{ "openapi": "3.0.1", "info": { "title": "Scanned PDF OCR: PDF & Image to Text (Bulk, 17 Languages)", "description": "Scanned PDF OCR for PDFs and images (PNG, JPG, TIFF, WebP, BMP). Tesseract text per page with confidence scores, 17 languages. Auto mode extracts existing text layers for free and OCRs only scanned pages. $2 per 1,000 OCR pages.", "version": "1.0", "x-build-id": "ZJjSe522Uz2anFN4x" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/globose_talent_mn9~pdf-image-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-globose_talent_mn9-pdf-image-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/globose_talent_mn9~pdf-image-ocr/runs": { "post": { "operationId": "runs-sync-globose_talent_mn9-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/globose_talent_mn9~pdf-image-ocr/run-sync": { "post": { "operationId": "run-sync-globose_talent_mn9-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", "required": [ "fileUrls" ], "properties": { "fileUrls": { "title": "PDF or image URLs", "type": "array", "description": "Direct links to scanned PDFs or images (PNG, JPG, TIFF, WebP, BMP), one per line. Redirects are followed.", "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "Languages in the documents. Pick 1-3 for best speed and accuracy.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "ita", "por", "nld", "pol", "tur", "rus", "ukr", "heb", "ara", "hin", "chi_sim", "jpn", "kor" ], "enumTitles": [ "English", "German", "French", "Spanish", "Italian", "Portuguese", "Dutch", "Polish", "Turkish", "Russian", "Ukrainian", "Hebrew", "Arabic", "Hindi", "Chinese (simplified)", "Japanese", "Korean" ] }, "default": [ "eng" ] }, "mode": { "title": "Mode", "enum": [ "auto", "ocr-all" ], "type": "string", "description": "Auto mode only OCRs (and charges) PDF pages without a usable text layer.", "default": "auto" }, "dpi": { "title": "Render resolution (DPI)", "minimum": 72, "maximum": 400, "type": "integer", "description": "Resolution used to render PDF pages for OCR. 200 is a good balance; 300 for small print.", "default": 200 }, "pageSegmentation": { "title": "Page layout mode (Tesseract PSM)", "enum": [ "3", "1", "4", "6", "11", "12" ], "type": "string", "description": "How Tesseract segments the page.", "default": "3" }, "includePages": { "title": "Include text per page", "type": "boolean", "description": "Add a 'pages' array with text, word count, method and confidence per page.", "default": true }, "maxPagesPerFile": { "title": "Max pages per file", "minimum": 0, "type": "integer", "description": "Only process the first N pages of each PDF. 0 = all pages.", "default": 0 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Skip files larger than this (free).", "default": 50 }, "maxFiles": { "title": "Max files", "minimum": 0, "type": "integer", "description": "Stop after this many URLs. 0 = no limit.", "default": 0 }, "concurrency": { "title": "Parallel files", "minimum": 1, "maximum": 4, "type": "integer", "description": "Files processed at once (1-4). Use more with more memory.", "default": 2 } } }, "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 } } } } } } } } } }