{ "openapi": "3.0.1", "info": { "title": "Image to Text OCR — Images & Scanned PDFs, 40+ Languages", "description": "Extract text from images, screenshots, photos of documents and scanned PDFs with OCR in 40+ languages. Plain text, Markdown, confidence, lines and words with boxes. PDF text layers read for less.", "version": "0.0", "x-build-id": "B0axnd8SaazDQaj0R" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/saliga~image-to-text-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-saliga-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/saliga~image-to-text-ocr/runs": { "post": { "operationId": "runs-sync-saliga-image-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/saliga~image-to-text-ocr/run-sync": { "post": { "operationId": "run-sync-saliga-image-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 or PDF URLs", "type": "array", "description": "Links to images (PNG, JPEG, TIFF, WebP, GIF, BMP) or PDFs. One result per image, per frame of a multi-page TIFF, and per PDF page.", "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "string", "description": "Language(s) of the text. Combine with + or commas, for example eng+tur or \"en, de\". Codes: eng, deu, fra, spa, ita, por, nld, tur, pol, swe, rus, ukr, ara, chi_sim, chi_tra, jpn, kor, hin, vie, ind, ces, ron, hun, dan, nor, fin, ell, heb, tha, bul, hrv, slk, slv, lit, lav, est, msa, ben, tam, fas, urd, srp, cat. Two-letter codes and English names also work.", "default": "eng" }, "outputDetail": { "title": "Layout detail", "enum": [ "text", "lines", "words" ], "type": "string", "description": "Text: text and Markdown only. Lines: also every line with its confidence and box. Words: also every word with its confidence and box (x, y, w, h in pixels of the original image; for PDF pages, of the page rendered at the PDF DPI).", "default": "text" }, "layout": { "title": "Page layout", "enum": [ "auto", "sparse_text", "single_block", "single_line" ], "type": "string", "description": "How the text is arranged. Auto suits documents and screenshots. Sparse text finds scattered text (labels, signs, receipts). Single block for one column of text, single line for a one-line crop.", "default": "auto" }, "minConfidence": { "title": "Minimum word confidence (0-100)", "minimum": 0, "maximum": 100, "type": "integer", "description": "Drop recognised words below this confidence from the text. 0 keeps everything. Every page still reports its average confidence and a lowConfidence flag (under 60).", "default": 0 }, "preprocess": { "title": "Image clean-up", "enum": [ "auto", "none" ], "type": "string", "description": "Auto: grayscale, enlarge small images and stretch contrast before OCR (better on screenshots and thumbnails). None: use the image as it is.", "default": "auto" }, "pdfMode": { "title": "PDF pages", "enum": [ "auto", "ocr", "text" ], "type": "string", "description": "Auto: read a page from its text layer when it has one (exact and cheaper), otherwise with OCR. OCR: OCR every page. Text: text layer only, no OCR.", "default": "auto" }, "pdfDpi": { "title": "PDF render resolution (DPI)", "minimum": 72, "maximum": 600, "type": "integer", "description": "Resolution used to render scanned PDF pages for OCR. 300 is right for most scans; lower is faster.", "default": 300 }, "maxPagesPerFile": { "title": "Max pages per file", "minimum": 0, "type": "integer", "description": "Stop after this many pages or frames of each file (0 = all). Caps the cost of long PDFs.", "default": 0 }, "datasetId": { "title": "Dataset ID", "type": "string", "description": "ID of an Apify dataset, for example the output of a scraper run." }, "urlField": { "title": "Link field", "type": "string", "description": "Field with the image or PDF link in each dataset item. Use dots for nested fields (image.url). A list of links is read too.", "default": "url" }, "maxDatasetItems": { "title": "Max dataset items", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Read at most this many items from the dataset.", "default": 1000 }, "requestHeaders": { "title": "Request headers", "type": "object", "description": "Extra HTTP headers for downloading, for example {\"Authorization\": \"Bearer …\"} for files behind a token. Sent only to the host of each URL, never to a redirect on another host. They are stored with the run input, so prefer short-lived tokens or pre-signed URLs." }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Files larger than this are skipped with an error (free).", "default": 50 }, "maxConcurrency": { "title": "Files at a time", "minimum": 1, "maximum": 8, "type": "integer", "description": "How many files are downloaded and read in parallel. Raise it together with memory for big batches.", "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 } } } } } } } } } }