app.py

import gradio as gr
from utils import transcribe_audio, split_story_to_pages, generate_image

def process_input(audio_path, text_input):
    # Priority: Audio > Text
    if audio_path:
        story = transcribe_audio(audio_path)
    elif text_input:
        story = text_input
    else:
        return "Please provide either an audio recording or a text input.", []

    # Process story
    pages = split_story_to_pages(story)
    images = [generate_image(page["image_prompt"]) for page in pages]
    results = [(page["text"], img) for page, img in zip(pages, images)]
    return "", results

with gr.Blocks() as demo:
    gr.Markdown("# 🎨 AI Story Illustrator for Kids")

    with gr.Row():
        audio_input = gr.Audio(type="filepath", label="🎙️ Record or Upload Story (Optional)")
        text_input = gr.Textbox(lines=6, placeholder="Or type/paste your story here...", label="📝 Story Text (Optional)")

    btn = gr.Button("Generate Storybook")

    error_box = gr.Textbox(visible=False, label="Error Message", interactive=False)
    output = gr.Gallery(label="📚 Illustrated Story")

    btn.click(fn=process_input, inputs=[audio_input, text_input], outputs=[error_box, output])

demo.launch()