app.py

# Importing necessary libraries
import os
import whisper
from groq import Groq
from gtts import gTTS
import gradio as gr

# Step 1: Load the Whisper model
print("Loading Whisper model...")
whisper_model = whisper.load_model("base")

# Step 2: Initialize the Groq API client
GROP_API_KEY = "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"
client = Groq(api_key=GROP_API_KEY)

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

# Function to interact with Groq's LLM
def get_llm_response(user_text):
    print(f"Sending request to Groq API with input: {user_text}")
    try:
        chat_completion = client.chat.completions.create(
            messages=[{"role": "user", "content": user_text}],
            model="llama3-8b-8192",
        )
        print(f"Groq API full response: {chat_completion}")
        return chat_completion.choices[0].message.content
    except Exception as e:
        print(f"Error while fetching response from Groq API: {e}")
        return f"Error occurred: {e}"

# Function to convert text to speech using gTTS
def text_to_speech(response_text, output_path="response.mp3"):
    print("Converting text to speech...")
    tts = gTTS(response_text)
    tts.save(output_path)
    return output_path

# Complete chat pipeline function
def chat_pipeline(audio_input):
    # Step 1: Transcribe audio
    transcribed_text = transcribe_audio(audio_input)

    # Step 2: Get response from LLM
    llm_response = get_llm_response(transcribed_text)

    # Step 3: Convert LLM response to audio
    response_audio_path = text_to_speech(llm_response)

    return transcribed_text, llm_response, response_audio_path

# Gradio Interface
print("Setting up Gradio interface...")
interface = gr.Interface(
    fn=chat_pipeline,
    inputs=gr.Audio(type="filepath", label="Record or Upload Audio"),
    outputs=[
        gr.Textbox(label="Transcribed Text"),
        gr.Textbox(label="LLM Response"),
        gr.Audio(label="Response Audio"),
    ],
    live=True
)

# Launch the Gradio app
print("Launching Gradio app...")
interface.launch()