Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/sabber-slt/rayvox
Audio and Video transcription with whisper API and Next.js
https://github.com/sabber-slt/rayvox
chakra-ui nextjs transcription typescript whisper
Last synced: about 1 month ago
JSON representation
Audio and Video transcription with whisper API and Next.js
- Host: GitHub
- URL: https://github.com/sabber-slt/rayvox
- Owner: sabber-slt
- License: mit
- Created: 2023-08-26T07:56:31.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2024-03-15T18:26:03.000Z (9 months ago)
- Last Synced: 2024-03-16T23:11:40.801Z (9 months ago)
- Topics: chakra-ui, nextjs, transcription, typescript, whisper
- Language: TypeScript
- Homepage: https://sub.raybod.io
- Size: 493 KB
- Stars: 34
- Watchers: 2
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# RayVox: Audio and Video Transcription & Translation Solution
## **✏️** Introduction
RayVox is a cutting-edge Progressive Web Application (PWA) dedicated to the transcription of audio and video files, ensuring a smooth, accurate, and adaptable experience. Leveraging the advanced Whisper ASR technology. All these features are meticulously designed to function within your browser, ensuring a user-friendly experience.
## ⚡ Note
This app is under development and it is not finished yet. Stay tuned for updates and enhancements as we continue to improve the platform.
## **🚀 Technologies**
- **Next.js:** A React framework for building user-friendly web applications with server-side rendering and static site generation capabilities.
- **PocketBase:** An all-in-one backend solution providing real-time databases, authentication, file storage, and more.
- **Tailwind CSS:** A utility-first CSS framework for rapidly building custom designs without leaving your HTML.
- **Next UI:** A React component library designed for building beautiful and modern interfaces with ease.
- **OpenAI's Whisper ASR:** An advanced automatic speech recognition system for accurate transcriptions.## **⭐ Future Enhancements**
- [ ] **Improved Language Support:** Expand the range of languages available for transcription and translation.
- [ ] **User Authentication:** Implement user authentication and authorization for personalized experiences and data protection.
- [ ] **Enhanced File Management:** Develop a more robust system for managing and organizing files within the application.
- [ ] **Real-Time Transcription:** Integrate real-time transcription capabilities for live audio and video streams.
- [ ] **Customizable Subtitle Styling:** Allow users to customize subtitle styles, including font, color, and positioning.
- [ ] **Accessibility Features:** Incorporate accessibility features such as voice commands and screen reader support.## **⚙️** Getting Started
1. **Clone the Repository**: Start by cloning this repository to your local machine.
```
git clone```
2. **Install Dependencies**: Navigate to the project directory and install the necessary dependencies.
```
cd
npm install```
3. **Run the Application**: Launch the application on your local development server.
```
npm run dev```
Your application should now be running on `http://localhost:3000`.
4. **Upload Your Files**: Simply drag and drop your audio or video files into the designated area and let our tool do the rest.
## **👩🏫** Contributing
We welcome contributions from the community! Whether it's a feature request, bug report, or a pull request, your input is valuable. Please refer to our contributing guidelines for more information on how you can contribute.
## License
This project is licensed under the MIT License - see the [LICENSE](notion://www.notion.so/LICENSE) file for details.