app.py

import streamlit as st
import google.generativeai as genai
from gtts import gTTS
from PIL import Image
import os
from dotenv import load_dotenv

load_dotenv()

genai.configure(api_key=os.getenv('GEMINI_API_KEY'))

model = genai.GenerativeModel('gemini-1.5-flash')

def image_to_text(image):
    response = model.generate_content(["Describe this image in such a way that a blind person can understand it in one line of 15 words.",image])
    return response.text
def text_to_speech(text, filename= 'output.mp3'):
    tts= gTTS(text=text,lang='en')
    tts.save(filename)
    return filename

def main():
    st.title("Image to Speech Converter")

    uploaded_file = st.file_uploader("Uplad an image",type=["jpeg","jpg","png"])

    if uploaded_file is not None:
        image = Image.open(uploaded_file)
        st.image(image, caption="Uploaded Image", use_container_width=True)
        
        if st.button("Generate Description"):
            with st.spinner("Processing..."):
                try:
                    # Generate description
                    description = image_to_text(image)
                    
                    # Display description
                    st.subheader("Image Description")
                    st.write(description)
                    
                    # Convert to speech
                    audio_file = text_to_speech(description)
                    
                    # Play audio
                    st.audio(audio_file, format='audio/mp3')
                    
                    # Download button
                    with open(audio_file, "rb") as file:
                        st.download_button(
                            label="Download Audio",
                            data=file,
                            file_name=audio_file,
                            mime="audio/mp3"
                        )
                    
                except Exception as e:
                    st.error(f"Error processing image: {str(e)}")

if __name__ == "__main__":
    main()