app.py

import streamlit as st
from transformers import pipeline
from gtts import gTTS
import os
from io import BytesIO
from PIL import Image
import torch

st.set_page_config(page_title="Your Image to Audio Story", page_icon="🦜")

def img2text(image_path):
    # Load Hugging Face image captioning model
    captioner = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")
    image = Image.open(image_path)
    caption = captioner(image)[0]['generated_text']
    return caption

def text2story(text):
    # Use Hugging Face model to generate a longer story from the caption
    generator = pipeline("text-generation", model="gpt2")
    story = generator(text, max_length=150, num_return_sequences=1)[0]['generated_text']
    return story


def text2audio(text):
    # Convert text to speech using gTTS
    tts = gTTS(text=text, lang='en')
    audio_buffer = BytesIO()
    tts.write_to_fp(audio_buffer)
    audio_buffer.seek(0)
    return audio_buffer



st.header("Turn Your Image to Audio Story")

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

if uploaded_file is not None:
    image = Image.open(uploaded_file)
    #st.image(image, caption="Uploaded Image", use_column_width=True)
    st.image(image, caption="Uploaded Image", use_container_width=True)

    
    # Process Image to Text
    st.text('Processing image to text...')
    scenario = img2text(uploaded_file)
    st.write("**Generated Caption:**", scenario)
    
    # Generate Story
    st.text('Generating a story...')
    story = text2story(scenario)
    st.write("**Generated Story:**", story)
    
    # Convert Story to Audio
    st.text('Generating audio...')
    audio_data = text2audio(story)
    
    # Play button
    if st.button("Play Audio"):
        st.audio(audio_data, format="audio/wav")