Redact XLSX for AI
Redact Microsoft Excel files before sending to AI.
Spreadsheets are where customer rosters, financial records, and HR data actually live. Cypherz reads every sheet, every cell — tokenizes PII cell-by-cell, and re-emits as a clean XLSX ready to upload to any AI sandbox or share with a vendor.
01
Cell-by-cell
Every string cell scanned independently — preserves formulas and number formats.
02
Multi-sheet support
All sheets in the workbook are processed in one pass.
03
Redacted XLSX download
Output stays in XLSX format; load it into Excel, Google Sheets, or feed to any model.
Upload via the REST API
curl -X POST https://api.cypherz.app/v1/files \
-H "authorization: Bearer $CYPHERZ_KEY" \
-F "file=@customer-list.xlsx"Common questions
Frequently asked.
What happens to my XLSX file when I upload it?
Cypherz extracts text, detects PII, tokenizes it, and stores the original encrypted (AES-256-GCM, per-project key) for download. You get a tokenized extraction back immediately. Files can be deleted at any time and their encryption key destroyed.
What's the max file size?
25 MB on managed cloud. Configurable up to 100 MB on self-hosted deployments.
Can I download a redacted version of the file?
Yes — GET /v1/files/{id}/redacted returns a downloadable redacted artifact. Text-native formats keep their original shape; binary formats fall back to a clean PDF.
Is the original ever stored unencrypted?
No. From the moment we receive your file, it's encrypted at rest with a project-scoped data encryption key.
Get started
Upload your first XLSX now.
Sign up, create a project, copy your API key. The first request is tokenized in under sixty seconds.
More file types
Redact PDF
Upload a PDF to Cypherz, get back a tokenized version safe to send to any AI. Em…
Redact DOCX
Upload a Word document, get a tokenized extraction. Cypherz uses mammoth to extr…
Redact CSV
Upload a CSV, get a tokenized version you can feed to ChatGPT, Claude, Gemini, o…
Redact PNG / JPG
Cypherz runs Tesseract OCR on PNG, JPG, and WebP uploads, then tokenizes every d…