Images and video · Apify actor
Captions, descriptions and alt text for every image
Give this tool image links and get back a short caption, a detailed description, alt text that fits the 125-character screen-reader guideline and keyword tags for each one, plus the text written in the image if you want it. Video files get a caption per scene, a timed scene list and a one-paragraph summary. It runs Microsoft's open-source Florence-2 model (MIT licence) inside the actor: no API key, and no image is sent to a third-party AI service.
What it does
AI Image Caption & Alt Text Generator, in short
- Three texts per image for one price: a short
caption, adetailedCaption(up to 3 sentences) andaltTextwithout “image of” filler - Keyword tags from the description, and optionally the text written in the image (OCR)
- Reads screenshots, slides and charts, not only photos
- Video files: frames sampled every 2 seconds, similar frames skipped for free, a caption per scene, a timed
timelineand asummary - Chains with Video Frame Extractor: caption the frames of one of its runs with their timestamps
- Direct image and video file links; social and video platform pages are refused on purpose
Who it's for
Built for
alt attributes on a website, blog or shop catalogue in bulk.Example
Input and output
One dataset row per result, downloadable as JSON, CSV or Excel, or read through the Apify API.
{
"imageUrls": ["https://example.com/shop/products/red-sneaker.jpg"],
"detailLevel": "detailed",
"altTextMaxLength": 125,
"includeTags": true,
"readImageText": false
}From a real run on the actor's built-in sample photo, shortened. Video frames add videoUrl, timestampSeconds and timecode, and each video gets a row with its timeline and summary.
{
"type": "image",
"fileName": "sample-caption-football.jpg",
"width": 1024,
"height": 683,
"status": "ok",
"caption": "A young boy playing soccer on a dirt field.",
"detailedCaption": "A young boy playing soccer on a dirt field. He is wearing a red t-shirt, black shorts, and black sneakers. ...",
"altText": "A young boy playing soccer on a dirt field.",
"altTextLength": 43,
"tags": ["boy", "soccer", "dirt", "field", "red", "t-shirt", "ball"],
"imageText": null,
"processingTimeMs": 2148
}Pricing
Pay per result. Failures are free.
No subscription, no monthly minimum. Apify platform compute is included in the price; Apify also adds a tiny start fee per run ($0.00005 per GB of run memory).
| You run | You pay |
|---|---|
| 1,000 product photos | $4.00 |
| 20 mixed images | $0.08 |
| A 30-second video (7 of 16 frames captioned, 9 similar skipped) | $0.028 |
| A Video Frame Extractor run of 24 frames | $0.096 |
12 dead links + 3 SVG files = $0.00
Not charged:
- Links that fail (404, private, timeout), web pages and other non-image files
- Unsupported formats (SVG, HEIC), blank single-colour images and refused platform links
- Video frames skipped because they look like the previous one
The same price covers the longer paragraph description and the OCR option. Max captioned frames per video (default 60) caps the cost of one video. You can set Maximum cost per run in the run options and the actor stops cleanly when it is reached.
FAQ
Questions
Can I use it for WCAG / accessibility alt text?
Yes. altText is written for screen readers (no “image of”, at most 125 characters by default). Like any AI caption, review alt text for images where the exact meaning matters, such as charts, legal or medical images.
How accurate is it?
On 20 varied test images, the caption named the main subject on all 20; 9 were fully correct, 10 had a wrong detail and 1 was wrong (what a chart shows). Wrong details mostly sit in sentences 2-3 of the detailed caption, so review descriptions where exact facts matter.
Does it send my images to OpenAI or Google?
No. The Florence-2 model runs inside the actor on Apify's servers. Your images are only downloaded from the links you give.
Which languages?
Captions are written in English. Text in the image (OCR) is read best for English and other Latin-script text.
Can I caption Instagram or YouTube content?
No. Those platforms forbid downloading in their terms, so their links are refused (free). Use your own files or files you are allowed to process.
Try AI Image Caption & Alt Text Generator on Apify
Apify's free plan includes monthly platform credit you can use to try it.
Other Kanto Labs tools
Video Frame Extractor
Scene-change keyframes, thumbnails or one frame every N seconds, plus a contact sheet.
Video to LLM Context
Scenes, one keyframe per scene and the transcript per scene, as a ready-to-paste prompt block.
Video to Slides
Every unique slide from a lecture or webinar video, as images, text and one PDF.