app.py

import gradio as gr

from google.generativeai import GenerativeModel, configure
from gtts import gTTS
import speech_recognition as sr
import os
import tempfile
import torch
from torchvision import models, transforms
from PIL import Image
import json

# ✅ Load API key from environment variable
GOOGLE_API_KEY = os.getenv("GEMINI_API_KEY")
if not GOOGLE_API_KEY:
    raise ValueError("❌ Missing API Key! Please set GEMINI_API_KEY as an environment variable.")

# ✅ Configure Gemini securely
configure(api_key=GOOGLE_API_KEY)
gemini_model = GenerativeModel("models/gemini-1.5-flash")

def transcribe_audio(audio_path):
    recognizer = sr.Recognizer()
    with sr.AudioFile(audio_path) as source:
        audio = recognizer.record(source)
    try:
        return recognizer.recognize_google(audio, language='pa-IN')
    except sr.UnknownValueError:
        return "❌ ਆਵਾਜ਼ ਨੂੰ ਸਮਝਿਆ ਨਹੀਂ ਜਾ ਸਕਿਆ।"
    except sr.RequestError:
        return "❌ ਗੂਗਲ ਸਪੀਚ ਐਪੀਆਈ ਨਾਲ ਕਨੇਕਟ ਨਹੀਂ ਹੋ ਸਕਿਆ।"
        
def get_gemini_response(query):
    try:
        response = gemini_model.generate_content(f"ਪੰਜਾਬੀ ਵਿੱਚ ਜਵਾਬ ਦਿਓ: {query}")
        return response.text.replace('*', '')
    except Exception as e:
        return f"❌ Gemini ਤਰਫੋਂ ਗਲਤੀ: {str(e)}"

def text_to_speech(text, lang='pa'):
    tts = gTTS(text=text, lang=lang)
    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
    tts.save(temp_file.name)
    return temp_file.name

# ---------------------------
# Combined Function
# ---------------------------
def handle_voice_query(audio_file):
    query = transcribe_audio(audio_file)
    response = get_gemini_response(query)
    audio_path = text_to_speech(response)
    return query, response, audio_path

with gr.Blocks() as demo:
    gr.Markdown("# 🗣️ **ਆਵਾਜ਼ ਰਾਹੀਂ ਪੁੱਛੋ**")
    gr.Markdown("### ਆਪਣਾ ਸਵਾਲ ਆਵਾਜ਼ ਰਾਹੀਂ ਪੁੱਛੋ (ਪੰਜਾਬੀ ਵਿੱਚ)")
    audio_input = gr.Audio(type="filepath", label="🎤 ਸਵਾਲ ਬੋਲੋ")
    query_text = gr.Textbox(label="🔍 ਬੋਲਿਆ ਗਿਆ ਸਵਾਲ")
    gemini_response = gr.Textbox(label="📜 Gemini ਜਵਾਬ")
    audio_output = gr.Audio(label="🔊 ਆਵਾਜ਼ੀ ਜਵਾਬ")
    submit_btn = gr.Button("➡️ ਜਵਾਬ ਲਵੋ")
    submit_btn.click(fn=handle_voice_query,
                        inputs=[audio_input],
                        outputs=[query_text, gemini_response, audio_output])

demo.launch()