app.py

import streamlit as st
from openai import OpenAI
import os
from pathlib import Path
import base64

def create_audio_player(audio_path):
    """Create an HTML audio player for the generated audio file"""
    audio_file = open(audio_path, 'rb')
    audio_bytes = audio_file.read()
    audio_base64 = base64.b64encode(audio_bytes).decode()
    audio_player = f'<audio controls><source src="data:audio/mp3;base64,{audio_base64}" type="audio/mp3"></audio>'
    return audio_player

def main():
    st.title("🗣️ Text to Speech with OpenAI")
    
    # Sidebar for API key
    with st.sidebar:
        st.header("Configuration")
        api_key = st.text_input("Enter your OpenAI API key", type="password")
        st.markdown("""
        ### How to get an API key
        1. Go to [OpenAI API Keys](https://platform.openai.com/api-keys)
        2. Create a new secret key
        3. Copy and paste it here
        """)

    # Main content
    st.markdown("Convert your text to natural-sounding speech using OpenAI's TTS API.")
    
    # Text input
    user_input = st.text_area("Enter the text you want to convert to speech:", 
                             height=150,
                             placeholder="Enter your text here...")
    
    # Voice selection
    voice_option = st.selectbox(
        "Select a voice:",
        ["alloy", "echo", "fable", "onyx", "nova", "shimmer"]
    )
    
    # Create a button to generate audio
    if st.button("Generate Speech"):
        if not api_key:
            st.error("Please enter your OpenAI API key in the sidebar.")
            return
        
        if not user_input:
            st.error("Please enter some text to convert to speech.")
            return
        
        try:
            # Show spinning indicator while processing
            with st.spinner("Generating audio..."):
                # Initialize OpenAI client with the API key
                client = OpenAI(api_key=api_key)
                
                # Create output directory if it doesn't exist
                output_dir = Path("generated_audio")
                output_dir.mkdir(exist_ok=True)
                
                # Generate unique filename
                output_file = output_dir / "output.mp3"
                
                # Generate speech
                response = client.audio.speech.create(
                    model="tts-1",
                    voice=voice_option,
                    input=user_input
                )
                
                # Save the audio file
                response.stream_to_file(str(output_file))
                
                # Display success message
                st.success("Audio generated successfully!")
                
                # Create and display audio player
                st.markdown("### Listen to the generated audio:")
                st.markdown(create_audio_player(output_file), unsafe_allow_html=True)
                
                # Add download button
                with open(output_file, "rb") as file:
                    st.download_button(
                        label="Download Audio",
                        data=file,
                        file_name="generated_speech.mp3",
                        mime="audio/mp3"
                    )
                
        except Exception as e:
            st.error(f"An error occurred: {str(e)}")

if __name__ == "__main__":
    main()