{ "openapi": "3.0.1", "info": { "title": "DOCX, PPTX, XLSX & EPUB to Text API — Office Docs to Markdown", "description": "Convert Word, PowerPoint, Excel, OpenDocument and EPUB files at public links to Markdown and text, with metadata, sheets as JSON rows and slides with notes. Office Document to Text API.", "version": "0.1", "x-build-id": "jhZEevdBXgf2A4cnw" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/highbrow_fame~office-document-to-text-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-highbrow_fame-office-document-to-text-api", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/highbrow_fame~office-document-to-text-api/runs": { "post": { "operationId": "runs-sync-highbrow_fame-office-document-to-text-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/highbrow_fame~office-document-to-text-api/run-sync": { "post": { "operationId": "run-sync-highbrow_fame-office-document-to-text-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "Document URLs", "type": "array", "description": "Public links to Office, OpenDocument or EPUB files, one per line: .docx, .pptx, .xlsx, .xls, .csv, .ods, .odt, .odp, .epub. The type is detected from the file itself, so the link does not need an extension. Up to 50 MB per file.", "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "both", "markdown", "text" ], "type": "string", "description": "What to deliver per document: Markdown (headings, bold, lists and tables kept), plain text, or both.", "default": "both" }, "maxRows": { "title": "Max rows per sheet", "minimum": 0, "type": "integer", "description": "Spreadsheets: how many data rows of each sheet to deliver in rows[] and in the Markdown table. 0 = all rows. The full row count is always reported.", "default": 1000 }, "includeRows": { "title": "Rows as JSON", "type": "boolean", "description": "Spreadsheets: deliver each sheet's rows as JSON — objects keyed by the header row when the first row is a header, arrays otherwise. Off keeps only headers, counts and the Markdown table.", "default": true }, "sheetNames": { "title": "Only these sheets", "type": "array", "description": "Spreadsheets: names of the sheets to deliver (case does not matter). Empty = every sheet.", "items": { "type": "string" } }, "maxTextLength": { "title": "Max text length", "minimum": 0, "type": "integer", "description": "Cut text and Markdown to this many characters and set textTruncated. 0 = no limit. Dataset records are limited to 9 MB; a very long EPUB may need a cap.", "default": 0 }, "maxConcurrency": { "title": "Parallel downloads", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many files to download and convert at the same time.", "default": 5 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Files are downloaded directly first. The proxy is used only to retry a download that failed on the network.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }