{ "openapi": "3.0.1", "info": { "title": "PDF to Text & OCR - DOCX, Scanned PDF, Images to Text", "description": "Convert PDF, DOCX, PNG, JPG and TIFF files to clean text, page by page. Text-layer PDFs are read directly without OCR; scanned pages and images are OCR'd in 7 languages. Optional Markdown and RAG chunks. $0.003 per document, $0.006 per OCR page, failed files free.", "version": "0.1", "x-build-id": "Undij2TGHgwgPOPlf" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sipki~docs-to-text-ocr/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sipki-docs-to-text-ocr", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/sipki~docs-to-text-ocr/runs": { "post": { "operationId": "runs-sync-sipki-docs-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/sipki~docs-to-text-ocr/run-sync": { "post": { "operationId": "run-sync-sipki-docs-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": { "urls": { "title": "File URLs", "type": "array", "description": "Direct links to PDF, DOCX, PNG, JPG, TIFF, BMP, GIF or WEBP files (http/https), one per line. The file type is detected from the content, not the extension.", "items": { "type": "string" } }, "keyValueStoreKeys": { "title": "Files in a key-value store", "type": "array", "description": "Keys of files you uploaded to a key-value store (upload each file with its real Content-Type, e.g. application/pdf). Combine with 'URLs' freely.", "items": { "type": "string" } }, "keyValueStoreName": { "title": "Key-value store name", "type": "string", "description": "Name of the store that holds the keys above. Leave empty to use this run's default store." }, "inlineFiles": { "title": "Inline files (advanced)", "type": "object", "description": "Small files passed directly in the input as {\"name.pdf\": \"\"}. Total input size is limited by Apify (about 9 MB); use URLs or a key-value store for anything bigger." }, "languages": { "title": "OCR languages", "type": "array", "description": "Languages of scanned pages and images. English is always added. Choose every language that occurs in your documents; each extra language slightly slows OCR.", "items": { "type": "string", "enum": [ "eng", "deu", "fra", "spa", "rus", "ita", "por" ], "enumTitles": [ "English", "German", "French", "Spanish", "Russian", "Italian", "Portuguese" ] }, "default": [ "eng" ] }, "ocrMode": { "title": "OCR mode", "enum": [ "auto", "force", "never" ], "type": "string", "description": "auto: OCR only pages that have no text layer (default, cheapest). force: OCR every page (use when a PDF has a broken or garbage text layer). never: text layers only, no OCR.", "default": "auto" }, "outputMarkdown": { "title": "Also output Markdown", "type": "boolean", "description": "Add a 'markdown' field. DOCX headings, lists and tables are preserved; PDF and OCR text becomes paragraphs with page markers.", "default": false }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "0 = no chunks. Otherwise adds a 'chunks' array of about this many characters, cut on paragraph boundaries, each with its page range.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "How much of the previous chunk is repeated at the start of the next one (paragraph granularity).", "default": 100 }, "maxPagesPerDocument": { "title": "Max pages per document", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Pages after this number are not processed (and not charged). The output tells you when a document was truncated.", "default": 200 }, "maxDocuments": { "title": "Max documents", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Stop after this many documents (the rest are skipped).", "default": 1000 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger files are reported as failed (free).", "default": 50 }, "ocrDpi": { "title": "OCR render resolution (DPI)", "minimum": 100, "maximum": 400, "type": "integer", "description": "Resolution used to rasterize PDF pages before OCR. 300 is the best default; 200 is faster and fine for clean scans.", "default": 300 }, "pageSegmentationMode": { "title": "Tesseract page segmentation mode", "minimum": 1, "maximum": 13, "type": "integer", "description": "3 = fully automatic (default), 4 = single column, 6 = single uniform block, 11 = sparse text.", "default": 3 } } }, "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 } } } } } } } } } }