BirdNET-Go

BirdNET-Go is the open-source, AI-powered soundscape analyzer providing 24/7, real-time bird species identification on local hardware.

This is BirdNET-Go: a high-performance, Go-based implementation for continuous avian monitoring. It leverages the core BirdNET AI model, trained on over 6,500 bird species, to deliver real-time detection and classification from an audio source (e.g., soundcard or RTSP stream). The application is designed for low resource usage, running efficiently on platforms like Windows, Linux, macOS, and Raspberry Pi. Key features include a user-friendly web interface for data visualization, support for over 40 languages, and local processing—no internet connection is required for analysis. It also integrates with the BirdWeather API for citizen science contributions and offers real-time log output for OBS overlays, making it a robust tool for researchers and enthusiasts.

https://github.com/tphakala/birdnet-go