Use cases · Research
Pseudonymize interview transcripts and survey data
Anonymize any document before it reaches an AI. Nothing leaves your device. Participants become consistent pseudonyms across all files, and the key stays with you, as your ethics protocol expects.
- 0 network requests
- Works with Wi‑Fi off
- Free, no account
- Restore names afterwards
Why it matters
Why researchers pseudonymize first
Your ethics approval assumes it
Consent forms usually promise that identifiable data will not be shared with third parties. An AI provider is a third party.
Coding needs consistency, not identity
Thematic coding, summarization and translation work on Participant 1 as well as on a real name. Consistent labels keep quotes traceable within your team.
Indirect identifiers matter too
Employers, towns, rare roles and dates can identify a participant together. Add them to your dictionary so they are replaced with the same care.
The key is a file you keep
The mapping table is your pseudonymization key. Store it with your restricted data; the anonymized transcripts can travel more freely.
How to do it
Four steps, all in your browser
- 1
Upload the file or paste the text
Word, PDF, PowerPoint, Excel, CSV, JSON, HTML, Markdown or plain text. Up to 10 files, 50 MB each. The file is opened in your browser tab and never sent anywhere.
- 2
Choose the rule
Decide how each category is rewritten: labels like Person 1 / Company A, realistic fake values, masking or redaction. Optionally enable smart detection and add words to your dictionary.
- 3
Review what will change
Names, companies, emails, phone numbers, IDs and IBANs are listed with their replacements. Turn items off, add missed ones, correct a category. Nothing changes until you confirm.
- 4
Download and paste into the AI
You get the same file back, a Markdown version to paste into the chat, and a mapping table. Paste the AI's answer into the de-anonymizer to put the original names back.
What to replace
Checklist for this domain
The tool detects most of these automatically. Add the rest to your dictionary so they are replaced consistently.
- Participant names and initials
- Interviewer and colleague names
- Employers and organizations mentioned
- Towns, neighbourhoods and institutions
- Emails and phone numbers from recruitment
- Dates of birth and ages, if identifying
- Rare job titles or roles
- Survey free-text fields with names
- File names that contain participant names
Before and after
What the AI sees
Original
Interviewer: Tell me about your work at Bosch. Hasan Çelik: I moved to Bursa in 2019 and my manager, Deniz Ak, was very supportive.
Anonymized
Interviewer: Tell me about your work at Company A. Person 1: I moved to Location 1 in Date 1 and my manager, Person 2, was very supportive.
Try it now
Anonymize your document here
Nothing is uploaded. Switch Wi‑Fi off if you want to check.
- 1Upload
- 2Choose rule
- 3Review
- 4Download
Upload
Drop files here or choose
Up to 10 files · 50 MB each · files stay on your device
- docx
- pptx
- xlsx
- txt
- md
- csv
- json
- html
Old .doc, .ppt and .xls files: save them as .docx, .pptx or .xlsx first.
Questions
Common questions
Are pseudonyms consistent across several transcripts?
Within one run each file gets its own mapping. Add participant names to your dictionary with the label you want; the dictionary applies to every file, so the same person gets the same pseudonym everywhere.
Can I export the key?
Yes. The mapping table downloads as CSV or JSON. Store it with your restricted data.
Does it handle CSV survey exports?
Yes. Each cell is scanned; delimiters and columns are preserved, so your analysis scripts keep working.
Is anything sent anywhere?
No. Everything runs in your browser; 0 network requests during processing.
Other use cases