Anonymize meeting notes or a transcript before an AI summarises them
Paste the notes or the transcript. Participants, clients, companies, phone numbers and emails become codes such as NAME-001, and each speaker keeps the same code from start to finish, so the AI can still say who decided what. Then paste its summary back here to get the names back.
Restoring uses the key of this tab: code your text here first, keep this tab open, then come back with the answer.
Adjust
See the key (it stays in this tab)
The key links each code to the real value. It exists only in this tab's memory: close or reload the tab and it is gone.
connect-src 'none' in its security policy) and loads no analytics. Turn Wi-Fi off once the page has loaded: the tool works just the same. The engine is the one inside the Hidden Tokens app.How it works
1 · Code
Paste a text or drop a file. Names, companies, addresses, emails, phone numbers, bank details, ID and case numbers become codes such as NAME-001 or COMPANY-001. Unknown proper nouns are coded too: when in doubt, the engine codes.
2 · Send the codes
Copy the coded text, or download the coded file, and give it to ChatGPT, Claude, Gemini or Copilot. The AI reasons on the codes: it still knows who did what, not who they are.
3 · Restore
Paste the AI's answer in the Restore tab, in the same browser tab. The codes become the real names again, on your screen only.
Why transcripts are riskier than they look
A transcript is not just a list of decisions. People say things in a meeting they would never write: a colleague's health, a client's money trouble, a candidate's salary. Automatic transcripts also capture every name spoken aloud, including people who were not in the room.
- Speakers and people mentioned become codes, consistently: “
FIRSTNAME-002agreed to send the figures” still makes sense in the summary. - Emails, phone numbers and references read out during the call are coded too.
- What the tool cannot judge: a sensitive remark without a name in it. Cut those passages before you paste, or tell the AI to ignore them.
- Download the transcript from Teams, Zoom or Meet as a Word or text file and drop it in the Word or Excel tab, or paste your own notes.
- Ask for the summary, the action list or the follow-up email on the coded version.
- Restore the answer here: owners and deadlines come back with real names, ready to send.
The free tool handles up to 3,000 words at a time, which is about twenty minutes of conversation. For longer meetings, split the transcript, or use the Hidden Tokens app, which has no limit and keeps the same codes across a whole folder of meetings.
The free tool or the Hidden Tokens app?
This free tool
- One text or one file at a time
- Up to 3,000 words or 1,000 spreadsheet rows
- The key lives in this tab and disappears when you close it
- Word, Excel, CSV and text
The Hidden Tokens app
- Whole folders: the same person keeps the same code in every document
- One key per case file, kept on your computer
- PDF and scanned documents, read on your computer
- Inside Claude Desktop, and in ChatGPT, Gemini and Copilot with the extension
- Industry packs, firm rules and a signed proof of what the AI saw
A word on the word “anonymize”
Strictly speaking, this tool pseudonymizes: each value is replaced by a code that can be reversed with the key. Under the GDPR, pseudonymised data is still personal data for whoever holds the key, which here is you, in this tab. What the AI receives no longer names anyone directly. Clues can remain, such as a job, a town and an age together: the tool warns you when it sees them. Read the result before sending it.
Questions
Can the AI still attribute actions to the right person?
Yes. Each speaker keeps one code for the whole transcript, so the AI can write that NAME-002 owns an action. Restoring the answer turns the codes back into names.
Does it work with Teams, Zoom or Google Meet transcripts?
Yes, as long as you paste the text or drop it as a .txt or Word file. Speaker labels at the start of each line are coded like any other name.
My transcript is longer than 3,000 words. What can I do?
Split it into parts and code each one in the same tab, so the same person keeps the same code. The Hidden Tokens app has no length limit.
Are health or HR remarks protected?
Only the names are coded. A remark such as a medical condition stays readable if no name is attached to it, so remove passages that are sensitive in themselves before sending.
Other ways to use the free tool
For whole folders, use the app
Hidden Tokens codes whole case files on your computer with one key, works inside Claude Desktop and in your browser, reads PDFs and scans, and puts the real names back into Word and Excel files.