{ "openapi": "3.0.1", "info": { "title": "Document to Markdown – DOCX, PPTX, XLSX", "description": "Convert DOCX, PPTX, XLSX, XLS, ODS, CSV, EPUB, RTF, ODT, HTML, TXT and PDF files to clean Markdown with GFM tables, slides with speaker notes, sheets as tables or JSON rows. $3 per 1,000 documents (up to 20 pages or 10,000 rows each).", "version": "0.1", "x-build-id": "3D9gl52Qa7JOqcwFd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sfoln~document-to-markdown/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sfoln-document-to-markdown", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/sfoln~document-to-markdown/runs": { "post": { "operationId": "runs-sync-sfoln-document-to-markdown", "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/sfoln~document-to-markdown/run-sync": { "post": { "operationId": "run-sync-sfoln-document-to-markdown", "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": { "documentUrls": { "title": "Document URLs", "type": "array", "description": "Documents to convert, one per line: public http(s) URLs, data: URIs (base64) or Apify key-value store records (kvs:///, or the record's API URL, read with the run's token). Formats: DOCX, PPTX, XLSX, XLS, ODS, CSV, EPUB, RTF, ODT, HTML, TXT and PDF, detected from the bytes (not the file name). Max 25 MB per office file, 50 MB per PDF. Accounts on the Apify free plan can process up to 10 documents per run (the first 20 pages or 10,000 rows of each).", "items": { "type": "string" } }, "documentFile": { "title": "Or upload a document", "type": "string", "description": "A document from your computer (or its URL). It is converted together with the document URLs above." }, "includeSections": { "title": "Per-part sections", "type": "boolean", "description": "Return sections[]: one entry per PDF page, slide (with speaker notes), sheet or e-book chapter, each with its own Markdown.", "default": true }, "includeRows": { "title": "Spreadsheet rows as JSON", "type": "boolean", "description": "For XLSX, XLS, ODS and CSV, also return every sheet's rows as JSON objects keyed by the header row (typed numbers, booleans and ISO dates) in tables[].rows.", "default": false }, "includePlainText": { "title": "Include plain text", "type": "boolean", "description": "Also return the content as plain text (text), without Markdown syntax.", "default": false }, "password": { "title": "PDF password", "type": "string", "description": "Password for encrypted PDFs (used for every PDF of this run). It is never written to the output." }, "maxPages": { "title": "Max pages per document", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Convert at most this many pages per document: PDF pages, slides, or pages of 3,000 characters for text documents. Every 20 pages beyond the first 20 are one document-overage event.", "default": 1000 }, "maxRows": { "title": "Max spreadsheet rows", "minimum": 1, "maximum": 200000, "type": "integer", "description": "Convert at most this many non-empty rows per spreadsheet (all sheets together). Every 10,000 rows beyond the first 10,000 are one document-overage event. About 100,000 rows of 10 columns fit in the default 1 GB of memory; give the run 2 GB or more for bigger workbooks.", "default": 100000 }, "maxSheets": { "title": "Max sheets per workbook", "minimum": 1, "maximum": 200, "type": "integer", "description": "Convert at most this many sheets of a workbook (in workbook order).", "default": 50 }, "maxItems": { "title": "Max documents", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Safety cap on how many documents are processed in this run; further ones are ignored and counted as inputItemsDropped in the OUTPUT record.", "default": 1000 }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 5, "type": "integer", "description": "Documents converted in parallel (1–5).", "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 } } } } } } } } } }