An efficient and user-friendly web application built with Next.js 14 that leverages Amazon Transcribe and Amazon S3 services to generate captions automatically from audio/video files. This project provides a seamless solution for captioning multimedia content, making it more accessible and inclusive.
- Amazon Transcribe Integration: Utilizes Amazon Transcribe service to accurately transcribe audio and generate captions from various media formats.
- Amazon S3 Storage: Securely stores uploaded media files and generated transcripts on Amazon S3 for easy retrieval and management.
- Next.js 14 Frontend: Built with the latest version of Next.js, providing a modern and responsive user interface for a smooth captioning experience.
- Next.js Backend: Leverages Next.js's server-side capabilities for efficient handling of file uploads, transcription requests, and caption generation.
- User-friendly Interface: Intuitive and user-friendly interface for seamless media file uploads, transcription monitoring, and caption generation.
- Accessibility: Enhances accessibility by providing captions for multimedia content, benefiting individuals with hearing impairments or those in noisy environments.
This project aims to simplify the captioning process, making it easier for content creators, educators, and organizations to create inclusive and accessible multimedia content.
- Clone the repository:
git clone https://github.com/your-username/auto-caption-generator.git - Install dependencies:
npm install - Copy .enc.example to env
- Configure AWS credentials and services (Transcribe and S3)
- Start the development server:
npm run dev - Open
http://localhost:3000in your browser
Contributions are welcome!
This project is licensed under the MIT License.