# PDF OCR to Word API
Convert scanned PDFs into editable Word documents.
## API Overview
- **HTTP Protocol:** HTTPS
- **HTTP Method:** POST
- **HTTP Endpoint:** https://api.gugudata.io/v1/imagerecognition/pdf2word
- **Response Type:** application/json; charset=utf-8
- **DEMO Endpoint:** https://api.gugudata.io/v1/imagerecognition/pdf2word/demo
- **Live Demo:** https://gugudata.io/demo/pdf2word
- **Postman:** https://www.postman.com/gugudata/gugudata-io
- **LLM Page:** https://gugudata.io/details/pdf2word/llm
- **Raw Markdown:** https://gugudata.io/details/pdf2word/llm.md
## Remote MCP
- **MCP Endpoint:** https://mcp.gugudata.io/mcp
- **MCP Guide:** https://gugudata.io/mcp/
- **Authorization:** OAuth authorization opens in the browser; do not paste appkeys into MCP clients.
- **Tool Scope:** MCP clients receive GuGuData API tools available to the authorized account.
## Data & API Features
- Scanned PDF recognition: Recognize printed text in scanned PDFs. Results depend on scan quality; handwriting recognition is not guaranteed.
- Editable Word documents: Download recognized text as a DOCX file for editing and correction. Save your result; permanent hosting is not guaranteed.
- Source-page organization: Keep source page order, line breaks, and blank-page positions with page breaks. Original layout, images, and table structure are not restored.
- English and Chinese options: Choose English, Simplified Chinese, Traditional Chinese, or English combined with either Chinese option.
- Upload or PDF link: Upload a PDF or submit a public PDF link, up to 20 MiB and 50 pages per request.
- Document review workflows: Send editable text to review queues, archive cleanup projects, and document intake workflows.
## API Request Parameters
| Name | Type | Is Required | Default Value | Remark |
| --- | --- | --- | --- | --- |
| appkey | string | true | YOUR_APPKEY | API key used to authenticate the request. |
| file | file | false | | Upload a PDF. Provide exactly one of file or file_url. Maximum 20 MiB and 50 pages. |
| file_url | string | false | | Public HTTP(S) PDF URL, up to 2048 characters. Provide exactly one of file or file_url. |
| lang | string | false | en | en, zh-CN, zh-TW, en+zh-CN, or en+zh-TW. Recognition quality depends on the scan. |
| filename | string | false | result.docx | Optional safe download filename, at most 128 Unicode characters including the normalized.docx suffix. Paths are not accepted. |
## API Response Parameters
| Name | Type | Remark |
| --- | --- | --- |
| wordPath | string | Public HTTPS DOCX download URL. Save the file in your own storage; permanent hosting is not guaranteed. |
## API Response Status Codes
| Status Code | Explanation of Status Code | Remarks |
| --- | --- | --- |
| 200 | Request processed successfully. | Some endpoints expose a separate application-level status field in the response body, such as `dataStatus.statusCode`. |
| 400 | Invalid request parameters or request format. | Check required fields, data types, and request body format. |
| 401 | Missing or unknown application key. | Provide a valid `appkey` with the request. |
| 403 | The application key is recognized but access is not allowed. | The key may be expired, inactive, or not permitted for the requested API. |
| 413 | PDF exceeds the size or page limit. | Use a PDF of at most 20 MiB and 50 pages. |
| 422 | PDF cannot be recognized. | Use an unencrypted PDF with legible printed text. |
| 429 | Request rate or trial usage limit exceeded. | Reduce request frequency and retry with backoff. If a trial allowance is exhausted, check Trial Keys for remaining requests and subscribe to continue. |
| 500 | Internal service error. | Retry later or contact support if the error persists. |
| 502 | PDF download or recognition failed. | Check the PDF link and try again later. |
| 503 | Recognition is temporarily unavailable. | Try again later. |
## cURL Example
```bash
curl --location 'https://api.gugudata.io/v1/imagerecognition/pdf2word?appkey=YOUR_APPKEY' --form 'file=@localfile_path.docx' --form 'lang=en' --form 'filename=result.docx'
```