app.py

#1st Line install Libraries:-
#!pip install gradio groq openai-whisper gtts numpy pydub requests
#!apt-get install -y ffmpeg


#2nd Line generate API key from GROQ:-
#import os
#os.environ["GROQ_API_KEY"] = "Mention_your API_Key_here"


#3rd Line Code:-
import os
import gradio as gr
from groq import Groq, GroqError
import whisper
from gtts import gTTS
import tempfile
import logging
import numpy as np
from pydub import AudioSegment

# Set up logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

# Set up Groq API key
groq_api_key = os.getenv('groq_api_key')
#GROQ_API_KEY = "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"

if not groq_api_key:
    raise ValueError("GROQ_API_KEY is not set.")
try:
    groq_client = Groq(api_key=groq_api_key)
    logger.info("Groq API key is set and client is initialized.")
except GroqError as e:
    logger.error(f"Failed to initialize Groq client: {e}")
    raise

try:
    # Load Whisper model
    whisper_model = whisper.load_model("base")
    logger.info("Whisper model loaded successfully.")
except Exception as e:
    logger.error(f"Failed to load Whisper model: {e}")
    raise

def process_audio(audio_file):
    try:
        # Transcribe audio using Whisper
        result = whisper_model.transcribe(audio_file)
        user_text = result['text']
        logger.info(f"Transcription successful: {user_text}")
    except Exception as e:
        logger.error(f"Error in transcribing audio: {e}")
        return "Error in transcribing audio.", None

    try:
        # Generate response using Llama 8b model with Groq API
        chat_completion = groq_client.chat.completions.create(
            messages=[
                {
                    "role": "user",
                    "content": user_text,
                }
            ],
            model="llama3-8b-8192",
        )
        response_text = chat_completion.choices[0].message.content
        logger.info(f"Received response from Groq API: {response_text}")
    except GroqError as e:
        logger.error(f"Error in generating response with Groq API: {e}")
        return "Error in generating response with Groq API.", None

    try:
        # Convert response text to speech using gTTS
        tts = gTTS(text=response_text, lang='en')
        audio_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp3')
        tts.save(audio_file.name)
        logger.info("Text-to-speech conversion successful.")
    except Exception as e:
        logger.error(f"Error in text-to-speech conversion: {e}")
        return "Error in text-to-speech conversion.", None

    return response_text, audio_file.name

# Create Gradio interface
iface = gr.Interface(
    fn=process_audio,
    inputs=gr.Audio(type="filepath"),
    title="AI-Powered Converter",
    outputs=[gr.Textbox(label="Response"), gr.Audio(label="Response Audio")],
    live=True
)

try:
    iface.launch()
    logger.info("Gradio interface launched successfully.")
except Exception as e:
    logger.error(f"Failed to launch Gradio interface: {e}")
    raise