Snaplist: A Local AI Listing Writer for Etsy & eBay Sellers

Description and use

Snaplist is a local desktop app that uses the Gemma 3 vision model via Ollama to generate titles, descriptions, and tags for Etsy and eBay listings from product photos. It runs offline, keeps data private, and eliminates API costs, though the 4B model can merge unrelated items and produce short text needing human editing.

Problem

Solo Etsy and eBay sellers repeatedly rewrite similar product descriptions, wasting time and risking inconsistent copy.

Outcome

Snaplist enables one-time desktop listing generation with local inference, eliminating API costs, preserving privacy, and allowing offline use. However, the 4B model can merge unrelated items and produces short descriptions that require human editing.

Workflow

• 1. Launch Snaplist on the seller’s computer. 2. Upload product photos. 3. Choose marketplace (Etsy or eBay) and desired tone. 4. Add any additional facts not visible in photos. 5. Click Generate. 6. Snaplist sends photos to the local Ollama Gemma 3 model via /api/chat. 7. The model returns structured JSON. 8. The UI displays editable title, description, and tags. 9. Seller reviews and edits as needed before publishing.

Evidence

Snaplist is a listing writer for solo sellers on Etsy and eBay. You drop in a few photos of an item, pick a marketplace and a tone, add any facts the photos can't show (condition, size, backstory), and it drafts a title, a description, and up to 13 search tags.

Source

The core is Gemma 3 (4B), an open-weight vision model, served by Ollama on my own MacBook Air.

Source

No silent fallback. If the model fails, you see an error, never fake sample text passed off as AI output.

Source

In my first test I uploaded photos of four unrelated items, and it merged them into one confused listing.

Source