Live Khutbah Displayer
The Problem
Mosques needed a system to display khutbah translations in real-time for multilingual congregations, but existing solutions were too resource-intensive for budget-friendly edge devices and couldn't handle live voice processing with proper noise removal.
What We Built
- Gemini AI for initial khutbah file alignment (Arabic, Urdu, English)
- Optimized local embedding model for resource-efficient matching
- Custom noise removal and voice enhancement pipeline
- FastAPI backend with WebSocket for lightweight real-time display
- Munsit API integration for live transcription directly on edge devices
Results
- Near-live display latency (<100ms real-time transcription)
- 3 simultaneous languages supported effortlessly
- Runs smoothly on low-end hardware (Raspberry Pi compatible)
- Currently in talks with UAE Awqaf for production deployment
- Packaged as a standalone hardware product using Raspberry Pi
Want results like this?
We can map out an autonomous pipeline for your specific bottleneck in a 15-minute call.
Get a Free AI AuditCLIENT
Confidential / UAE Awqaf
CATEGORY
Hardware & Edge AI
COMPLETION DATE
May 2024
TECH STACK
FastAPIGemini AIWebSocketEmbeddingsRaspberry PiMunsit API