app.py

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

# Set up Groq API Key
GROQ_API_KEY = os.getenv("api_key")  # Ensure to set this in your Hugging Face Space Secrets
client = Groq(api_key=GROQ_API_KEY)

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

# Function to get LLM response from Groq
def get_llm_response(user_input):
    try:
        chat_completion = client.chat.completions.create(
            messages=[{"role": "user", "content": user_input}],
            model="llama3-8b-8192",  # Replace with your desired model
        )
        return chat_completion.choices[0].message.content
    except Exception as e:
        return f"Error fetching LLM response: {e}"

# Function to convert text to speech using gTTS
def text_to_speech(text, output_audio="output_audio.mp3"):
    try:
        tts = gTTS(text)
        tts.save(output_audio)
        return output_audio
    except Exception as e:
        return f"Error generating audio: {e}"

# Main function to handle audio input and output
def chatbot(audio_path):
    try:
        # Step 1: Transcribe the audio using Whisper
        result = model.transcribe(audio_path)
        user_text = result["text"]

        # Step 2: Get LLM response from Groq
        response_text = get_llm_response(user_text)

        # Step 3: Convert the response text to speech
        output_audio = text_to_speech(response_text)

        return user_text, response_text, output_audio
    except Exception as e:
        return "Error processing audio", str(e), None

# Define Gradio interface
def gradio_interface(audio_file):
    user_text, response_text, output_audio = chatbot(audio_file)
    return user_text, response_text, output_audio

interface = gr.Interface(
    fn=gradio_interface,
    inputs=gr.Audio(type="filepath", label="Upload Audio"),
    outputs=[
        gr.Textbox(label="Transcription of User Input"),
        gr.Textbox(label="LLM Response"),
        gr.Audio(label="Generated Audio Response")
    ],
    title="AI Chatbot with Audio Input and Output",
    description=(
        "Upload an audio file to transcribe it using Whisper, "
        "get a response from an LLM (Groq), and generate an audio response using gTTS."
    ),
)

if __name__ == "__main__":
    interface.launch()