A web-based application for transcribing, organizing, and summarizing audio recordings with minimal friction and maximum learning value.
This tool replaces traditional transcription services by providing an automated workflow to process short MP3 recordings, detect topics, and create organized summaries. Designed for users who record voice notes and need efficient organization without subscription costs.
This project prioritizes learning and collaboration. All code includes comprehensive comments, documentation targets both beginners and professionals, and contributions from developers at any skill level are welcomed.
- Drag-and-drop MP3 file upload
- Automatic transcription using AI
- Topic detection and organization
- Summary generation combining related notes
- Clean, web-based interface
- Cost-effective operation (~$0.50-1.00/month)
- Frontend: React
- Backend: Node.js
- Transcription: OpenAI Whisper API
- AI Processing: Claude API
- Hosting: Vercel/Netlify
- Version Control: Git/GitHub
🚧 In Development - Currently setting up project foundation and architecture.
Setup instructions will be added as development progresses.
We welcome contributors of all experience levels. Detailed contribution guidelines will be available in docs/CONTRIBUTING.md.
License to be determined