Image & Scanned PDF OCR: Image to Text (Tesseract)
Pricing
$3.00 / 1,000 page read (ocr)s
Image to text: reads the text in images, screenshots and scanned PDFs with Tesseract OCR, offline: no AI, no third-party API. Plain text, per-page confidence, and optional words with bounding boxes, in 27 languages. Respects robots.txt and PDF permissions. Failed files are free.
You can access the Image & Scanned PDF OCR: Image to Text (Tesseract) programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "TV9I2sNQ79dFPWvnc" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/wrentools~scanned-pdf-image-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-wrentools-scanned-pdf-image-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/wrentools~scanned-pdf-image-ocr/runs": { "post": { "operationId": "runs-sync-wrentools-scanned-pdf-image-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/wrentools~scanned-pdf-image-ocr/run-sync": { "post": { "operationId": "run-sync-wrentools-scanned-pdf-image-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "fileUrls": { "title": "Image or PDF URLs", "type": "array", "description": "Links to images (PNG, JPEG, TIFF, GIF, BMP, WebP) or PDFs you are allowed to process. Each file is downloaded once; the site's robots.txt is respected.", "items": { "type": "string" } }, "filesBase64": { "title": "Files as base64", "type": "array", "description": "Files sent inline, for files that are not online: a list of base64 strings, or of objects {\"name\": \"scan.png\", \"data\": \"<base64>\"}. A data: URL prefix is accepted." }, "languages": { "title": "Languages", "type": "array", "description": "The languages printed in the files (at most 3; each one added slows every page). Use the fewest that cover the text.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "ces", "swe", "dan", "nor", "fin", "tur", "ron", "hun", "ell", "rus", "ukr", "vie", "ind", "jpn", "chi_sim", "chi_tra", "kor", "ara", "hin" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Czech", "Swedish", "Danish", "Norwegian", "Finnish", "Turkish", "Romanian", "Hungarian", "Greek", "Russian", "Ukrainian", "Vietnamese", "Indonesian", "Japanese", "Chinese (simplified)", "Chinese (traditional)", "Korean", "Arabic", "Hindi" ] }, "default": [ "eng" ] }, "pageSegmentation": { "title": "Page layout", "enum": [ "auto", "singleColumn", "singleBlock", "sparse" ], "type": "string", "description": "How the text is laid out. Automatic suits most pages; try 'sparse' for forms and photos.", "default": "auto" }, "includePages": { "title": "Include per-page text", "type": "boolean", "description": "Add a 'pages' list with each page's text, confidence and size.", "default": false }, "includeWords": { "title": "Include words with positions", "type": "boolean", "description": "Add each word with its confidence and bounding box (pixels) to the 'pages' list, for layout-aware parsing.", "default": false }, "pdfDpi": { "title": "PDF render resolution (DPI)", "minimum": 72, "maximum": 600, "type": "integer", "description": "PDF pages are rendered at this resolution before OCR. 300 suits most scans; raise it for small print.", "default": 300 }, "maxPagesPerFile": { "title": "Maximum pages per file", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Read at most this many pages of each PDF or multi-page TIFF; longer files are marked truncated. Pages are charged as read.", "default": 100 }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger downloads are stopped and reported as file-too-large, without charge.", "default": 50 }, "requestDelayMs": { "title": "Delay between downloads from one site (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Minimum pause between two downloads from the same site.", "default": 500 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Image & Scanned PDF OCR: Image to Text (Tesseract) from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: