PodText AI is a full-stack web application that enables users to create and publish podcasts using AI voice generation and text-to-speech technology. This project integrates OpenAI's DALL-E to generate podcast thumbnails, enhancing the visual appeal of user content.
PodText AI leverages cutting-edge AI technologies to simplify podcast creation and publication. Users can easily generate podcast content using text-to-speech capabilities and enhance their episodes with AI-generated thumbnails. This project showcases the potential of AI in the creative industry, providing a seamless experience for podcast creators.
-
Frontend:
- Next.js
- React
- TypeScript
- TailwindCSS
-
Backend:
- Convex
- Clerk
-
AI Integration:
- OpenAI (DALL-E for thumbnails, AI voice generation, AI chat complettion for generating text)
- AI Voice Generation: Create podcast episodes using text-to-speech technology.
- AI-Generated Thumbnails: Enhance visual appeal with thumbnails generated by OpenAI's DALL-E.
- User Authentication: Secure and seamless user authentication using Clerk.
- Responsive Design: User-friendly on all devices.
- Easy Publishing: Simplified process for creating and publishing podcasts.
To run this project locally, follow these steps:
-
Clone the repository:
https://github.com/HassanChowdhry/PodText-AI.git
-
Navigate to the project directory:
cd podtext-ai -
Install the dependencies:
npm install
-
Start the development server:
npm run dev
After starting the development server, you can access the application by navigating to http://localhost:3000 in your web browser. Sign up or log in to start creating and publishing podcasts.
Feel free to reach out to me for any professional inquiries or questions:
- Email: hassan.chowdhry@dal.ca
- LinkedIn: Hassan Chowdhry
- Website: HassanChowdhry.live
Thank you for exploring PodText AI!