{ "openapi": "3.0.1", "info": { "title": "OCR: Image & Scanned PDF to Text (Spanish, English, Portuguese)", "description": "OCR images and scanned PDFs in Spanish, English or Portuguese and get the text plus a searchable PDF. $4 per 1,000 pages, failed files are free.", "version": "0.1", "x-build-id": "vwR4VLdmFPIXw3Jgf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/isnard~ocr-image-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-isnard-ocr-image-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/isnard~ocr-image-to-text/runs": { "post": { "operationId": "runs-sync-isnard-ocr-image-to-text", "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/isnard~ocr-image-to-text/run-sync": { "post": { "operationId": "run-sync-isnard-ocr-image-to-text", "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": [ "urls" ], "properties": { "urls": { "title": "Image or PDF URLs", "type": "array", "description": "Direct links to images (PNG, JPG, WebP, TIFF, BMP, GIF) or PDF files, one per line. Only http and https. Each image and each PDF page becomes one dataset item. Duplicates are processed once.", "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "Languages of the text. Pick only the ones present: every extra language makes OCR slower and can add mistakes. The first one is the main language.", "items": { "type": "string", "enum": [ "spa", "eng", "por" ], "enumTitles": [ "Spanish", "English", "Portuguese" ] }, "default": [ "spa", "eng" ] }, "autoRotate": { "title": "Auto-rotate", "type": "boolean", "description": "Detect pages that are rotated 90, 180 or 270 degrees and turn them upright before OCR (Tesseract OSD). Adds a short extra step per page.", "default": true }, "upscaleSmallImages": { "title": "Upscale small images", "type": "boolean", "description": "Enlarge images whose longest side is under 2000 px (up to 3x). Helps with screenshots and thumbnails.", "default": true }, "threshold": { "title": "Black and white thresholding", "type": "boolean", "description": "Convert the page to pure black and white (Otsu threshold) before OCR. Can help with faded scans and gray backgrounds. Can hurt photos with uneven light, so it is off by default.", "default": false }, "searchablePdf": { "title": "Save searchable PDF", "type": "boolean", "description": "Also save one searchable PDF per input file (page image with an invisible text layer) to the key-value store. The link is in searchable_pdf_url. The PDF shows the pre-processed (grayscale) page.", "default": false }, "maxPdfPages": { "title": "Maximum pages per PDF", "minimum": 1, "maximum": 500, "type": "integer", "description": "Only the first N pages of each PDF (or multi-page TIFF) are processed and charged.", "default": 20 }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Larger files are skipped with an error and not charged.", "default": 25 }, "timeoutSecs": { "title": "Download timeout (seconds)", "minimum": 5, "maximum": 300, "type": "integer", "description": "Network timeout for each download.", "default": 60 } } }, "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 } } } } } } } } } }