03 — Work
ZeitZuHelfen
Project Overview
A help request platform that bridges the gap between seniors needing assistance and students willing to help. Features an AI voice-first interface that allows seniors to request help by simply speaking, no typing, no forms, just conversation.
Project Details
- Client
- HackaTUM 2025
- Timeline
- November 2025
- Role
- Backend Developer
- Team
- 3 members
Challenge
Selecting the correct LLM for speech-to-text and data processing. Synchronizing Telegram webhooks, ngrok tunnels, and FastAPI endpoints was tricky. Ensuring a smooth user experience for seniors using voice commands required careful design and testing.
Approach
Voice-First Pipeline: Built a Telegram-based voice system where seniors send audio requests; FFmpeg handles audio conversion and Google Gemini extracts structured data and detects emergencies.
Backend Architecture: Developed a FastAPI backend using async SQLAlchemy, Pydantic validation, and environment-based configuration; runs alongside a Telegram bot server sharing a SQLite database.
Request & User Management: Created endpoints for registration, authentication, and request status transitions for seniors and students.
Student Interface: Exposed REST APIs enabling students to browse, accept, and complete help requests through a lightweight web interface.
Key Results
- —AI voice-first interface for seniors
- —Audio conversion via FFmpeg with Google Gemini
- —Emergency detection system
Technologies Used
- Python
- Telegram Bot API
- FastAPI
- SQLAlchemy
- React
- Vite
- TypeScript
- Gemini API
- ngrok
View & Demo
Key Features
AI voice-first interface via Telegram Bot
Audio processing with FFmpeg and Gemini API
Emergency detection system
Async SQLAlchemy backend
React + Vite student dashboard
Gallery
Image
Image
Image
