Extract structured invoice data from images and PDFs via the iFlytek OCR API.
npx skills add https://github.com/iflytek/iFly-Skills --skill ifly-ocr-invoice
Please help me install this Agent Skill. Skill: ifly-ocr-invoice Source: https://github.com/iflytek/iFly-Skills/tree/main/ifly-ocr-invoice Command: npx skills add https://github.com/iflytek/iFly-Skills --skill ifly-ocr-invoice
Manual processing of invoices and receipts is slow and error-prone; this skill automates extracting structured data.
Run the OCR script on an invoice image after setting XFYUN_APP_ID, XFYUN_API_KEY, and XFYUN_API_SECRET in your environment.
High-intent search queries and answers about installing and using this skill.
OCR extracts structured invoice data from images and PDFs by posting a signed request to the iFlytek API endpoint. It automates data entry for expense reporting by identifying fields across various receipts.
OCR data extraction supports VAT invoices, taxi receipts, train tickets, medical bills, and bank receipts. It parses these documents to output human-readable text or raw API JSON for expense workflows.
Yes, you need Python 3 to automate invoice data extraction. You must set the XFYUN_APP_ID, XFYUN_API_KEY, and XFYUN_API_SECRET environment variables before running the script.
To set up API credentials for receipt OCR processing, configure XFYUN_APP_ID, XFYUN_API_KEY, and XFYUN_API_SECRET as environment variables. Run scripts/invoice.py to authenticate and send requests.
Yes, you can integrate raw API JSON output into accounting processes. The OCR script outputs structured data from invoices and bills, enabling easy integration into expense workflows and record-keeping.
The best way to automate expense reporting from mixed receipts is using an OCR script to extract structured fields. It handles VAT invoices, taxi receipts, and medical bills, outputting standardized data.
JaykaijackExtract structured fields from Chinese invoice and receipt images via the xfyun OCR API.
alibabaExtract text, tables, and metadata from PDF documents into JSON.
wordflowlabExtract text, tables, and form data from PDF documents.
mindeeExtracts structured text and data from PDFs and images using Mindee's Python SDK and API.
