# Transcript privacy editor

> Redact supported sensitive-data patterns from a transcript.

[Open tool](https://www.toolcabana.com/so/transcript-redactor) · [AI iyo tilmaamo](https://www.toolcabana.com/so/category/ai-and-prompt-tools)

Tool ID: transcript-redactor. Requested language: so. Description language: en. Complete guide translation: no; untranslated sections use English.

## Overview (en)

Transcript privacy editor redacts meeting, call or interview transcripts by replacing email addresses, supported phone formats, Luhn-valid card numbers and IPv4 addresses with bracketed type labels. List speaker names or other phrases to replace with [CUSTOM], matched case-insensitively. Download the edited transcript as redacted.txt and use the type, start and end table to review each change.

## Supported tasks (en)

Redacts email, supported phone formats, validated card numbers, IPv4 addresses and your additional phrases. Pattern matching can miss sensitive information. Review before sharing.

## Steps (en)

1. Paste the source into the input editor, or load the built-in example.
2. Set additional names / phrases to redact (one per line).
3. Run transcript privacy editor, review the output, then use the available copy or download controls.

## Settings

- Additional names / phrases to redact (one per line) (en; key: custom; type: textarea)

## Limitations (en)

Browser file and text limits apply, along with the bounds shown in Settings. Image processing is capped at 32 megapixels. OCR quality depends on source resolution and layout.

## Example input

```text
Contact Alex at alex@example.com or 555-123-4567.
```

## Privacy and connections (en)

Processes source in your browser. Copy and download are explicit actions; source is not saved to account history.

## Questions (en)

### How do I anonymize speaker names in a transcript?

Enter each speaker name in the additional phrases field, one per line. Every occurrence, in speaker labels and within sentences, is replaced with [CUSTOM]. Because all names get the same label, rename speakers to roles first if you need to keep them distinct.

### Are phone numbers written out as words redacted?

No. Detection works on digits, so numbers transcribed as words are not recognized. Phone numbers must appear in a supported digit format such as 555-123-4567; add other spellings as custom phrases or edit them by hand.

### What does the start and end table show?

Each row lists the redaction type and the character positions where the original text started and ended in your input. Use these offsets to find each redaction in the source transcript and check the surrounding context.

### Where is my input processed?

Processes source in your browser. Copy and download are explicit actions; source is not saved to account history.

### What are the input limits?

Browser file and text limits apply, along with the bounds shown in Settings. Image processing is capped at 32 megapixels. OCR quality depends on source resolution and layout.

## Related tools

- [Subtitle timing editor](https://www.toolcabana.com/so/subtitle-editor)
- [Photo contact sheet](https://www.toolcabana.com/so/image-contact-sheet)
- [Visual image comparison](https://www.toolcabana.com/so/image-diff)
- [Palette accessibility preview](https://www.toolcabana.com/so/palette-preview)