Multimodal Content Generator

A web application built with Streamlit, LangChain, OpenAI, and ElevenLabs that generates a short story, a matching image, and an audio narration based on a user's creative prompt.

🌟 Features

• AI-generated story using OpenAI's language models
• Image creation via OpenAI's image generation API (DALL·E)
• Voice narration using ElevenLabs text-to-speech
• Interactive UI for selecting genre, tone, image style, and narration voice

🚀 Getting Started

Prerequisites

• Python 3.8+
• OpenAI API key
• ElevenLabs API key

Installation

1. Clone this repository:

   git clone <your-repo-link-here>
   cd multimodal-content-generator

2. Create and activate a virtual environment (optional but recommended):

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install the dependencies:

   pip install -r requirements.txt

4. Set your environment variables:

   • Create a .env file in the project root and add:

     OPENAI_API_KEY=your_openai_api_key
     ELEVENLABS_API_KEY=your_elevenlabs_api_key

Run the App

streamlit run app.py

📄 Usage

1. Enter a creative prompt (e.g., "A dragon who learns to dance").
2. Choose your preferred genre, tone, image style, and narration voice.
3. Click Generate to create a story, an illustration, and a voiceover.

🧰 Tech Stack

• Streamlit
• LangChain
• OpenAI GPT & DALL·E APIs
• ElevenLabs Text-to-Speech

📎 Project Link

<https://chatgpt.com/c/6812406e-35d8-8000-b99a-3c86c426ce84>

💡 License

MIT License

🙏 Acknowledgments

• OpenAI for the GPT and image generation APIs
• ElevenLabs for their speech synthesis API
• Streamlit for easy and elegant web UI

---

Built with ❤️ using AI technologies

=======

Multimodal_Content_Generator