Google Lens OCR

Google Lens OCR by Omkar Cloud gets you 🎯 accurate, 🔍 detailed text from any image — read by Google Lens.

Google Lens OCR reads screenshots, documents, signs, receipts and product labels in 100+ languages, so you get the text and can successfully complete your project.

$1 per 1,000 images. And with Apify's free plan you get $5 of credit every month, so your first ~5,000 images each month are free.

This is an excellent Actor made by Omkar Cloud, which is Rated Excellent — 4.7 based on 30 reviews on Trustpilot.

👉 Try Google Lens OCR free — your first ~5,000 images are Free.

What can I get

• 📝 The full text of any image — with its language, in reading order
• 📐 Paragraphs, lines & words with positions — bounding boxes for every block
• 🌐 Translation from 100+ languages — paragraph by paragraph, next to the original
• ⚡ About a second per image — built for thousands of pictures

Why Google Lens OCR

Most other OCR actors fail you in one of four ways:

• 🗄️ Inaccurate, cached, stale data
• 🧩 Low-detail data — a few links per picture, never the full picture
• 💸 Pay more to get the same data
• 🪦 Works today, breaks next month — nobody maintains it

Google Lens OCR is scraped live on every run, priced honestly, and actively maintained.

Example: Text From a Textbook Page

{
  "input_image": "https://s3-us-west-2.amazonaws.com/courses-images/wp-content/uploads/sites/1844/2017/06/15212914/images-textwrap-square.png",
  "mode": "text",
  "language": "en",
  "text": "The simplest model of communication relies on three distinct parts: sender, message, and receiver.",
  "paragraphs": [
    {
      "position": 1,
      "text": "The simplest model of communication relies on three distinct parts: sender, message, and receiver.",
      "writing_direction": "left_to_right",
      "bounding_box": { "x": 0.02107, "y": 0.01537, "width": 0.91379, "height": 0.03692 }
    }
  ]
}

And in Translate mode (a Tokyo restaurant sign, into English):

{
  "source_language": "ja",
  "target_language": "en",
  "status": "success",
  "paragraphs": [
    { "position": 4, "original_text": "一軒まるごと!", "translated_text": "A whole house!" }
  ]
}

Trimmed for readability.

Get Started with 5,000 Free Images

1. Hit Try for Free Button — the input is pre-filled with a textbook page and a Tokyo street sign.
2. Enjoy your data 😎.

What you can scrape

Paste picture links — or web page links, their main image is used. Each picture becomes one row.

Mode	You get
Image to text (OCR)	Full text, language, and paragraphs → lines → words with positions
Translate	The text translated paragraph by paragraph, next to the original and its position

Read part of a picture with Region.

Pricing

High value, Low price.

What	Price	What you get
Images	$1 per 1,000	The text of the picture, or its translation

No start fee — you pay only for the pictures you read. Control your spend with Max pictures: 1,000 pictures ≈ $1.

💡 Apify's free plan includes $5 of credit every month — about 5,000 free images, every month.

👉 Read your first 5,000 images free

Run It from Code

Grab your API token from Integrations Settings here and replace <YOUR_API_TOKEN> below.

Python (pip install apify-client)

from apify_client import ApifyClient

client = ApifyClient("<YOUR_API_TOKEN>")
run = client.actor("omkar-cloud/google-lens-ocr").call(run_input={"images": ["https://upload.wikimedia.org/wikipedia/commons/a/a5/Illuminated_facade_of_a_3-storey_restaurant_with_Japanese_signs_and_red_paper_lanterns%2C_Chiyoda%2C_Tokyo.jpg"], "mode": "translate", "targetLanguage": "en"})
for row in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(row["input_image"], row.get("translated_text") or row.get("text"))

Node.js (npm install apify-client)

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: '<YOUR_API_TOKEN>' });
const run = await client.actor('omkar-cloud/google-lens-ocr').call({ images: ["https://s3-us-west-2.amazonaws.com/courses-images/wp-content/uploads/sites/1844/2017/06/15212914/images-textwrap-square.png"], level: "words" });
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

FAQ

How much does a run cost? $1 per 1,000 images, flat — OCR and translation cost the same.

Which languages work? Google Lens reads 100+ languages, including Japanese, Chinese, Arabic and Hindi, and detects the language for you.

What are the coordinates? Fractions of the picture (0-1) from its top-left corner: x, y, width, height.

💬 Have Questions? We Have Answers.

You're a business owner — we know how hard completing a project can be. So we offer full support: just message us and we'll reply ✅ with a solution within 1 working day.

You are important to us — just message us and we will solve your problem ✅ within 1 working day. 🩷 Pinky Promise 🤙!

Related Actors

• 🔍 Google Lens Scraper — search by image — what it is, visual matches, products with prices. $2.50 per 1,000 images.
• 🔍 Reverse Image Search — every page that uses your picture, with dates. $2.50 per 1,000 images.
• 🔎 Google Search Scraper — full Google results pages: organic, AI Overview, People also ask. $2.50 per 1,000 pages.

Popular Actors by Omkar Cloud

• G2 Product Scraper — G2 product details, ratings & AI-found contacts
• Website Email Contact Scraper — emails, phones & socials from any website
• AliExpress Product Scraper — live product details, SKU variants, stock & shipping
• Booking Scraper — Booking.com hotels: prices, ratings, rooms & amenities
• IMDb Scraper — IMDb titles: ratings, votes, cast, box office & charts

👉 Read your first 5,000 images free now