{ "openapi": "3.0.1", "info": { "title": "Image to Text OCR: Images & Scanned PDFs, 24 Languages", "description": "Extract text from image URLs (PNG, JPG, WebP, TIFF, GIF) and scanned PDFs with open-source Tesseract OCR. 24 languages incl. Korean, Japanese, Chinese. Confidence, word boxes, dataset input. Blank pages and failed files are free.", "version": "0.1", "x-build-id": "UTYgvpXi5UCY4zrDT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ctriolab~image-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ctriolab-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ctriolab~image-ocr/runs": { "post": { "operationId": "runs-sync-ctriolab-image-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ctriolab~image-ocr/run-sync": { "post": { "operationId": "run-sync-ctriolab-image-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "imageUrls": { "title": "Image or PDF URLs", "type": "array", "description": "Direct links to images (PNG, JPG, WebP, TIFF, GIF, BMP) or scanned PDFs. The URL must return the file itself, not a web page. Leave empty to read a built-in public domain sample page.", "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "Language(s) of the text. Pick more than one for mixed documents (slower). Default English.", "items": { "type": "string", "enum": [ "eng", "kor", "jpn", "chi_sim", "chi_tra", "spa", "deu", "fra", "por", "ita", "nld", "pol", "rus", "ukr", "tur", "ara", "hin", "vie", "ind", "tha", "swe", "ces", "ell", "heb" ], "enumTitles": [ "English", "Korean", "Japanese", "Chinese (Simplified)", "Chinese (Traditional)", "Spanish", "German", "French", "Portuguese", "Italian", "Dutch", "Polish", "Russian", "Ukrainian", "Turkish", "Arabic", "Hindi", "Vietnamese", "Indonesian", "Thai", "Swedish", "Czech", "Greek", "Hebrew" ] }, "default": [ "eng" ] }, "keyValueStore": { "title": "Or files in an Apify key-value store", "type": "string", "description": "A key-value store in your account that holds images or PDFs. Pick it here and list the record keys below." }, "keyValueStoreKeys": { "title": "Record keys in that store", "type": "array", "description": "Keys of the image or PDF records, for example receipt-01.jpg.", "items": { "type": "string" } }, "datasetId": { "title": "Or read URLs from a dataset", "type": "string", "description": "An Apify dataset (for example from a scraper run) with image or PDF links. Every column of the source row is kept in the result row. In an integration after another Actor use {{resource.defaultDatasetId}}." }, "urlField": { "title": "URL field in that dataset", "type": "string", "description": "Field that holds the link in each dataset item. Dotted paths work, for example images.0.url.", "default": "url" }, "layout": { "title": "Page layout", "enum": [ "auto", "block", "column", "sparse", "line" ], "type": "string", "description": "Tells Tesseract how the text is laid out. Try Sparse for receipts and photos with scattered text.", "default": "auto" }, "grayscale": { "title": "Convert to grayscale", "type": "boolean", "description": "Usually improves results on colored backgrounds.", "default": true }, "upscale": { "title": "Upscale small images", "enum": [ "auto", "2x", "none" ], "type": "string", "description": "Small text is read much better at a larger size. Word boxes are always given in original image pixels.", "default": "auto" }, "deskew": { "title": "Straighten tilted scans (deskew)", "type": "boolean", "description": "Detects a tilt of up to 10 degrees and rotates the page straight before OCR. Word boxes then refer to the straightened page.", "default": false }, "includePages": { "title": "Include per-page results", "type": "boolean", "description": "Add a pages list with the text, confidence and word count of each page.", "default": true }, "includeWords": { "title": "Include word boxes", "type": "boolean", "description": "Add every word with its confidence (0 to 100) and bounding box (left, top, width, height) to each page. Makes rows much larger.", "default": false }, "pages": { "title": "Pages of PDFs and TIFFs", "type": "string", "description": "Optional page selection, for example 1-3, 7, 10- (10 to the end). Empty: all pages up to the limit below." }, "maxPagesPerFile": { "title": "Max pages per file", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Pages after this are not read and not charged.", "default": 50 }, "pdfDpi": { "title": "PDF render resolution (DPI)", "minimum": 72, "maximum": 600, "type": "integer", "description": "300 suits most scans. Use 400 for tiny print. Higher is slower.", "default": 300 }, "pdfPassword": { "title": "PDF password", "type": "string", "description": "Only for password protected PDFs." }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are skipped and not charged.", "default": 50 }, "onlyNew": { "title": "Only new files", "type": "boolean", "description": "Skip URLs this Actor already read in an earlier run with the same monitor name. Useful for scheduled runs over a growing list.", "default": false }, "stateName": { "title": "Monitor name", "type": "string", "description": "Name of the key-value store that remembers read URLs when Only new files is on. Use a different name per list.", "default": "ctriolab-image-ocr-state" } } }, "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 } } } } } } } } } }