By George Curta · Last updated 2026-06-30
48 langues. Une seule plateforme.
Détectez et anonymisez les PII dans 48 langues grâce à une prise en charge native des motifs. Prise en charge RTL complète pour l'arabe, l'hébreu, le persan et l'ourdou.
48 langues prises en charge
Détection et anonymisation complètes des PII sur l'ensemble de la plateforme
🌍Europe— 28 langues
🌎Amériques— 2 langues
🌍Afrique— 2 langues
🌏Moyen-Orient— 5 langues
🌏Asie du Sud— 3 langues
🌏Asie du Sud-Est— 5 langues
🌏Asie de l'Est— 3 langues
Fonctionnalités multilingues
Détection automatique
Notre système identifie automatiquement la langue de votre texte et applique les modèles de détection appropriés.
- Prend en charge 48 langues
- Aucune sélection manuelle nécessaire
Prise en charge des langues RTL
Prise en charge complète des langues s'écrivant de droite à gauche, avec une gestion correcte du texte bidirectionnel.
- Arabe, hébreu, persan, ourdou
- Positionnement correct du texte
Chargement intelligent des modèles
Les modèles de langue sont chargés à la demande afin de réduire l'utilisation de la mémoire et d'améliorer les performances.
- Charge uniquement les modèles nécessaires
- Met en cache jusqu'à 5 modèles
Industry Precision Benchmark — Feb 2026
Independent benchmarks on mixed-language datasets reveal a critical gap in multilingual PII detection across the industry.
Industry average
22.7% precision
3.4 false positives per real PII finding in mixed-language datasets
anonym.legal
285+ entity types
spaCy NLP engine across 48 languages — 419/419 test cases passing
Why precision matters in multilingual PII detection
Low precision means more false positives — legitimate data gets blocked, workflows break
Mixed-language documents (e.g., German contracts with English headers) require per-language NLP models — not a single global model
spaCy NER models trained per language outperform multilingual transformers on country-specific entity formats (PESEL, IBAN, BSN, etc.)
GDPR and regional data protection laws require correct identification — misidentification creates compliance risk
Formats spécifiques à chaque pays
Nous détectons les PII dans les formats propres à chaque pays et région.
Formats européens
- Allemagne : Personalausweis, Steuer-ID
- France : NIR, Carte Nationale
- Italie : Codice Fiscale
- Espagne : DNI, NIE
- Pays-Bas : BSN
- Pologne : PESEL
Formats mondiaux
- États-Unis : SSN, permis de conduire
- Royaume-Uni : National Insurance
- Canada : SIN
- Australie : TFN, Medicare
- Japon : My Number
- Inde : Aadhaar, PAN
Anonymisez dans n'importe quelle langue
Commencez avec 200 jetons gratuits. Fonctionne avec les 48 langues.
Créer un compte gratuitLimitations / Important note
- Detection accuracy and entity coverage vary by language; some languages are supported more comprehensively than others.
- Detection is probabilistic; review high-stakes outputs. This is not legal advice.
About this page
We update this page when our platform or the law changes.
Read our founder note for how we work.
Each change shows up in the timestamp at the top.
Related reading
We follow these rules
- GDPR (EU 2016/679).
- ISO/IEC 27001:2022.
- NIS2 (EU 2022/2555).
- HIPAA safe harbor under 45 CFR § 164.514(b)(2).
Our promise
We do not sell your data.
We do not train models on your text.
We store your files in Germany.
You can delete your account at any time.
You own your work.
Where we run
Our company HQ is in Saarbrücken, Germany. Our servers run in Hetzner's Falkenstein datacenter.
Hetzner holds ISO 27001 certification.
All data stays in the EU.
Backups run every day.
Need help?
Email support@anonym.legal.
We reply within one business day.
How we test
We run a full check suite on every release.
Each surface gets its own sweep script and report.
Human reviewers spot-check the output each week.
We track recall and precision on a labelled set.
Bad runs block the deploy.
What we never do
- We never sell your information to third parties.
- We never train models on what you upload.
- We never keep your work after you delete it.
- We never share keys with any outside firm.
- We never run ads inside the product.
Plans in plain words
We sell credits, not seats.
One credit covers one short job.
Long jobs use a few credits each.
You can top up at any time.
Unused credits roll over each month.
Read the plans page for current rates.
Who built this
A small team of engineers and lawyers built this.
We ship from Europe and work in the open.
Our founder note spells out why we started.
Where to start
- Open the web app and try a sample file.
- Learn how credits get counted.
- See current plans and limits.
- Meet the team behind the product.
How the parts fit
A browser add-on cleans text inside Chrome.
A Word plug-in handles drafts in Office.
A small desktop tool works on whole folders.
An agent protocol link feeds large models safely.
All four share one core engine and one rule set.
Words from our team
We started this work after a lunch about cookies.
One friend kept getting odd ads on her phone.
We asked why a court file leaked through a draft.
We sketched the first build on a napkin that week.
By month three we had a tiny demo for a friend.
She used it on her first case the next day.
Common questions we hear
Can the tool read scanned PDFs? Yes, with OCR.
Does it work on long files? Yes, in small chunks.
Can I roll my own rule set? Yes, save it as a preset.
Does it run offline? The desktop build runs offline.
Do you keep my files? No, the cloud build wipes after each run.
Will it learn from my work? No, we never train on inputs.
A short tour of the workflow
Upload a file or paste a snippet of prose.
Pick the entities you want gone from the draft.
Choose a method: replace, mask, hash, encrypt, or redact.
Press run and watch the side panel show each hit.
Skim the result and tweak any rule that misfired.
Save the cleaned file or send it to a teammate.