How can computers learn to recognize birds from sounds? The BirdNET research project uses artificial intelligence neural networks to train computers to identify more than 500 of the most common species of North America and Germany. Help us test this prototype app by recording a file using the internal microphone of your Android device and seeing if BirdNET correctly identifies the probable bird species present in your recording.

Please note: Response time is affected by the need to transfer the audio recordings to our servers in order to process the files. Recording quality may affect results and will vary depending on your device. External microphones will probably increase the recording quality.


BirdNET is a joint project of the Cornell Lab of Ornithology and Chemnitz University of Technology.