app.py

# Install the required libraries (run this on Colab)
!pip install git+https://github.com/openai/whisper.git
!pip install gradio
!pip install gTTS  # You can use other TTS libraries if you prefer
!pip install groq
!pip install --upgrade pip setuptools wheel
!pip install git+https://github.com/openai/whisper.git --no-cache-dir
!pip install gradio --upgrade
!pip install gTTS --upgrade
!pip install groq


import whisper
import numpy as np
from groq import Groq
import os
from gtts import gTTS
import gradio as gr

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

# Function to transcribe audio using Whisper
def transcribe_audio(audio_file):
    result = model.transcribe(audio_file)
    return result['text']

# Function to interact with Groq LLM
def generate_response(transcription):
    client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
    chat_completion = client.chat.completions.create(
        messages=[{"role": "user", "content": transcription}],
        model="llama3-groq-8b-8192-tool-use-preview",
    )
    response = chat_completion.choices[0].message.content
    return response

# Function to convert text into speech using gTTS
def text_to_speech(text):
    tts = gTTS(text)
    tts.save("output.mp3")
    return "output.mp3"

# Main function to handle the chatbot interaction
def chatbot_interaction(audio):
    # Transcribe the uploaded audio to text
    transcription = transcribe_audio(audio)
    print(f"Transcription: {transcription}")
    
    # Generate a response from Groq's LLM
    response = generate_response(transcription)
    print(f"LLM Response: {response}")
    
    # Convert the LLM response to speech
    output_audio = text_to_speech(response)
    return output_audio

# Gradio interface to deploy the chatbot
def chatbot_ui():
    # Input: Audio file upload, Output: Audio file with the response
    gr.Interface(fn=chatbot_interaction, inputs="audio", outputs="audio").launch()

# Run the chatbot UI
chatbot_ui()