{ "openapi": "3.0.1", "info": { "title": "Image to Text OCR - Extract Text From Images & Screenshots", "description": "Extract the text from any list of image URLs: screenshots, scans, receipts, signs, slides. Returns the full text, a confidence score and word count per image, optionally every line with its position. 20 languages, long text split into agent-sized rows. Pay only for images with text.", "version": "1.0", "x-build-id": "d1pFwz5vJEKhbi8jd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/appdata-labs~image-to-text-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-appdata-labs-image-to-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/appdata-labs~image-to-text-ocr/runs": { "post": { "operationId": "runs-sync-appdata-labs-image-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/appdata-labs~image-to-text-ocr/run-sync": { "post": { "operationId": "run-sync-appdata-labs-image-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "imageUrls": { "title": "Image URLs", "type": "array", "description": "Links to the images to read: PNG, JPEG, WebP, GIF, BMP, TIFF or PNM, up to 25 MB each and 500 per run. The link must open without signing in. A bad entry is skipped with a reason; the rest still run.", "default": [ "https://raw.githubusercontent.com/naptha/tesseract.js/master/tests/assets/images/testocr.png", "https://raw.githubusercontent.com/naptha/tesseract.js/master/tests/assets/images/bill.png", "https://raw.githubusercontent.com/naptha/tesseract.js/master/tests/assets/images/cosmic.png", "https://raw.githubusercontent.com/naptha/tesseract.js/master/tests/assets/images/escape_chars.png", "https://raw.githubusercontent.com/naptha/tesseract.js/master/tests/assets/images/simple.jpg", "https://raw.githubusercontent.com/naptha/tesseract.js/master/tests/assets/images/simple.webp", "https://raw.githubusercontent.com/naptha/tesseract.js/master/tests/assets/images/simple.gif", "https://raw.githubusercontent.com/naptha/tesseract.js/master/tests/assets/images/simple-90.jpg", "https://raw.githubusercontent.com/tesseract-ocr/test/main/testing/phototest.tif", "https://raw.githubusercontent.com/tesseract-ocr/test/main/testing/eurotext.tif", "https://raw.githubusercontent.com/tesseract-ocr/test/main/testing/8071_093.3B.tif" ], "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "The language(s) of the text, as Tesseract codes. English is built in and fastest; other languages load on first use. Pick more than one only for mixed-language documents — each extra language slows reading.", "items": { "type": "string", "enum": [ "eng", "spa", "fra", "deu", "ita", "por", "nld", "pol", "tur", "rus", "ukr", "ara", "hin", "tha", "vie", "ind", "jpn", "kor", "chi_sim", "chi_tra" ], "enumTitles": [ "English", "Spanish", "French", "German", "Italian", "Portuguese", "Dutch", "Polish", "Turkish", "Russian", "Ukrainian", "Arabic", "Hindi", "Thai", "Vietnamese", "Indonesian", "Japanese", "Korean", "Chinese (Simplified)", "Chinese (Traditional)" ] }, "default": [ "eng" ] }, "maxTextBytesPerRow": { "title": "Max text per row (bytes)", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Long text is split across several rows of at most this many bytes, at paragraph and line breaks, so each row fits an AI agent's context and drops straight into a RAG pipeline. The image is still charged once. 0 keeps each image whole in one row.", "default": 3000 }, "includeLines": { "title": "Include each line with its position", "type": "boolean", "description": "Off by default: one row per image with its full text. On: each row also lists every line with its confidence and bounding box (x, y, width, height in pixels) — useful for receipts, forms and highlighting.", "default": false } } }, "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 } } } } } } } } } }