Spectrolipi

Bioacoustics Visualization and Annotation Suite
What is Spectrolipi?

Spectrolipi is an open-source, privacy-focused bioacoustics annotation tool built for researchers, birders, and machine-learning practitioners. It supports full audio spectrogram playback, manual and template-assisted annotation, species labeling, metadata management, audio cutting/filtering, and automatic identification using the BirdNET AI classifier.

No installation is required. To protect data privacy, all audio processing and neural network calculations are executed locally in the browser. No audio data ever leaves your computer.

Metadata & Links
Author / Maintainer
Nishant Bhagwat (nishantnnb)
License Type
GNU General Public License v3.0 (GPL-3.0)
Contact / Support
GitHub Issues
spectrolipi@gmail.com
Dependencies & Software Libraries
Credits & Acknowledgements
BirdNET AI Model
Developed by the K. Lisa Yang Center for Conservation Bioacoustics at the Cornell Lab of Ornithology in collaboration with Chemnitz University of Technology. (Stefan Kahl, Connor Wood, Maximilian Eibl, Holger Klinck). Learn more at the BirdNET-Analyzer repository.
BirdNET Web Port
The TensorFlow.js local classifier implementation is adapted from georg95/birdnet-web.
Xeno-canto Integration
Direct upload support and recordings browsing powered by Xeno-canto's public data sharing API.