Featherframe

Description

BirdNET is a free, open-source AI model (not an LLM) that listens to birdsong and identifies about 6,500 species by their calls. It is made by the K. Lisa Yang Center for Conservation Bioacoustics at the Cornell Lab of Ornithology and Chemnitz University of Technology, and runs on a Raspberry Pi.

Featherframe is an e-paper panel, matted and framed like a print. It shows the last species BirdNET heard as its illustration from John James Audubon’s The Birds of America (1827–1838) or John Gould’s The Birds of Europe, Australia, Asia and Great Britain: more than 1,300 species, hand-painted and hand-printed in the 1800s, all in the public domain. Real art by real people, not AI art. Browse every plate, matched to its modern species, at historical-bird-plates.wells.ee.

The Featherframe webapp finds the illustration and sends it to the frame. Run it hosted at featherframe.app, free with a frame, or on your BirdNET device, or in Docker on a NAS or home server. It sets the refresh interval, quiet hours, the daily collage and more.

There is an option to generate AI illustrations, but it’s off by default. About 1,350 species have an illustration in one of the books. A species that has none gets a name card, its name set in type (the default), or, if you turn it on, an illustration generated in Audubon’s style by the image model of your choice.

I spent hours crafting a prompt that attempts to reproduce the Audubon style with a high degree of authenticity. I think it looks great, and I personally use it, especially to get beautiful end-of-day summaries of all of the species that BirdNET detected that day. AI-generated images are clearly labeled with a ✦ shape, and not passed off as human-created art. Your own API key is required (OpenAI, Gemini, Replicate, or a self-hosted server), and each illustration costs about $0.04 at the default quality, billed by your provider. Learn more about AI illustrations.

Can’t or don’t want to run BirdNET in your backyard? Featherframe can also display detections from any BirdWeather station in the world. So if you want grandma to see the birds in your yard, or if you want to see detections in Vail or Maui, you can.

Featherframe software is free and open-source. Buying from Wells Workshop supports the original creator (me!) and continued development of this and other projects.

Configurations

• Featherframe 10.3-inch — Grayscale e-paper display in an 8.5 × 11 in frame
• Featherframe 13.3-inch — Six-color e-paper display in an 11 × 14 in frame

What’s inside

• A Seeed XIAO ePaper kit (the e-paper panel, its driver board and a XIAO ESP32-S3 Plus), with Featherframe firmware installed and Wi-Fi setup left for you: either the 10.3” 1404 × 1872 16-gray panel, or the 13.3” 1200 × 1600 Spectra 6 color panel
• A handmade solid walnut frame with tempered glass
• A 2 m USB-C cable

Add-ons

• Backyard Bird Detector — A Raspberry Pi 5 (2 GB) and USB microphone in a small weatherproof enclosure, running BirdNET-Go. Mount it within Wi-Fi range to hear the birds in your own backyard. BirdNET-Go also keeps statistics and can identify some insects, frogs and bats.
• USB power supply — any USB-C phone charger works with the frame.

Note: BirdNET-Go is pre-installed as-is and is not created, sold, or maintained by Wells Workshop. Setting up your Raspberry Pi for Wi-Fi access and configuring BirdNET-Go can be a technical process, but is well documented in the BirdNET-Go wiki.

Requirements

• A BirdNET-Pi or BirdNET-Go station, or the ID of any public BirdWeather station
• 2.4 GHz Wi-Fi where the frame hangs
• A USB-C power supply (any phone charger)
• Somewhere to run the Featherframe webapp: hosted at featherframe.app, free with a frame, or your own BirdNET device or Docker host

Software is licensed under the Apache License 2.0. The illustrations are in the public domain.

Note: while 3D renders are meticulously rendered to give you a realistic sense of what each product looks like, they're not 100% perfect. Some variation or inconsistencies may exist that have little to no impact on aesthetics or functionality, unless otherwise noted. If you have questions or concerns, please ask before purchasing. Thank you!