How can computers learn to recognize birds from sounds? The BirdNET research project uses artificial intelligence and neural networks to train computers to identify nearly 3,000 of the most common species of North America and Europe. You can record a file using the internal microphone of your iOS device and see if BirdNET correctly identifies the probable bird species present in your recording. Get to know the birds around you and help us to collect observations by submitting your recordings.
BirdNET is a joint project of the Cornell Lab of Ornithology and Chemnitz University of Technology.
Resolved playback issues.
Ratings and Reviews
Great app, but....
I’ve been using the app for a week and it is very accurate for western Maine birds. Great for the high pitched warblers that are on the edges of my hearing range.
My biggest issue is that it freezes up and stops analyzing about every twenty analyses. At the times it’s frozen up (with the infinite spinning orb) there has been plenty of cell signal on my phone. Any suggestions of what to do in the field to correct this? Turning the phone off and on does not work. The only thing that works is to delete and reload the app. Big pain while in the field!
I agree with another reviewer that it would be useful to submit feedback when multiple birds have resulted in the analysis. Often it’s right on one but not on all. Seems this would be good to know.
Overall great despite some issues
First of all, this is a fantastic tool! You need to learn how to use it, but once you do it’s quite useful. Keep in mind, it’s far from perfect as a bird ID tool, as it often misidentifies with high certainty. You need to use it with other information if using it to ID. I wish it would use location and date information as Merlin Bird ID does to filter possibilities. For example, it was highly certain this morning’s yellow-green vireo was a red-eyed vireo; there’s no way it could be the red-eyed at my location this time of year. Duh!
There is one annoyingly missing feature: the ability to bulk delete observations. Or at least to swipe-delete observations. Right now it’s a 3-click process. Multiply that times tens or hundreds…
This app is amazing. As an experienced birder I still puzzle over the trills of several species. The app provides virtually instant identification that has helped to reinforce (or correct!) my personal ID. And when I hear an unusual version of a song or only a partial song it has been quite reliable.
It’s also great that it records for later analysis if I’m out of cell range.
I’m not sure if this can be addressed, but it is sometimes difficult to get a good result when there are several birds vocalizing at the same time. My ear recognizes the separate songs while BirdNET seems “confused.” Any suggestions?
Data Not Linked to You
The following data may be collected but it is not linked to your identity:
- User Content
Privacy practices may vary, for example, based on the features you use or your age. Learn More
- Stefan Kahl
- 56.3 MB
- Requires iOS 13.0 or later.
- Requires iPadOS 13.0 or later.
- iPod touch
- Requires iOS 13.0 or later.
English, Czech, Dutch, French, German, Italian, Lithuanian, Polish, Portuguese, Russian, Spanish, Ukrainian
- Age Rating
- © 2021 Stefan Kahl and Holger Klinck
With Family Sharing set up, up to six family members can use this app.