app.py

import streamlit as st
from gtts import gTTS
from io import BytesIO
from PyPDF2 import PdfReader

st.set_page_config(page_title="📚 PDF to Audio 🎧", page_icon="🎉")

st.markdown("""
    <style>
    body {
        background-color: #F0F8FF;
        font-family: 'Arial', sans-serif;
    }
    h1 {
        color: #1E90FF;
        font-size: 36px;
        text-align: center;
        margin-bottom: 30px;
    }
    h2 {
        color: #00BFFF;
        font-size: 24px;
        margin-bottom: 10px;
    }
    p {
        color: #333;
        font-size: 18px;
    }
    .stAudio {
        margin-bottom: 20px;
    }
    .stTextArea {
        font-size: 18px;
        padding: 10px;
    }
    .stButton {
        background-color: #1E90FF;
        color: #FFF;
        font-size: 18px;
        padding: 10px 20px;
        border-radius: 5px;
        margin-top: 20px;
    }
    </style>
    """, unsafe_allow_html=True)

st.markdown("<h1>📚 PDF to Audio Converter 🎧</h1>", unsafe_allow_html=True)

col1, col2 = st.columns(2)

with col1:
    st.markdown("<h2>📜 PDF File</h2>", unsafe_allow_html=True)
    uploaded_file = st.file_uploader("Choose a file", "pdf")

with col2:
    st.markdown("<h2>🔢 Pages</h2>", unsafe_allow_html=True)
    x = st.slider('Select the number of pages you wish to transcribe', min_value=1, max_value=100, value=1)

if uploaded_file is not None:
    reader = PdfReader(uploaded_file)
    X = len(reader.pages)
    st.markdown(f"<p>Total pages in the PDF: {X}</p>", unsafe_allow_html=True)

    i = 0
    while i <= X and i <= x:
        page = reader.pages[i]
        text = page.extract_text()
        sound_file = BytesIO()
        tts = gTTS(text, lang='en')
        tts.write_to_fp(sound_file)
        st.audio(sound_file, format='audio/mp3')
        st.markdown(f"<p>Read aloud page {i+1} of {X} total pages.</p>", unsafe_allow_html=True)
        i = i + 1

    st.balloons()
    st.markdown("<h2>🎉 That's the whole PDF! Have an awesome day! 🎉</h2>", unsafe_allow_html=True)

st.markdown("<h2>✍️ Text to Audio</h2>", unsafe_allow_html=True)
prompt = st.text_area("Copy/Paste or type in text to have read aloud", height=200)

if prompt:
    st.write(prompt)
    sound_file = BytesIO()
    tts = gTTS(prompt, lang='en')
    tts.write_to_fp(sound_file)
    st.audio(sound_file, format='audio/mp3')

st.markdown("<button class='stButton'>Convert to Audio</button>", unsafe_allow_html=True)