():
            text_output = gr.Textbox(label="💬 Chatbot Response", interactive=False)
            audio_output = gr.Audio(label="🔊 AI Voice Reply")
        
        submit_button.click(fn=process_audio, inputs=audio_input, outputs=[text_output, audio_output])
    
    return demo

if __name__ == "__main__":
    ui = create_ui()
    ui.launch()