Redact PNG / JPG for AI

Redact Image (OCR) files before sending to AI.

Receipts, screenshots, ID documents, mobile photos of forms — visual data is full of PII you don't want to send to an LLM raw. Cypherz extracts text via Tesseract, tokenizes the result, and gives you the safe version.

  • 01

    Tesseract under the hood

    Battle-tested OCR engine, suitable for receipts and printed forms.

  • 02

    Multi-language ready

    English by default; configure additional language packs on self-hosted deployments.

  • 03

    Combined with all detectors

    Names, dates, money, IBANs, credit cards — all run against the OCR'd text.

Upload via the REST API

curl -X POST https://api.cypherz.app/v1/files \
  -H "authorization: Bearer $CYPHERZ_KEY" \
  -F "file=@receipt.png"

Common questions

Frequently asked.

What happens to my PNG / JPG 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 PNG / JPG now.

Sign up, create a project, copy your API key. The first request is tokenized in under sixty seconds.