{ "openapi": "3.0.1", "info": { "title": "Image OCR Bulk - Text from Images (40 Languages)", "description": "Extract text from images in bulk with OCR in 40+ languages. Paste image URLs, get clean text, confidence and word positions as JSON. Fast, cheap, no setup.", "version": "0.0", "x-build-id": "rB11ESX6oScCYx3r0" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tiger19935~image-ocr-bulk/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tiger19935-image-ocr-bulk", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/tiger19935~image-ocr-bulk/runs": { "post": { "operationId": "runs-sync-tiger19935-image-ocr-bulk", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/tiger19935~image-ocr-bulk/run-sync": { "post": { "operationId": "run-sync-tiger19935-image-ocr-bulk", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "Image URLs", "type": "array", "description": "Direct links to image files, one per row. Public URLs only.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "languages": { "title": "Languages", "type": "string", "description": "Tesseract language codes joined with a plus sign, for example eng or eng+deu or rus+ukr. Available: eng, deu, fra, spa, ita, por, rus, ukr, pol, nld, tur, ara, chi_sim, chi_tra, jpn, kor, hin, ces, swe, heb, vie, tha, ron, dan, fin, nor, hun, bul, srp, hrv, slk, slv, lit, lav, est, cat, ind, msa, ben, tam.", "default": "eng" }, "pageSegmentation": { "title": "Layout mode", "enum": [ "auto", "block", "line", "word", "sparse", "sparseOsd" ], "type": "string", "description": "How the text is laid out on the image. Automatic suits documents and photos; use single block for a paragraph, single line for a caption or number plate, sparse text for screenshots with scattered labels.", "default": "auto" }, "autoRotate": { "title": "Auto-rotate pages", "type": "boolean", "description": "Detect sideways or upside-down text and rotate the image before recognition. EXIF orientation is always applied.", "default": true }, "preprocess": { "title": "Improve image before OCR", "type": "boolean", "description": "Convert to grayscale, normalise contrast, sharpen and enlarge small images. Turn off for clean, high-resolution scans.", "default": true }, "includeLines": { "title": "Return lines with coordinates", "type": "boolean", "description": "Add an array of text lines with bounding boxes (left, top, width, height in pixels) and confidence.", "default": false }, "includeWords": { "title": "Return words with coordinates", "type": "boolean", "description": "Add an array of words with bounding boxes and confidence. Makes the output larger.", "default": false }, "minConfidence": { "title": "Minimum word confidence", "minimum": 0, "maximum": 100, "type": "integer", "description": "Drop words recognised with lower confidence (0-100). 0 keeps everything.", "default": 0 }, "maxConcurrency": { "title": "Parallel images", "minimum": 1, "maximum": 16, "type": "integer", "description": "How many images to process at the same time.", "default": 4 }, "maxFileSizeMb": { "title": "Max image size (MB)", "minimum": 1, "maximum": 100, "type": "integer", "description": "Larger images are skipped.", "default": 25 } } }, "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 } } } } } } } } } }