fugleramme

E-ink bird frame for Raspberry Pi - real-time bird detection by audio.

Sorry about the dirty window - squirrels have been stealing the bird food.

[!NOTE] Still in early development: expect the odd bug and a few unpolished edges, with plenty more features to come.

Built on top of BirdNET-Go, which handles the mic, the BirdNET classifier and the detection settings. Fugleramme reads the detections and renders recently-seen birds on an Inky-Impression e-ink panel.

[!TIP] The e-ink panel is not required, although it's recommended for the intended experience. Without one, Fugleramme runs web-only - show the kiosk on a display over HDMI, or open it from any device on the network.

Live on fugleramme.arnegiacomo.dev running from my kitchen window and displaying the actual birds currently heard in my garden (Bergen, Norway).

Hardware, install and operations docs: arnegiacomo.dev/fugleramme

How it works

BirdNET-Go listens on a USB mic and records what it identifies. Fugleramme polls the BirdNET-Go api, matches each species to an illustration, then packs them onto a page, and redraws only when the birds change. There's an admin page that lets you configure what to show, and automatic updates and such.

If you already run BirdNET-Go, point the frame at it instead - on the same machine or anywhere else reachable from your network.

Hardware

A Raspberry Pi 5, an Inky Impression 13.3" (Spectra 6), a USB mic and an A4 frame. Full parts list, alternatives, and why each part: Hardware.

Art

The birds are cut-outs from historic, public-domain natural-history drawings, hand-curated for this project. Each detected species is matched to its illustration, background-removed, and packed onto a textured paper page - larger birds toward the centre, sized by body mass. An empty window shows a bare perch.

Half the point of this project is showing off some amazing public-domain natural-history illustrations: every bird is cut from a real plate, no art is AI-generated (though some has been retouched with AI).

See Adding artwork for manual cutout steps.

No detections	A few visitors	A full garden

Known limitations

• The artwork covers Northern Europe. The plates are Scandinavian and British, so the Nordics, the British Isles and Germany are well covered. Elsewhere not so much (yet).
• The mic matters more than the Pi. Detection is BirdNET-Go's job, and how well it does depends mostly on the mic, where you put it, how many birds are in your area and so on.
• BirdNET-Go OIDC not supported. Currently only Basic Authentication (password) is supported. OIDC is in the works.

Run locally (for development)

uv sync                                       # set up venv
uv run fugleramme-fake-detector               # stand-in BirdNET-Go on :8090
uv run fugleramme-dev                         # start service on :8080 with hot-reload

Install on a Raspberry Pi

From the pi (assuming you have the hardware up and running):

curl -fsSL https://raw.githubusercontent.com/arnegiacomo/fugleramme/main/install.sh | bash

Asks where BirdNET-Go should live and which ports to use, clones the repo, installs the required deps, and starts the frame as a systemd service. NB! Will probably require a reboot on a fresh system.

If the display stays blank after that, see Troubleshooting.

From a blank SD card, see the full install guide.

License

• Code: MIT - see LICENSE.
• Detection (BirdNET-Go, installed separately as a container): CC BY-NC-SA 4.0, non-commercial only. BirdNET model by the Cornell Lab of Ornithology and Chemnitz University of Technology, taxonomy data powered by eBird.org.
• Bird images: each style folder carries its own terms and sources, and its manifest links the plate every file was cut from. classic is CC BY-SA 4.0 - see assets/artwork/classic/ATTRIBUTION.md.
• Label fonts (assets/fonts/): SIL OFL 1.1 - see assets/fonts/ATTRIBUTION.md.
• Bird sizes (assets/bird_sizes.csv): body mass from AVONET (Tobias et al. 2022, Ecology Letters, doi:10.1111/ele.13898), CC BY 4.0.

Prebuilt frames

I've built a few of these. If you'd like one rather than building it yourself, please get in touch.