A desktop tool for twitchers

See more in
every frame.

BirdWatcher finds and identifies birds in video, turning hours of footage into a clear record of what visited.

Download BirdWatcher
A Goldfinch identified by BirdWatcher in a garden bird feeder video

01

What it does
and why it's useful.

BirdWatcher uses AI to analyse videos, locate birds, and identify their species. You can upload hours of footage from a garden camera, or short videos taken on your mobile phone. The software will generate a folder named after each bird that is identified in the video and in these folders will be images of the birds and the timestamp at which they appear. This is a great way to track what is visiting your feeders throughout the day or to identify birds which you don't know.

02

Currently included

20 UK garden birds.

  • House Sparrow
  • Blue Tit
  • Starling
  • Wood Pigeon
  • Blackbird
  • Robin
  • Goldfinch
  • Great Tit
  • Magpie
  • Long-tailed Tit
  • Chaffinch
  • Dunnock
  • Jackdaw
  • Feral Pigeon
  • Collared Dove
  • Carrion Crow
  • Coal Tit
  • Greenfinch
  • Wren
  • Song Thrush

Latest release

Choose your
way in.

Finding the latest release...

Downloads open the latest release. If a direct download is unavailable, you'll be taken to the release page.

First launch

Install BirdWatcher.

Windows

  1. Run the downloaded .exe installer.
  2. When the security pop-up appears, click More info.
  3. Click Open anyway to start the installation.

macOS

  1. Double-click the downloaded .dmg file.
  2. Drag BirdWatcher into the Applications folder.
  3. Open BirdWatcher from Applications.
  4. If macOS says it cannot open the app, go to System Settings > Privacy & Security and choose Open Anyway. You only need to do this the first time.

Linux

  1. Extract the downloaded .tar.gz archive.
  2. Open the extracted folder in a terminal.
  3. Make the app executable with chmod +x BirdWatcher.
  4. Start it with ./BirdWatcher.

Report an
issue.

Tell us what happened, which version you are using, and how to reproduce the problem. Screenshots and sample videos are helpful too.

Open GitHub issues