DAVID
GONZALEZ

Data Scientist

ZeitZuHelfen

Project Category

Project Main Image

Project Overview

ZeitZuHelfen is a help request platform that bridges the gap between seniors needing assistance and students willing to help. An AI voice-first interface that allows seniors to request help by simply speaking, no typing, no forms, just conversation. For students, a way to engage with the Munich community while earning some rewards.

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.

Results & Impact

  • Enabled seniors to request help using simple AI voice messages—no typing or apps required.
  • Achieved reliable real-time transcription and structured data extraction using Google Gemini.
  • Delivered a fully operational end-to-end system connecting seniors and student volunteers.
  • Built a scalable two-server architecture with clean REST APIs for seamless student interaction.

Project Details

Client: HackaTUM 2025

Timeline: Nov 2025

Role: Backend Developer

Team Size: 3

Technologies Used

Python Telegram Bot API FastAPI SQLAlchemy React Vite TypeScript Gemini API

Key Features

  • Voice-first help requests via Telegram with AI-powered transcription.
  • Automated address validation, confirmation flow, and emergency detection.
  • Web interface for students to browse, accept, and complete requests.

Lessons Learned

Building a voice-first system highlighted the complexity of handling real-world speech, incomplete information, and diverse speaking styles. Designing a reliable confirmation flow and managing multi-step conversations without confusion were key challenges. Integrating multiple external services—Telegram, FFmpeg, Google Gemini, and address validation—required careful error handling and async coordination.

Next time, I would add dedicated session management earlier (e.g., Redis) to improve scalability and support multiple simultaneous senior conversations. I also learned the importance of designing prompts and user flows that remain simple, especially for non-technical users.

Future Improvements

  • Add security code verification and push notifications for students.
  • Develop a mobile app and implement automatic student–senior matching based on location and availability.