🔎 Google Lens OCR API: Image to Text with a Live Standby Endpoint

Extract text from a single image, or a whole batch, using the same engine behind Google Lens. Call it as a live REST endpoint for one image at a time (no cold start), or submit a batch of image URLs, Base64 payloads, or Apify key-value store records in one run. Every submitted image returns one correlated result with its status, detected language, dimensions, word count, timing, and any real error.

Use the output for document indexing, searchable archives, translation workflows, content moderation, accessibility pipelines, RAG preparation, and AI agent tool calls.

Copy to your AI assistant

getascraper/google-lens-ocr on Apify. Two ways to call it:
1) Standby REST API (no cold start, one image per call): find this Actor's Standby hostname on its
   Standby tab in Apify Console, then GET https://<standby-hostname>/ocr?imageUrl=...&outputDetail=full&token=TOKEN
2) Batch run via the Apify client: ApifyClient("TOKEN").actor("getascraper/google-lens-ocr").call(run_input={"imageUrl": "..."}), then client.dataset(run["defaultDatasetId"]).list_items().items for results.
Key inputs: imageUrl: string (a single image), outputDetail: string (text_only|lines|full|paragraphs|words), translateTo: string (optional language code). Batch inputs (imageUrls, imagesBase64, imageKvsRecords) also available for many images in one run.
Full actor spec (input schema, output dataset fields, README): GET https://api.apify.com/v2/acts/getascraper~google-lens-ocr/builds/default (Bearer TOKEN) → inputSchema, actorDefinition.storages.dataset, readme.
Get a token: https://console.apify.com/account/integrations

✨ What this Actor gives you

• A live Standby endpoint: Call GET /ocr?imageUrl=... for a single image with no container cold start, alongside normal batch runs.
• Four input modes: One image URL for the common case, plus bulk URLs, Base64 image data, and Apify key-value store records for batches.
• Stable correlation: Supply your own inputId, or use deterministic IDs assigned in input order.
• Honest batch rows: Successful, partial, and failed inputs all remain visible.
• Source dimensions: Get the original image width and height when the image can be decoded.
• Detected language and writing direction: Know whether text reads left-to-right, right-to-left, or top-to-bottom.
• Real word, line, and paragraph geometry: Every box comes directly from Google's own response. Nothing is estimated or interpolated.
• Detected regions: Salient regions and objects Google's own response identifies in the image, at no extra cost.
• Optional translation: Request a target language while retaining the original OCR text.
• Bounded concurrency: Process batches without launching every image request at once.
• Run summary: Review submitted, successful, partial, and failed counts in RUN_SUMMARY.

🎯 Common workflows

• AI agents and MCP tools: Call the Standby endpoint as a fast, stateless OCR tool with no run-management overhead.
• AI and RAG teams: Turn screenshots and scanned pages into searchable text with source correlation.
• Automation teams: Process receipt, label, menu, poster, and document image batches.
• Localization teams: Extract original text and request a translated version in the same row.
• Data operations teams: Reconcile every input against a clear success, partial, or failure status.
• Developers: Use real word-level boxes and writing direction for layout reconstruction and highlighting.

⚡ Call it live, or run it as a batch

For a single image, call the Standby endpoint directly instead of starting a run. Find this Actor's Standby hostname on its Standby tab in Apify Console, then:

GET https://<standby-hostname>/ocr?imageUrl=https://example.com/photo.jpg&outputDetail=full&token=YOUR_TOKEN

It answers in about a second, since there is no container start-up wait once the Actor is warm.

For many images, run the Actor normally:

1. Open the Actor in Apify Console.
2. Add a single image URL, or open "Batch and advanced sources" for a bulk list, Base64 data, or key-value store records.
3. Optionally add input IDs and a translation target.
4. Choose the output detail and concurrency.
5. Start the run.
6. Open the dataset for correlated rows or RUN_SUMMARY for run totals.

📥 Input

Field	Type	Required	What it controls
imageUrl	string	Conditional	One public HTTP or HTTPS image URL. This is all most runs need.
imageUrlInputId	string	No	Correlation ID for imageUrl. Defaults to single-1.
imageUrls	array	Conditional	Bulk URL objects, for batches. Each item can include url and userData.inputId.
imagesBase64	array	Conditional	Objects containing data and an optional inputId. Raw Base64 and image data URIs are accepted.
imageKvsRecords	array	Conditional	Objects containing key, optional storeId, and optional inputId.
outputDetail	string	No	text_only, lines, full (default), paragraphs (adds grouping and writing direction), or words (adds every word's own box and rotation).
translateTo	string	No	Target language code such as es, de, or pt-BR.
maxConcurrency	integer	No	Images processed at once in a batch run, from 1 to 10.

At least one of imageUrl, imageUrls, imagesBase64, or imageKvsRecords must be provided.

URL batch example

{
    "imageUrls": [
        {
            "url": "https://tesseract.projectnaptha.com/img/eng_bw.png",
            "userData": { "inputId": "poem-page-1" }
        },
        {
            "url": "https://example.com/document-page-2.png",
            "userData": { "inputId": "document-page-2" }
        }
    ],
    "outputDetail": "full",
    "translateTo": "es",
    "maxConcurrency": 3
}

Apify storage example

{
    "imageKvsRecords": [
        {
            "storeId": "my-image-store",
            "key": "receipts/july-001.png",
            "inputId": "receipt-july-001"
        }
    ],
    "outputDetail": "lines"
}

The default key-value store is used when storeId is omitted. A storage record can contain binary image data, a Base64 string, or a JSON object with a Base64 data field.

Recurring document OCR workflow

Use the same imageUrls input from an Apify schedule. Keep inputId stable so downstream systems can reconcile each image across runs.

{
    "imageUrls": [
        {
            "url": "https://example.com/invoices/2026-08-01.png",
            "userData": { "inputId": "invoice-2026-08-01" }
        }
    ],
    "outputDetail": "full"
}

📤 Output

The Actor writes one row for each submitted image. This abbreviated example comes from the public Tesseract sample image:

{
    "inputId": "sample-1",
    "sourceType": "URL",
    "sourceReference": "https://tesseract.projectnaptha.com/img/eng_bw.png",
    "imageUrl": "https://tesseract.projectnaptha.com/img/eng_bw.png",
    "status": "SUCCEEDED",
    "language": "en",
    "fullText": "Mild Splendour of the various-vested Night!\nMother of wildly-working visions! hail!\nI watch thy gliding, while with watery light\nThy weak eye glimmers through a fleecy veil;\nAnd when thou lovest thy pale orb to shroud\nBehind the gather'd blackness lost on high;\nAnd when thou dartest from the wind-rent cloud\nThy placid lightning o'er the awaken'd sky.",
    "translationTarget": "es",
    "wordCount": 58,
    "imageWidth": 1486,
    "imageHeight": 668,
    "lineGeometryAvailable": true,
    "wordGeometryAvailable": false,
    "geometryLevel": "LINE",
    "durationMs": 3154,
    "processedAt": "2026-08-01T16:51:13.248Z"
}

Result status

Status	Meaning
SUCCEEDED	OCR completed. Requested translation also completed when text was available.
PARTIAL	OCR completed, but an optional translation request failed. OCR text remains in the row.
FAILED	The image could not be loaded, decoded, or processed. The row contains errorCode and errorMessage.

Field reference

Field	Description
inputId	User-provided or deterministic correlation ID.
sourceType	URL, BASE64, or KEY_VALUE_STORE.
sourceReference	URL or storage record reference. Base64 content is never copied into this field.
status	Per-input processing outcome.
language	Language reported by Google, for the whole image.
fullText	Extracted lines joined with newline characters.
translatedText	Real translated text when requested and completed.
wordCount	Whitespace-delimited word count calculated from fullText.
imageWidth, imageHeight	Source image dimensions in pixels.
lineGeometryAvailable	Whether at least one genuine line box is present.
wordGeometryAvailable	Whether at least one genuine word box is present. Only ever true when Output detail is words.
geometryLevel	WORD or LINE, whichever is the finest real geometry present in this row. Omitted for text-only rows.
lines	Extracted lines with normalized and pixel geometry when available.
paragraphs	Present when Output detail is paragraphs or words: each paragraph's writing direction, joined text, and (at words) every word's own box and rotation.
regions	Present at the same tiers: salient regions and objects Google's own response identifies, each with a real box when available.
durationMs	Total processing time for that input.
errorCode, errorMessage	Real failure details for partial or failed rows.

One real element from the sample row's lines array:

{
    "text": "Mild Splendour of the various-vested Night!",
    "boundingBox": {
        "normalized": {
            "centerX": 0.44486331939697266,
            "centerY": 0.1067144051194191,
            "width": 0.8516666889190674,
            "height": 0.11873840540647507
        },
        "pixel": {
            "x": 28,
            "y": 32,
            "width": 1266,
            "height": 79
        }
    }
}

With outputDetail: "words" on the same image, the first paragraph's first word looks like this (also real, not estimated):

{
    "writingDirection": "LTR",
    "text": "Mild Splendour of the various-vested Night! Mother of wildly-working visions! hail!",
    "words": [
        {
            "text": "Mild",
            "boundingBox": {
                "normalized": { "centerX": 0.067, "centerY": 0.1035, "width": 0.0958, "height": 0.1169 },
                "pixel": { "x": 28, "y": 30, "width": 142, "height": 78 },
                "rotation": 0.0049304598942399025
            }
        }
    ]
}

🛡️ Data integrity and limits

• The Actor does not fill missing values with invented labels, zero coordinates, or placeholder text.
• Word, line, paragraph, and region boxes are never estimated or interpolated. Every box, including rotation, comes directly from Google's own response.
• A known full-image geometry fallback from the upstream parser is removed at every level instead of being presented as a precise box.
• Input images are limited to 25 MB each.
• Translation is optional. If it fails after OCR succeeds, the row is marked PARTIAL and keeps the original text.
• OCR and translation depend on external services, so response time and availability can vary.
• Only process images that you are authorized to use.

💳 Pricing

The repository's intended PPE configuration charges the Processed OCR image event for successful or partial OCR results while keeping failed audit rows visible. The active Store pricing is configured separately from the Actor build, so verify the live pricing record and each run's chargedEventCounts before relying on a failure-free billing boundary.

❓ FAQ

Does the Actor keep batch order?

Yes. Rows are pushed in the same order as the normalized input list, even when images finish at different times.

Can I match results to my own database records?

Yes. Add a unique inputId to each item. The same value appears in its dataset row.

Does it return word bounding boxes?

Yes, when Output detail is set to words. Every word gets its own real box (from Google's own response, never estimated), with rotation. full and paragraphs stay at line-level geometry to keep the default payload small.

What happens when one image fails?

The rest of the batch continues. The failed image receives its own FAILED row with an error code and message.

What happens when translation fails?

Valid OCR data is retained, and the row is marked PARTIAL.

Does it run as a Standby web server?

Yes. Find this Actor's Standby hostname on its Standby tab in Apify Console, then call GET /ocr?imageUrl=... for single-image requests with no cold start. Batch runs (imageUrls, imagesBase64, imageKvsRecords) are only available through a normal run, not through Standby.

⭐ Was this useful?

⭐ ⭐ ⭐ ⭐ ⭐ If this Actor made your image batch easier to audit, leave a rating. Your review helps other automation and AI teams find it and tells us which workflows to improve next.

★  Rate this Actor on Apify

🔗 Other actors

• Google Lens Visual Search ↗: Find visual matches, descriptions, and related links for an image.
• Bulk Image Downloader ↗: Download image batches with metadata, hashes, and Apify storage output.
• arXiv RAG Extractor ↗: Extract research papers as structured text for RAG pipelines.