Pricing

from $4.20 / 1,000 image reads

Try for free

Go to Apify Store

Image OCR Extractor 🖼️ (image to text extractor)

Try for free

OCR for images: image to text with line and word boxes, confidence and orientation. PNG, JPG, WebP, GIF, BMP, TIFF. Clean-up for low-res photos, 7 languages. No API key.

Pricing

from $4.20 / 1,000 image reads

Rating

0.0

(0)

Developer

Tagada Data

Actor stats

Bookmarked

Total users

Monthly active users

4 days ago

Last modified

Categories

Developer tools

Automation

Image links

urls

Optional

Links to images, one per line (or upload a list). PNG, JPG, WebP, GIF, BMP and TIFF work. Any public https link works, including files stored in an Apify key-value store. Animated GIFs and multi-page TIFFs use their first frame.

Type:array

Output detail

output

Optional

Text: the recognized text and its confidence. Lines: also every line with its box and confidence. Words: also every word with its box and confidence. Boxes are in pixels of the upright original image.

Type:string

Default:lines

Options:

textlineswords

Languages

languages

Optional

Languages printed in the images. Pick up to 2 for mixed text; each extra language slows OCR.

Type:string[]

Max. items:2

Default:

[
  "eng"
]

What the image contains

imageType

Optional

Helps the reader pick the right layout. Document suits scans, screenshots and photos of pages with columns or paragraphs. Use a single block for one paragraph, a single line for a cropped line (captcha-free codes, labels, plates), or scattered text for signs, memes and UI screenshots.

Type:string

Default:document

Options:

documentblocklinesparse

Image clean-up

preprocessing

Optional

Auto converts to grayscale, boosts contrast, enlarges small images and retries a weak read with a hard black-and-white copy. Pick another option to force one treatment or none.

Type:string

Default:auto

Options:

autononegrayscalethreshold

Fix sideways and upside-down images

autoRotate

Optional

When a read is weak or the text runs vertically, detect the orientation and read the image again turned upright. The turn applied is reported as orientationDegrees.

Type:boolean

Default:true

Store Screenshot Url

dainty_screw/store-screenshot-url

Effortlessly capture and extract URL screenshots with the Store Screenshot URL Extractor. This powerful Apify actor is designed to streamline your data collection process, providing high-quality snapshots of web pages with ease. Ideal for market research, content verification, and SEO analysis, this

codemaster devops

5.0

(2)

Bulk Image Downloader & Converter — ZIP, WebP, Resize

masahishop/bulk-image-downloader

Download images from image URLs or from web pages, convert to JPEG/PNG/WebP/AVIF, resize, skip duplicates and get one ZIP. Japanese/CJK file names stay readable. $2 per 1,000 images.

Masahi Shop

Atida Santédiscount France Scraper API: prix et catalogue

scraperseurope/atida-france

Collectez le catalogue public Atida Santédiscount France : prix EUR, marques, EAN, SKU, disponibilité et images. Recherche paginée, API et export JSON, CSV ou Excel pour comparer les produits de parapharmacie.

Scrapers Europe

RSS Feed Reader — RSS, Atom & JSON Feed to Rows

nexgensignal/rss-feed-reader-api

Read any RSS, Atom, RDF or JSON Feed, or give a website and it finds the feed. Get clean rows: title, link, dates, summary text, categories, enclosures and images. Filter by date or keyword, de-duplicated across feeds. Part of NexGen Signal — data tools and official-source data products

NexGen Signal

JSON Schema Record Validator

grounded_goldeneye/json-schema-record-validator

Validate inline JSON records against JSON Schema Draft 2020-12 or Draft 7. Export per-record results, complete counts and bounded error paths. Local references only; no network fetching.

david tan

Dish Photo Matcher (No AI Markup): Food Photos to Menu Items

traveleat/dish-photo-matcher

$0.1/1K photos | Match restaurant food and drink photos to your menu items with Gemini vision. Send photo URLs or a Google Maps place URL (place mode needs your Outscraper key for gallery photos) plus your menu; unmatched photos return null. Your own Gemini key. Not affiliated with Google.

Travel Eat

IKEA Deutschland Scraper API: Produktkatalog und Preise

scraperseurope/ikea-germany

IKEA Deutschland auslesen: Artikelnummern, Produktnamen, EUR-Preise, Maße, Farben, Bilder und Online-Verkaufseignung. Paginierte Suche, API und JSON-, CSV- oder Excel-Export für Katalog- und Preisvergleiche.

Scrapers Europe

AI Menu Parser (Flat Price per Menu) + Allergens

traveleat/ai-menu-parser-flat

$20/1K menus | Parse a menu (up to 10 photos) into dish JSON for one flat price per menu, however many dishes it has: translated names, prices, ingredients and AI-estimated allergens in 15 languages. No API key.

Travel Eat

Image to Text — OCR with line boxes

hermeskd/image-to-text

Image URLs in, the text read from each out: line by line with confidence and bounding boxes, in up to three languages. PNG, JPEG, WebP, TIFF, BMP, GIF. Pay per image.

Logan Parker

Image to Text OCR

cyber1nj3ct0r/image-to-text-ocr

Read the text in images from their web addresses with the Tesseract OCR engine. For each image you get the text, a confidence score, line and word counts and, if you want, every word with its position. 35 languages. Receipts, screenshots, scans and labels.