📌 Inspiration The inspiration behind this project came from the growing need for accessible, real-time healthcare assistance powered by AI. With voice technology rapidly advancing, I wanted to build a solution that feels like talking to a doctor—instantly and securely.
📚 What I Learned Real-time speech-to-text integration using Vapi AI and AssemblyAI
Secure user authentication with Clerk
Working with NeonDB for cloud-native PostgreSQL
Building scalable UI using Tailwind CSS
Deploying full-stack apps seamlessly on Vercel
Integrating Google Gemini for AI-generated, context-aware medical responses
🛠️ How I Built It Used Next.js and React for the frontend and routing
TypeScript ensured type safety and cleaner code
Integrated Vapi AI for real-time voice input
Connected AssemblyAI for speech-to-text conversion
Leveraged Google Gemini API for AI medical responses
Used Clerk for user authentication and session handling
Connected to NeonDB for cloud-based database
Styled with Tailwind CSS
Deployed the complete SaaS application on Vercel
🧱 Challenges Faced Synchronizing voice input with real-time API responses
Managing latency and maintaining a smooth user experience
Ensuring HIPAA-like data privacy best practices
Integrating multiple third-party APIs efficiently
Debugging real-time voice-to-text pipeline
Built With
- ai
- clerk
- css
- db
- gemini
- neon
- next.js
- react.js
- tailwind
- typescript
- vapi
- vercel

Log in or sign up for Devpost to join the conversation.