Spaces:
Sleeping
Sleeping
metadata
title: Camouflage
emoji: 🔇
colorFrom: blue
colorTo: purple
sdk: docker
pinned: false
license: mit
short_description: Ultrasonic audio jammer for privacy protection
Camouflage
Ultrasonic audio jamming tool to protect against unauthorized recording
Camouflage generates ultrasonic signals (20-24kHz) that interfere with audio recording devices while remaining inaudible to humans. It operates in two distinct modes:
Features
- Speaker Jammer Mode: Outputs ultrasonic signals through speakers to jam nearby microphones
- System Jammer Mode: Creates virtual audio devices to prevent remote recording during voice calls
- Multi-tone Generation: Uses multiple ultrasonic frequencies for increased effectiveness
- Inaudible Operation: Optimized amplitude settings to remain completely inaudible
- Cross-platform Support: macOS, Linux, and Windows (platform-specific features vary)
Installation
Docker
docker pull nomiswan/nomi.so:latest
docker run nomiswan/nomi.so speaker
From Source
cargo build --release
./target/release/camouflage speaker
Usage
Speaker Jammer Mode
# Run with default settings
camouflage speaker
# Custom frequency and amplitude
camouflage speaker -f 23000 -a 0.3
# Multi-tone jamming
camouflage speaker -n 5 -s 500
System Jammer Mode
# Run with default settings
camouflage system
# Custom mix ratio
camouflage system -m 0.5
Performance
Tested against commercial STT services:
- OpenAI Whisper: 95%+ jamming effectiveness
- Deepgram: 90%+ jamming effectiveness
- CPU Usage: <5% on modern hardware
- Latency: <10ms in system mode
Links
License
MIT License