{ "openapi": "3.0.1", "info": { "title": "Image to Text OCR: Arabic, Scans and Screenshots", "description": "Read text from image links or base64: screenshots, scans and photos (receipt photos read at lower confidence and are flagged for review). English and Arabic built in, line boxes, a quality report per image. No browser. Empty and unreliable images are not charged.", "version": "0.1", "x-build-id": "nqcRVjLR4jS6KuKQ8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/leadharbor~image-text-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-leadharbor-image-text-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/leadharbor~image-text-ocr/runs": { "post": { "operationId": "runs-sync-leadharbor-image-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/leadharbor~image-text-ocr/run-sync": { "post": { "operationId": "run-sync-leadharbor-image-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Image links", "type": "array", "description": "Public links to JPEG, PNG, WebP, GIF, BMP or TIFF images (up to 100 per run, links and base64 together, 25 MB and 50 megapixels each). Google Drive and Dropbox share links are turned into direct download links; any other link must point straight at the image. Links to private networks, localhost and pages that need a login are refused.", "items": { "type": "string" } }, "imageBase64": { "title": "Images as base64 text", "type": "array", "description": "Images sent as text instead of links: each item is a plain base64 string, or a data URL such as data:image/png;base64,AAAA... Every item is a string (not an object). Counts towards the 100 images per run and the 25 MB limit per image.", "items": { "type": "string" } }, "ocrLanguages": { "title": "OCR languages", "type": "array", "description": "Language codes of the text in the images, at most 3, for example [\"eng\"], [\"ara\", \"eng\"] or [\"deu\", \"fra\"]. English (eng) and Arabic (ara) are built in; every other official Tesseract 'tessdata_fast' language is downloaded when needed. List the main language first. Right-to-left text is returned in logical reading order. Only English and Arabic were benchmarked: any other language is marked experimental in the quality report.", "default": [ "eng" ], "items": { "type": "string" } }, "outputFormat": { "title": "Output", "enum": [ "lines", "text", "blocks", "all" ], "type": "string", "description": "'text' returns only the text. 'lines' (default) adds one entry per line with its confidence and a box on your picture. 'blocks' adds paragraphs with boxes. 'all' returns lines with a box and confidence for every word, and blocks. Fields you do not ask for are null.", "default": "lines" }, "preprocess": { "title": "Image clean-up", "enum": [ "auto", "none", "strong" ], "type": "string", "description": "'auto' reads the picture as it is and, only when the result is poor, again after clean-up (contrast, noise removal, adaptive black and white for photos, shadows and low light). 'none' never cleans up. 'strong' always cleans up first.", "default": "auto" } } }, "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 } } } } } } } } } }