Upload folder using huggingface_hub

.github/workflows/sync.yml

@@ -0,0 +1,17 @@
+name: Sync to Hugging Face hub
+on:
+  push:
+    branches: [main]
+
+jobs:
+  sync-to-hub:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+          lfs: true
+      - name: Push to hub
+        env:
+          HF_TOKEN: ${{ secrets.HF_TOKEN }}
+        run: git push https://thatupiso:[email protected]/spaces/thatupiso/Podcastfy.ai_demo main 

.gitignore

@@ -2,7 +2,6 @@
 
 specs/
 docs/
-data/
 
 *.ipynb
 

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----
+MIIFazCCA1OgAwIBAgIRAIIQz7DSQONZRGPgu2OCiwAwDQYJKoZIhvcNAQELBQAw
+TzELMAkGA1UEBhMCVVMxKTAnBgNVBAoTIEludGVybmV0IFNlY3VyaXR5IFJlc2Vh
+cmNoIEdyb3VwMRUwEwYDVQQDEwxJU1JHIFJvb3QgWDEwHhcNMTUwNjA0MTEwNDM4
+WhcNMzUwNjA0MTEwNDM4WjBPMQswCQYDVQQGEwJVUzEpMCcGA1UEChMgSW50ZXJu
+ZXQgU2VjdXJpdHkgUmVzZWFyY2ggR3JvdXAxFTATBgNVBAMTDElTUkcgUm9vdCBY
+MTCCAiIwDQYJKoZIhvcNAQEBBQADggIPADCCAgoCggIBAK3oJHP0FDfzm54rVygc
+h77ct984kIxuPOZXoHj3dcKi/vVqbvYATyjb3miGbESTtrFj/RQSa78f0uoxmyF+
+0TM8ukj13Xnfs7j/EvEhmkvBioZxaUpmZmyPfjxwv60pIgbz5MDmgK7iS4+3mX6U
+A5/TR5d8mUgjU+g4rk8Kb4Mu0UlXjIB0ttov0DiNewNwIRt18jA8+o+u3dpjq+sW
+T8KOEUt+zwvo/7V3LvSye0rgTBIlDHCNAymg4VMk7BPZ7hm/ELNKjD+Jo2FR3qyH
+B5T0Y3HsLuJvW5iB4YlcNHlsdu87kGJ55tukmi8mxdAQ4Q7e2RCOFvu396j3x+UC
+B5iPNgiV5+I3lg02dZ77DnKxHZu8A/lJBdiB3QW0KtZB6awBdpUKD9jf1b0SHzUv
+KBds0pjBqAlkd25HN7rOrFleaJ1/ctaJxQZBKT5ZPt0m9STJEadao0xAH0ahmbWn
+OlFuhjuefXKnEgV4We0+UXgVCwOPjdAvBbI+e0ocS3MFEvzG6uBQE3xDk3SzynTn
+jh8BCNAw1FtxNrQHusEwMFxIt4I7mKZ9YIqioymCzLq9gwQbooMDQaHWBfEbwrbw
+qHyGO0aoSCqI3Haadr8faqU9GY/rOPNk3sgrDQoo//fb4hVC1CLQJ13hef4Y53CI
+rU7m2Ys6xt0nUW7/vGT1M0NPAgMBAAGjQjBAMA4GA1UdDwEB/wQEAwIBBjAPBgNV
+HRMBAf8EBTADAQH/MB0GA1UdDgQWBBR5tFnme7bl5AFzgAiIyBpY9umbbjANBgkq
+hkiG9w0BAQsFAAOCAgEAVR9YqbyyqFDQDLHYGmkgJykIrGF1XIpu+ILlaS/V9lZL
+ubhzEFnTIZd+50xx+7LSYK05qAvqFyFWhfFQDlnrzuBZ6brJFe+GnY+EgPbk6ZGQ
+3BebYhtF8GaV0nxvwuo77x/Py9auJ/GpsMiu/X1+mvoiBOv/2X/qkSsisRcOj/KK
+NFtY2PwByVS5uCbMiogziUwthDyC3+6WVwW6LLv3xLfHTjuCvjHIInNzktHCgKQ5
+ORAzI4JMPJ+GslWYHb4phowim57iaztXOoJwTdwJx4nLCgdNbOhdjsnvzqvHu7Ur
+TkXWStAmzOVyyghqpZXjFaH3pO3JLF+l+/+sKAIuvtd7u+Nxe5AW0wdeRlN8NwdC
+jNPElpzVmbUq4JUagEiuTDkHzsxHpFKVK7q4+63SM1N95R1NbdWhscdCb+ZAJzVc
+oyi3B43njTOQ5yOf+1CceWxG1bQVs5ZufpsMljq4Ui0/1lvh+wjChP4kqKOJ2qxq
+4RgqsahDYVvTH9w7jXbyLeiNdd8XM2w9U/t7y0Ff/9yi0GE44Za4rF2LN9d11TPA
+mRGunUHBcnWEvgJBQl9nJEiU0Zsnvgc/ubhPgXRR4Xq37Z0j4r7g1SgEEzwxA57d
+emyPxgcYxn/eR44/KJ4EBs+lVDR3veyJm+kXQ99b21/+jh5Xos1AnX5iItreGCc=
+-----END CERTIFICATE-----

README.md

@@ -2,109 +2,34 @@
 title: Podcastfy.ai_demo
 app_file: podcastfy-app/app.py
 sdk: gradio
-sdk_version: 4.44.1
-python_version: 3.11
+sdk_version: 5.4.0
+python_version: "3.11"
+header: mini
 ---
-# Podcastfy.ai
-[![CodeFactor](https://www.codefactor.io/repository/github/souzatharsis/podcastfy/badge)](https://www.codefactor.io/repository/github/souzatharsis/podcastfy)
-[![PyPi Status](https://img.shields.io/pypi/v/podcastfy)](https://pypi.org/project/podcastfy/)
-[![Downloads](https://pepy.tech/badge/podcastfy)](https://pepy.tech/project/podcastfy)
-[![Issues](https://img.shields.io/github/issues-raw/souzatharsis/podcastfy)](https://github.com/souzatharsis/podcastfy/issues)
-[![License: CC BY-NC-SA 4.0](https://img.shields.io/badge/License-CC%20BY--NC--SA%204.0-lightgrey.svg)](https://creativecommons.org/licenses/by-nc-sa/4.0/)
-[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/python/black)
+# Podcastfy.ai demo
+
+Created with ❤️ by Open Source [Podcastfy](https://www.podcastfy.ai)
 
 Transforming Multi-Sourced Text into Captivating Multi-Lingual Audio Conversations with GenAI
 
 https://github.com/user-attachments/assets/f1559e70-9cf9-4576-b48b-87e7dad1dd0b
 
-Podcastfy is an open-source Python package that transforms web content, PDFs, and text into engaging, multi-lingual audio conversations using GenAI. 
+Try [HuggingFace 🤗 space app](https://huggingface.co/spaces/thatupiso/Podcastfy.ai_demo) for a simple use case (URLs -> Audio).
+
+See [Open Source Python package](https://www.podcastfy.ai) and CLI at the original github repo for full customization options.
 
-Unlike UI-based tools focused primarily on note-taking or research synthesis (e.g. NotebookLM ❤️), Podcastfy focuses on the programmatic and bespoke generation of engaging, conversational transcripts and audio from a multitude of text sources therefore enabling customization and scale.
+WARNING: This UI App was not as thoroughly tested as the underlying Python package.
 
 ## Audio Examples
 
 This sample collection is also [available at audio.com](https://audio.com/thatupiso/collections/podcastfy):
-- [English] Book Networks, Crowds, and Markets: [audio](https://audio.com/thatupiso/audio/networks)
-- [English] Research paper: ([audio](https://audio.com/thatupiso/audio/agro-paper) | [pdf](./data/pdf/s41598-024-58826-w.pdf))
+- [English] Youtube Video from YCombinator on LLMs: ([audio](https://audio.com/thatupiso/audio/ycombinator-llms) | [youtube](https://www.youtube.com/watch?v=eBVi_sLaYsc))
+- [English] Book pdf Networks, Crowds, and Markets: [audio](https://audio.com/thatupiso/audio/networks)
+- [English] Research paper on Climate Change in France: ([audio](https://audio.com/thatupiso/audio/agro-paper) | [pdf](./data/pdf/s41598-024-58826-w.pdf))
 - [English] Personal website: ([audio](https://audio.com/thatupiso/audio/tharsis) | [website](https://www.souzatharsis.com))
 - [English] Personal website + youtube video: ([audio](https://audio.com/thatupiso/audio/tharsis-ai) | [website](https://www.souzatharsis.com) | [youtube](https://www.youtube.com/watch?v=sJE1dE2dulg))
 - [French] Website: ([audio](https://audio.com/thatupiso/audio/podcast-fr-agro) | [website](https://agroclim.inrae.fr/))
 - [Portuguese-BR] News article: ([audio](https://audio.com/thatupiso/audio/podcast-thatupiso-br) | [website](https://noticias.uol.com.br/eleicoes/2024/10/03/nova-pesquisa-datafolha-quem-subiu-e-quem-caiu-na-disputa-de-sp-03-10.htm))
-  
-## Quickstart
-
-### Setup
-Before installing, ensure you have Python 3.12 or higher installed on your system.
-
-1. Install from PyPI
-
-  `$ pip install podcastfy`
-
-2. Set up your [API keys](usage/config.md)
-
-3. Ensure you have ffmpeg installed on your system, required for audio processing
-```
-sudo apt update
-sudo apt install ffmpeg
-```
-
-### Python
-```python
-from podcastfy.client import generate_podcast
-
-audio_file = generate_podcast(urls=["<url1>", "<url2>"])
-```
-### CLI
-```
-python -m podcastfy.client --url <url1> --url <url2>
-```
-  
-## Usage
-
-- [Python Package](podcastfy.ipynb)
-
-- [CLI](usage/cli.md)
-
-
-## Contributing
-
-Contributions are welcome! Please feel free to submit a Pull Request - see [Open Issues](https://github.com/souzatharsis/podcastfy/issues) for ideas. But even more excitingly feel free to fork the repo and create your own app! Please let me know if I could be of help.
-
-## Features
-
-- Generate engaging, AI-powered conversational content from multiple sources (URLs and PDFs)
-- Create high-quality transcripts from diverse textual information sources
-- Convert pre-existing transcript files into dynamic podcast episodes
-- Support for multiple advanced text-to-speech models (OpenAI and ElevenLabs) for natural-sounding audio
-- Support for multiple languages, enabling global content creation
-- Seamlessly integrate CLI for streamlined workflows
-
-## Example Use Cases
-
-1. **Content Summarization**: Busy professionals can stay informed on industry trends by listening to concise audio summaries of multiple articles, saving time and gaining knowledge efficiently.
-
-2. **Language Localization**: Non-native English speakers can access English content in their preferred language, breaking down language barriers and expanding access to global information.
-
-3. **Website Content Marketing**: Companies can increase engagement by repurposing written website content into audio format, providing visitors with the option to read or listen.
-
-4. **Personal Branding**: Job seekers can create unique audio-based personal presentations from their CV or LinkedIn profile, making a memorable impression on potential employers.
-
-5. **Research Paper Summaries**: Graduate students and researchers can quickly review multiple academic papers by listening to concise audio summaries, speeding up the research process.
-
-6. **Long-form Podcast Summarization**: Podcast enthusiasts with limited time can stay updated on their favorite shows by listening to condensed versions of lengthy episodes.
-
-7. **News Briefings**: Commuters can stay informed about daily news during travel time with personalized audio news briefings compiled from their preferred sources.
-
-8. **Educational Content Creation**: Educators can enhance learning accessibility by providing audio versions of course materials, catering to students with different learning styles.
-
-9. **Book Summaries**: Avid readers can preview books efficiently through audio summaries, helping them make informed decisions about which books to read in full.
-
-10. **Conference and Event Recaps**: Professionals can stay updated on important industry events they couldn't attend by listening to audio recaps of conference highlights and key takeaways.
-
-
-## License
-
-This project is licensed under the [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License](https://creativecommons.org/licenses/by-nc-sa/4.0/).
 
 ## Disclaimer
 

podcastfy-app/app.py

@@ -1,127 +1,430 @@
 import gradio as gr
-from podcastfy.client import generate_podcast
 import os
+import tempfile
+import logging
+from podcastfy.client import generate_podcast
 from dotenv import load_dotenv
 
-# Load environment variables from .env file
+# Configure logging
+logging.basicConfig(level=logging.DEBUG)
+logger = logging.getLogger(__name__)
+
+# Load environment variables
 load_dotenv()
 
 def get_api_key(key_name, ui_value):
     return ui_value if ui_value else os.getenv(key_name)
 
-def create_podcast(urls, openai_key, jina_key, gemini_key):
-	try:
-		# Set API keys, prioritizing UI input over .env file
-		os.environ["OPENAI_API_KEY"] = get_api_key("OPENAI_API_KEY", openai_key)
-		os.environ["JINA_API_KEY"] = get_api_key("JINA_API_KEY", jina_key)
-		os.environ["GEMINI_API_KEY"] = get_api_key("GEMINI_API_KEY", gemini_key)
-		
-		url_list = [url.strip() for url in urls.split(',') if url.strip()]
-		
-		if not url_list:
-			return "Please provide at least one URL."
-		
-		audio_file = generate_podcast(urls=url_list)
-		return audio_file
-	except Exception as e:
-		return str(e)
-
-# Create the Gradio interface
-with gr.Blocks(title="Podcastfy.ai", theme=gr.themes.Default()) as iface:
-	gr.Markdown("# Podcastfy.ai demo")
-	gr.Markdown("Generate a podcast from multiple URLs using Podcastfy.")
-	gr.Markdown("For full customization, please check [Podcastfy package](https://github.com/souzatharsis/podcastfy).")
-
-	with gr.Accordion("API Keys", open=False):
-		with gr.Row(variant="panel"):
-			with gr.Column(scale=1):
-				openai_key = gr.Textbox(label="OpenAI API Key", type="password", value=os.getenv("OPENAI_API_KEY", ""))
-				gr.Markdown('<a href="https://platform.openai.com/api-keys" target="_blank">Get OpenAI API Key</a>')
-			with gr.Column(scale=1):
-				jina_key = gr.Textbox(label="Jina API Key", type="password", value=os.getenv("JINA_API_KEY", ""))
-				gr.Markdown('<a href="https://jina.ai/reader/#apiform" target="_blank">Get Jina API Key</a>')
-			with gr.Column(scale=1):
-				gemini_key = gr.Textbox(label="Gemini API Key", type="password", value=os.getenv("GEMINI_API_KEY", ""))
-				gr.Markdown('<a href="https://makersuite.google.com/app/apikey" target="_blank">Get Gemini API Key</a>')
-
-	urls = gr.Textbox(lines=2, placeholder="Enter URLs separated by commas...", label="URLs")
-
-	generate_button = gr.Button("Generate Podcast", variant="primary")
-
-	with gr.Column():
-		gr.Markdown('<p style="color: #666; font-style: italic; margin-bottom: 5px;">Note: Podcast generation may take a couple of minutes.</p>', elem_id="generation-note")
-		audio_output = gr.Audio(type="filepath", label="Generated Podcast")
-
-	generate_button.click(
-		create_podcast,
-		inputs=[urls, openai_key, jina_key, gemini_key],
-		outputs=audio_output
-	)
-
-	gr.Markdown('<p style="text-align: center;">Created with ❤️ by <a href="https://github.com/souzatharsis/podcastfy" target="_blank">Podcastfy</a></p>')
-
-	# Add JavaScript for splash screen and positioning the disclaimer
-	iface.load(js="""
-	function addSplashScreen() {
-		const audioElement = document.querySelector('.audio-wrap');
-		if (audioElement) {
-			const splashScreen = document.createElement('div');
-			splashScreen.id = 'podcast-splash-screen';
-			splashScreen.innerHTML = '<p>Generating podcast... This may take a couple of minutes.</p>';
-			splashScreen.style.cssText = `
-				position: absolute;
-				top: 0;
-				left: 0;
-				right: 0;
-				bottom: 0;
-				background-color: rgba(0, 0, 0, 0.7);
-				color: white;
-				display: flex;
-				justify-content: center;
-				align-items: center;
-				z-index: 1000;
-			`;
-			audioElement.style.position = 'relative';
-			audioElement.appendChild(splashScreen);
-		}
-	}
-
-	function removeSplashScreen() {
-		const splashScreen = document.getElementById('podcast-splash-screen');
-		if (splashScreen) {
-			splashScreen.remove();
-		}
-	}
-
-	function positionGenerationNote() {
-		const noteElement = document.getElementById('generation-note');
-		const audioElement = document.querySelector('.audio-wrap');
-		if (noteElement && audioElement) {
-			noteElement.style.position = 'absolute';
-			noteElement.style.top = '-25px';
-			noteElement.style.left = '0';
-			noteElement.style.zIndex = '10';
-			audioElement.style.position = 'relative';
-		}
-	}
-
-	document.querySelector('#generate_podcast').addEventListener('click', addSplashScreen);
+def process_inputs(
+    text_input, 
+    urls_input,
+    pdf_files,
+    image_files,
+    gemini_key,
+    openai_key,
+    elevenlabs_key,
+    word_count,
+    conversation_style,
+    roles_person1,
+    roles_person2,
+    dialogue_structure,
+    podcast_name,
+    podcast_tagline,
+    tts_model,
+    creativity_level,
+    user_instructions
+):
+    try:
+        logger.info("Starting podcast generation process")
+        
+        # API key handling
+        logger.debug("Setting API keys")
+        os.environ["GEMINI_API_KEY"] = get_api_key("GEMINI_API_KEY", gemini_key)
+        
+        if tts_model == "openai":
+            logger.debug("Setting OpenAI API key")
+            if not openai_key and not os.getenv("OPENAI_API_KEY"):
+                raise ValueError("OpenAI API key is required when using OpenAI TTS model")
+            os.environ["OPENAI_API_KEY"] = get_api_key("OPENAI_API_KEY", openai_key)
+            
+        if tts_model == "elevenlabs":
+            logger.debug("Setting ElevenLabs API key")
+            if not elevenlabs_key and not os.getenv("ELEVENLABS_API_KEY"):
+                raise ValueError("ElevenLabs API key is required when using ElevenLabs TTS model")
+            os.environ["ELEVENLABS_API_KEY"] = get_api_key("ELEVENLABS_API_KEY", elevenlabs_key)
+        
+        # Process URLs
+        urls = [url.strip() for url in urls_input.split('\n') if url.strip()]
+        logger.debug(f"Processed URLs: {urls}")
+        
+        temp_files = []
+        temp_dirs = []
+        
+        # Handle PDF files
+        if pdf_files is not None and len(pdf_files) > 0:
+            logger.info(f"Processing {len(pdf_files)} PDF files")
+            pdf_temp_dir = tempfile.mkdtemp()
+            temp_dirs.append(pdf_temp_dir)
+            
+            for i, pdf_file in enumerate(pdf_files):
+                pdf_path = os.path.join(pdf_temp_dir, f"input_pdf_{i}.pdf")
+                temp_files.append(pdf_path)
+                
+                with open(pdf_path, 'wb') as f:
+                    f.write(pdf_file)
+                urls.append(pdf_path)
+                logger.debug(f"Saved PDF {i} to {pdf_path}")
+        
+        # Handle image files
+        image_paths = []
+        if image_files is not None and len(image_files) > 0:
+            logger.info(f"Processing {len(image_files)} image files")
+            img_temp_dir = tempfile.mkdtemp()
+            temp_dirs.append(img_temp_dir)
+            
+            for i, img_file in enumerate(image_files):
+                # Get file extension from the original name in the file tuple
+                original_name = img_file.orig_name if hasattr(img_file, 'orig_name') else f"image_{i}.jpg"
+                extension = original_name.split('.')[-1]
+                
+                logger.debug(f"Processing image file {i}: {original_name}")
+                img_path = os.path.join(img_temp_dir, f"input_image_{i}.{extension}")
+                temp_files.append(img_path)
+                
+                try:
+                    # Write the bytes directly to the file
+                    with open(img_path, 'wb') as f:
+                        if isinstance(img_file, (tuple, list)):
+                            f.write(img_file[1])  # Write the bytes content
+                        else:
+                            f.write(img_file)     # Write the bytes directly
+                    image_paths.append(img_path)
+                    logger.debug(f"Saved image {i} to {img_path}")
+                except Exception as e:
+                    logger.error(f"Error saving image {i}: {str(e)}")
+                    raise
+        
+        # Prepare conversation config
+        logger.debug("Preparing conversation config")
+        conversation_config = {
+            "word_count": word_count,
+            "conversation_style": conversation_style.split(','),
+            "roles_person1": roles_person1,
+            "roles_person2": roles_person2,
+            "dialogue_structure": dialogue_structure.split(','),
+            "podcast_name": podcast_name,
+            "podcast_tagline": podcast_tagline,
+            "creativity": creativity_level,
+            "user_instructions": user_instructions
+        }
+        
+        # Generate podcast
+        logger.info("Calling generate_podcast function")
+        logger.debug(f"URLs: {urls}")
+        logger.debug(f"Image paths: {image_paths}")
+        logger.debug(f"Text input present: {'Yes' if text_input else 'No'}")
+        
+        audio_file = generate_podcast(
+            urls=urls if urls else None,
+            text=text_input if text_input else None,
+            image_paths=image_paths if image_paths else None,
+            tts_model=tts_model,
+            conversation_config=conversation_config
+        )
+        
+        logger.info("Podcast generation completed")
+        
+        # Cleanup
+        logger.debug("Cleaning up temporary files")
+        for file_path in temp_files:
+            if os.path.exists(file_path):
+                os.unlink(file_path)
+                logger.debug(f"Removed temp file: {file_path}")
+        for dir_path in temp_dirs:
+            if os.path.exists(dir_path):
+                os.rmdir(dir_path)
+                logger.debug(f"Removed temp directory: {dir_path}")
+        
+        return audio_file
+        
+    except Exception as e:
+        logger.error(f"Error in process_inputs: {str(e)}", exc_info=True)
+        # Cleanup on error
+        for file_path in temp_files:
+            if os.path.exists(file_path):
+                os.unlink(file_path)
+        for dir_path in temp_dirs:
+            if os.path.exists(dir_path):
+                os.rmdir(dir_path)
+        return str(e)
 
-	// Use a MutationObserver to watch for changes in the audio element
-	const observer = new MutationObserver((mutations) => {
-		mutations.forEach((mutation) => {
-			if (mutation.type === 'childList' && mutation.addedNodes.length > 0) {
-				removeSplashScreen();
-				positionGenerationNote();
-			}
-		});
-	});
+# Create Gradio interface with updated theme
+with gr.Blocks(
+    title="Podcastfy.ai",
+    theme=gr.themes.Base(
+        primary_hue="blue",
+        secondary_hue="slate",
+        neutral_hue="slate"
+    ),
+    css="""
+        /* Move toggle arrow to left side */
+        .gr-accordion {
+            --accordion-arrow-size: 1.5em;
+        }
+        .gr-accordion > .label-wrap {
+            flex-direction: row !important;
+            justify-content: flex-start !important;
+            gap: 1em;
+        }
+        .gr-accordion > .label-wrap > .icon {
+            order: -1;
+        }
+    """
+) as demo:
+    # Add theme toggle at the top
+    with gr.Row():
+        gr.Markdown("# 🎙️ Podcastfy.ai")
+        theme_btn = gr.Button("🌓", scale=0, min_width=0)
 
-	observer.observe(document.querySelector('.audio-wrap'), { childList: true, subtree: true });
+    gr.Markdown("An Open Source alternative to NotebookLM's podcast feature")
+    gr.Markdown("For full customization, please check Python package on github (www.podcastfy.ai).")
+    
+    with gr.Tab("Content"):
+        # API Keys Section
+        gr.Markdown(
+            """
+            <h2 style='color: #2196F3; margin-bottom: 10px; padding: 10px 0;'>
+                🔑 API Keys
+            </h2>
+            """,
+            elem_classes=["section-header"]
+        )
+        with gr.Accordion("Configure API Keys", open=False):
+            gemini_key = gr.Textbox(
+                label="Gemini API Key", 
+                type="password", 
+                value=os.getenv("GEMINI_API_KEY", ""),
+                info="Required"
+            )
+            openai_key = gr.Textbox(
+                label="OpenAI API Key", 
+                type="password", 
+                value=os.getenv("OPENAI_API_KEY", ""),
+                info="Required only if using OpenAI TTS model"
+            )
+            elevenlabs_key = gr.Textbox(
+                label="ElevenLabs API Key",
+                type="password",
+                value=os.getenv("ELEVENLABS_API_KEY", ""),
+                info="Required only if using ElevenLabs TTS model [recommended]"
+            )
+        
+        # Content Input Section
+        gr.Markdown(
+            """
+            <h2 style='color: #2196F3; margin-bottom: 10px; padding: 10px 0;'>
+                📝 Input Content
+            </h2>
+            """,
+            elem_classes=["section-header"]
+        )
+        with gr.Accordion("Configure Input Content", open=False):
+            with gr.Group():
+                text_input = gr.Textbox(
+                    label="Text Input", 
+                    placeholder="Enter or paste text here...", 
+                    lines=3
+                )
+                urls_input = gr.Textbox(
+                    label="URLs", 
+                    placeholder="Enter URLs (one per line) - supports websites and YouTube videos.", 
+                    lines=3
+                )
+                
+                # Place PDF and Image uploads side by side
+                with gr.Row():
+                    with gr.Column():
+                        pdf_files = gr.Files(  # Changed from gr.File to gr.Files
+                            label="Upload PDFs",  # Updated label
+                            file_types=[".pdf"],
+                            type="binary"
+                        )
+                        gr.Markdown("*Upload one or more PDF files to generate podcast from*", elem_classes=["file-info"])
+                    
+                    with gr.Column():
+                        image_files = gr.Files(
+                            label="Upload Images",
+                            file_types=["image"],
+                            type="binary"
+                        )
+                        gr.Markdown("*Upload one or more images to generate podcast from*", elem_classes=["file-info"])
+        
+        # Customization Section
+        gr.Markdown(
+            """
+            <h2 style='color: #2196F3; margin-bottom: 10px; padding: 10px 0;'>
+                ⚙️ Customization Options
+            </h2>
+            """,
+            elem_classes=["section-header"]
+        )
+        with gr.Accordion("Configure Podcast Settings", open=False):
+            # Basic Settings
+            gr.Markdown(
+                """
+                <h3 style='color: #1976D2; margin: 15px 0 10px 0;'>
+                    📊 Basic Settings
+                </h3>
+                """,
+            )
+            word_count = gr.Slider(
+                minimum=500, 
+                maximum=5000, 
+                value=2000, 
+                step=100, 
+                label="Word Count",
+                info="Target word count for the generated content"
+            )
+            
+            conversation_style = gr.Textbox(
+                label="Conversation Style", 
+                value="engaging,fast-paced,enthusiastic",
+                info="Comma-separated list of styles to apply to the conversation"
+            )
+            
+            # Roles and Structure
+            gr.Markdown(
+                """
+                <h3 style='color: #1976D2; margin: 15px 0 10px 0;'>
+                    👥 Roles and Structure
+                </h3>
+                """,
+            )
+            roles_person1 = gr.Textbox(
+                label="Role of First Speaker",
+                value="main summarizer",
+                info="Role of the first speaker in the conversation"
+            )
+            
+            roles_person2 = gr.Textbox(
+                label="Role of Second Speaker",
+                value="questioner/clarifier",
+                info="Role of the second speaker in the conversation"
+            )
+            
+            dialogue_structure = gr.Textbox(
+                label="Dialogue Structure",
+                value="Introduction,Main Content Summary,Conclusion",
+                info="Comma-separated list of dialogue sections"
+            )
+            
+            # Podcast Identity
+            gr.Markdown(
+                """
+                <h3 style='color: #1976D2; margin: 15px 0 10px 0;'>
+                    🎙️ Podcast Identity
+                </h3>
+                """,
+            )
+            podcast_name = gr.Textbox(
+                label="Podcast Name",
+                value="PODCASTFY",
+                info="Name of the podcast"
+            )
+            
+            podcast_tagline = gr.Textbox(
+                label="Podcast Tagline",
+                value="YOUR PERSONAL GenAI PODCAST",
+                info="Tagline or subtitle for the podcast"
+            )
+            
+            # Voice Settings
+            gr.Markdown(
+                """
+                <h3 style='color: #1976D2; margin: 15px 0 10px 0;'>
+                    🗣️ Voice Settings
+                </h3>
+                """,
+            )
+            tts_model = gr.Radio(
+                choices=["openai", "elevenlabs", "edge"],
+                value="openai",
+                label="Text-to-Speech Model",
+                info="Choose the voice generation model (edge is free but of low quality, others are superior but require API keys)"
+            )
+            
+            # Advanced Settings
+            gr.Markdown(
+                """
+                <h3 style='color: #1976D2; margin: 15px 0 10px 0;'>
+                    🔧 Advanced Settings
+                </h3>
+                """,
+            )
+            creativity_level = gr.Slider(
+                minimum=0, 
+                maximum=1, 
+                value=0.7, 
+                step=0.1, 
+                label="Creativity Level",
+                info="Controls the creativity of the generated conversation (0 for focused/factual, 1 for more creative)"
+            )
+            
+            user_instructions = gr.Textbox(
+                label="Custom Instructions",
+                value="",
+                lines=2,
+                placeholder="Add any specific instructions to guide the conversation...",
+                info="Optional instructions to guide the conversation focus and topics"
+            )
+    
+    # Output Section
+    gr.Markdown(
+        """
+        <h2 style='color: #2196F3; margin-bottom: 10px; padding: 10px 0;'>
+            🎵 Generated Output
+        </h2>
+        """,
+        elem_classes=["section-header"]
+    )
+    with gr.Group():
+        generate_btn = gr.Button("🎙️ Generate Podcast", variant="primary")
+        audio_output = gr.Audio(
+            type="filepath", 
+            label="Generated Podcast"
+        )
+    
+    # Footer
+    gr.Markdown("---")
+    gr.Markdown("Created with ❤️ using [Podcastfy](https://github.com/souzatharsis/podcastfy)")
+    
+    # Handle generation
+    generate_btn.click(
+        process_inputs,
+        inputs=[
+            text_input, urls_input, pdf_files, image_files,
+            gemini_key, openai_key, elevenlabs_key,
+            word_count, conversation_style,
+            roles_person1, roles_person2,
+            dialogue_structure, podcast_name,
+            podcast_tagline, tts_model,
+            creativity_level, user_instructions
+        ],
+        outputs=audio_output
+    )
 
-	// Position the note on initial load
-	window.addEventListener('load', positionGenerationNote);
-	""")
+    # Add theme toggle functionality
+    theme_btn.click(
+        None,
+        None,
+        None,
+        js="""
+        function() {
+            document.querySelector('body').classList.toggle('dark');
+            return [];
+        }
+        """
+    )
 
 if __name__ == "__main__":
-	iface.launch(share=True)
+    demo.queue().launch(share=True)

pyproject.toml

@@ -1,16 +1,16 @@
 [tool.poetry]
-name = "podcastfy-app"
-version = "0.1.0"
-description = "Simple application for podcastfy.ai"
+name = "podcastfy-demo"
+version = "0.2.0"
+description = "Demo for podcastfy"
 authors = ["Tharsis T. P. Souza"]
 readme = "README.md"
 
 [tool.poetry.dependencies]
-python = "^3.12"
-gradio-client = "^1.3.0"
-gradio = "^4.44.1"
+python = "^3.11"
+gradio = "^5.4.0"
+podcastfy = "^0.2.15"
+gradio-client = "^1.4.2"
 python-dotenv = "^1.0.1"
-podcastfy = "^0.1.12"
 
 
 [build-system]

requirements.txt

@@ -1,4 +1,4 @@
-gradio-client==1.3.0
-gradio==4.44.1
-podcastfy==0.1.13
-python-dotenv==1.0.1
+gradio-client==1.4.2
+gradio==5.4.0
+podcastfy==0.2.15
+python-dotenv==1.0.1

tomlbackup.txt

@@ -0,0 +1,18 @@
+[tool.poetry]
+name = "podcastfy-app"
+version = "0.1.0"
+description = "Simple application for podcastfy.ai"
+authors = ["Tharsis T. P. Souza"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.11"
+gradio-client = "^1.3.0"
+gradio = "^4.44.1"
+python-dotenv = "^1.0.1"
+podcastfy = "^0.1.13"
+
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"