Veil – On-device meeting transcription with 100% PII redaction

Show HN: VeilPhantom – Open-source on-device PII detection for AI pipelines

Veil – On-device meeting transcription with 100% PII redaction operates in show hn launch.

Profile

I built VeilPhantom, a Python SDK that detects and tokenizes PII before text reaches any LLM.The problem: AI agents processing meetings, emails, support tickets are handling raw sensitive data. Names, salaries, medical details — all flowing through cloud APIs.The solution: Detect PII on-device, replace with tokens ([PERSON_1], [AMOUNT_1]), send safe tokens to LLM, rehydrate response locally.Interesting finding: In benchmarks (98 scenarios, 8 verticals, Claude Haiku), accuracy went UP with PII redaction — 91.5% → 93.3%. Token-structured input seems to help models parse arguments more reliably.Technical details: - Shade V7: 22M param PhoneticDeBERTa (DeBERTa-v3-xsmall + Double Metaphone embedd

The company sits in the show hn launch segment, where it competes on its core product or service.

The company is listed at the Show HN launch stage of development.

Website: helloveil.com/sdk