Braillience

Braillience makes studying accessible for blind students with voice-controlled flashcards, screen reader support, and AI-generated study materials for inclusive, hands-free learning.

Comment

About Braillience

🧠 What It Does

Braillience is an accessible flashcard learning platform for blind and visually impaired college students. It enables fully voice-driven studying with AI-generated flashcards, speech navigation, and screen reader support. Users can upload PDFs, generate flashcards, and learn hands-free through spoken commands.

🛠️ How We Built It

The frontend is built with React and TypeScript, and the backend uses Node.js + Express.
We integrated VAPI for seamless voice processing and Letta File + Agent to manage intelligent flashcard generation and conversational learning.
Accessibility was designed in from the start — with ARIA markup, keyboard-only navigation, and high-contrast visual themes.

🚧 Challenges We Ran Into

  • Integrating Letta agents with dynamic voice feedback loops.
  • Handling speech-to-text accuracy in noisy environments.
  • Achieving full screen reader and browser compatibility (NVDA, VoiceOver).

🏆 Accomplishments

  • Built a voice-first learning experience end-to-end.
  • Successfully linked Letta AI agents with VAPI voice pipelines.
  • Created a fully accessible workflow from upload → generate → learn → test.

💡 What We Learned

We explored the intersection of AI agents, voice UX, and accessibility engineering.
We learned to design for inclusivity and discovered the complexity behind combining speech systems with real-time learning interfaces.

🚀 What’s Next

  • Expand Gemini AI integration for deeper content understanding.
  • Add multi-language voice support.
  • Launch a mobile PWA for offline study.
  • Partner with universities to pilot Braillience in accessibility programs.
Share this project:

Updates