MediScribe is an intelligent medical note-taking web application designed to help doctors, students, and healthcare workers quickly convert spoken or written symptoms into structured and readable clinical notes. Built with the MERN stack and powered by AI/ML models and speech-to-text APIs, MediScribe simplifies the tedious documentation process in healthcare.
- ✍️ Smart Symptom Input: Accepts voice or text input to describe symptoms.
- 🧠 AI-Powered Note Structuring: Converts free-form input into structured medical notes using language processing APIs.
- 🔊 Voice-to-Text Support: Use your voice to dictate symptoms, powered by real-time speech recognition.
- 📄 Formatted Output: Clean, professional note output that can be saved or exported.
- 🗂️ Patient History (Future Scope): Store and manage multiple patient records.
Frontend:
- React.js
- CSS
Backend:
- Spring Boot
- MySQL
AI/ML & APIs:
- Fine tuned Gemini API (for note structuring)
- Assembly (for speech-to-text)
- Node.js (v14 or higher)
- npm or yarn package manager
-
Clone the repository
git clone https://github.com/Akenzz/Mediscribe.git cd Mediscribe/mediscribe -
Install dependencies
npm install
-
Configure Environment Variables
Create a
.envfile in themediscribedirectory by copying the example file:cp .env.example .env
Then update the
.envfile with your actual values:# API Configuration VITE_API_BASE_URL=your_api_base_url_here # AssemblyAI API Key for audio transcription VITE_ASSEMBLYAI_API_KEY=your_assemblyai_api_key_here # Password hashing salt (use a secure random string) VITE_PASSWORD_SALT=your_password_salt_here
Important: Never commit your
.envfile to version control. It's already included in.gitignore. -
Run the development server
npm run dev
-
Build for production
npm run build