Describe the photo
A description of the photo in English, written by AI: a caption, alt text for your shop, or a paragraph to start a listing from.
How it works
An AI model describes what it sees in English: one sentence for a caption or alt text, a few, or a paragraph. The same photo always gets the same words. It can be wrong about a colour, a count or what a thing is, more often in the longer forms, and it knows no names, brands or places unless they are written in the photo: read it before you publish it.
- You choose
-
- How much to say: One sentence, A few sentences, A paragraph
- It takes
- One photo at a time, or a whole folder at once in the browser.
- You get
- The description, as text.
- Cost
- Free
In the API
One request a photo, with an API key from the console. POST /v1/caption
curl -X POST "https://api.photos.sh/v1/caption?detail=short" \
-H "Authorization: Bearer $PHOTOS_KEY" \
-H "Content-Type: image/jpeg" \
--data-binary @photo.jpg
More tools to read the product
- Read a labelBarcode, net quantity, dates, lot, ingredients, allergens, nutrition and more, from up to 8 photos of one product.
- Read barcodesEAN, UPC and ITF-14 codes with their check digits verified; QR and others on request.
- Read textEvery line of text in a photo, with where it is, in many languages.
- Find facesWhere each face is, with its eyes, nose and mouth: check photos for people before you publish them.
- Find the coloursThe main colours of a photo, most common first, with their codes and how much of it each covers.
Try it on your own photos.
Create an account, buy a pack when you need one, and drop your first photos into Describe the photo.