Crop answers where the farm is.Even offline.

Bring a leaf to the CropVox field station. It recognises likely disease, pest damage, nutrient problems and crop stress on the spot, then talks the farmer through what to do next in their own language.

  • 10 crops at launch
  • Diagnosis runs without signal
  • Spoken guidance in five languages
Likely issueOffline
Maize
Fall armyworm
Confidence 92%
Also possible
Stem borer5%
Leaf beetle2%
Guidance ready in Hausa
The CropVox field station open on a wooden crate at the edge of a maize field, showing a fall armyworm result on screen
No signal needed

The core scan runs on the station itself.

14scans saved offline today
  • Diagnosis
  • Spoken guidance
  • Scan history
  • Sync when connected

Built for the people who walk the rows

Farmers notice the problem first. Extension workers and cooperatives are usually the next people they ask. CropVox is designed to sit between them.

A farmer holding up a maize leaf in his field
The farmerSpots damage on a leaf and wants to know what it is today.
Extension workers and farmers discussing armyworm control in a maize field
The extension workerCovers many farms and needs a consistent way to inspect them.
Two women smallholder farmers tending maize
The cooperativeShares one station across hundreds of members.

Photos: Emmanuel Ssekaggo, Tigana Chileshe and McKay Savage via Wikimedia Commons. Credits

A complete crop clinic that closes like a briefcase

Everything a scan needs travels in one sealed case: two cameras, controlled lighting, a screen, a speaker, embedded AI compute and a day of battery.

The CropVox field station open, showing the screen, scan tray, camera arm, wand and controls
  1. 15.6 inch display in the lid. Readable in direct sun and usable with gloves or wet fingers.

  2. A fixed camera above the tray with its own diffused light, so every leaf is photographed the same way at noon or at dusk.

  3. Lay a leaf flat on the backlit tray. The colour strip along its edge lets the model correct for lighting before it reads symptoms.

  4. A second camera on a 3 metre coiled cable for standing plants, stems, pods and leaves too big for the tray.

  5. One large button that works through gloves and mud. Speak and Back sit either side of it.

  6. Sized for a full field day and kept under the 100 Wh airline limit so the station can fly as cabin luggage.

  7. USB-C charging, a 12 to 24 V solar input and an optional LTE antenna behind a rubber flap.

1 / 7

Try a scan

Pick a leaf, set the light and focus, then press Scan. Push a slider too far and the station refuses the photo instead of guessing.

Sharp Light OK Offline
  1. Image checkSharpness and light
  2. Crop and damageFind the plant and the problem area
  3. Rank problemsCompare against the crop catalogue
  4. GuidancePick curated next steps
Ready when you are Press Scan, or tap S on your keyboard.

Results are a demonstration with sample data. The real station runs its models on the device.

A farmer inspecting his maize crop in northern Nigeria Photo: Salihu Aliyu, CC BY-SA 4.0

No network? Keep scanning.

Crop problems are found far from good coverage. The model, the guidance library and the voices are stored on the station, so the farmer gets an answer in the field, not after a trip to town.

Ten widely grown crops at launch

Each crop gets its own catalogue of diseases, pests, nutrient problems and visible stress, trained and checked one crop at a time.

One station serves a whole network of farms

The case moves between farms with an extension worker, or stays at a cooperative where farmers bring leaves to it.

The same inspection on every farm

An extension worker carries the station on their round. Every scan is logged with crop, result and date, so the agency sees what is spreading and where.

40 to 60scans in a working day
1 casereplaces a bag of reference sheets
Extension workers with farmers in a maize field

Size a deployment for your network

It reports likelihood, not certainty

Every result comes with a confidence level and the next most likely options. When the station is unsure, it says so and asks for a better image or an expert, instead of guessing.

Below 50%Asks for another image. Offers to send the case for expert review when connected.
50 to 80%Shows the top options side by side and suggests what to check to tell them apart.
Above 80%Gives the likely problem and curated, locally approved next steps.

Put a field station in your next growing season

The first FS-1 units go out for the 2027 growing season. We are looking for extension programmes, cooperatives and research partners to run them.