Redact Audio: Bleep or Mute Sensitive Speech, Free

Drop in a recording and it gets transcribed, phone numbers and card numbers and emails and ID numbers read aloud get flagged as they're spoken, and you click any word to redact a name or anything else by hand. Transcription, review, redaction, and export all run on your device, and the recording itself is never uploaded anywhere.

What it catches on its own, and what it doesn't

Found automatically

As the transcript streams in, phone numbers, card and bank numbers, email addresses, and ID numbers spoken aloud get flagged on their own, including numbers read out digit by digit ("four two four two…"), which get normalized to digits before matching.

Found by you

Names are usually the whole reason someone wants a recording redacted, and reliably recognizing a spoken name is a much harder problem than recognizing a phone number, so it doesn't pretend to. Click a word, or drag across a phrase, and choose bleep or mute. Click a single word and "redact all occurrences" flags every instance at once: a multi-word selection doesn't offer that, since matching a whole phrase everywhere it's spoken reliably is a different problem. A custom term list flags a name or phrase automatically from then on, without you re-clicking it each time it comes up.

Bleep or mute: checked before you export, and after

Mute silences the redacted span outright, and a listener just hears a gap.
Bleep replaces it with the classic tone instead, so it's obvious something was cut on purpose rather than a recording glitch.

Set the mode per redaction, or switch a whole group at once.

Two checks keep that from being a leap of faith. Every redaction gets its own preview button, so you hear exactly what's being removed before you commit to it. Try to export with redactions you haven't listened to yet and you'll be asked to confirm first. After you export, the finished file gets decoded and checked span by span: a muted span has to measure out near-silent, a bleeped span has to measure out as dominated by the tone, and if either check fails on a specific span, the export is held back and that span is called out rather than handed to you with a hidden leak in it. (A recording too long to decode and check this way, past 45 minutes on a computer, 10 on a phone, skips that automated pass with a plain notice, and gets a spot-check playback of the exported file instead.)

Nothing here is saved between visits: close the tab and the recording, transcript, and flags are gone. An optional export log (times, redaction type, and a count, without the matched words unless you separately ask for them) is available if you need to attest to what was removed.

From file to export

1

Drop in a file

Audio, or a video file with an audio track: you'll get back just the redacted audio. Video output isn't in yet.

2

It transcribes and flags live

Speech recognition turns the recording into a transcript as it goes, with automatic flags appearing the moment they're found, so a long file is reviewable before it's even finished transcribing.

3

Export as WAV or MP3

WAV is lossless (the safer pick for court or compliance use), MP3 is smaller and more universal. Either way, the file's own metadata (recording-app tags, GPS, embedded titles) is stripped from the export by default.

Who this is for

Clinics & telehealth

Redact a patient's name and details from a therapy or telehealth recording before it goes to a transcription service, a supervisor, or a training set: no vendor contract or Business Associate Agreement required.

Law firms & paralegals

Prepare an audio exhibit without exposing a privileged conversation or a third party's details: redact a client call or deposition recording before it enters the record.

Call centers & QA teams

Scrub a card number or account detail read aloud on a support call before the recording is stored or reviewed: the PCI-DSS pressure, handled without a vendor contract.

Researchers

Anonymize interview audio for IRB compliance before archiving or sharing a dataset: a participant's name is gone before the file ever leaves your laptop.

Journalists & podcasters

Protect a source's identity before publication: bleep a name or a location without re-recording the segment.

Frequently Asked Questions

How do I bleep out a word in a recording? +
Drop in your recording and it gets transcribed. Click any word in the transcript, or drag across several, and choose Bleep or Mute from the popup. Every redaction gets its own preview button, so you can listen to exactly what will be removed before you export the finished file.
Is this HIPAA compliant? +
Nothing about your recording ever leaves your device: there's no upload, no server, and no third party involved, so there's nothing to sign a Business Associate Agreement about. You can disconnect your internet after the page loads and redacting a recording still works, start to finish.
Can it find names automatically? +
Not automatically. Recognizing a spoken name reliably is a much harder problem than recognizing a phone number or an email address, so we don't claim it does. What it does find automatically as the transcript comes in: phone numbers, card and bank numbers, emails, and ID numbers read aloud. For names, click any occurrence in the transcript and choose "Redact all occurrences," or add the name to a custom term list so every mention is flagged the moment it's spoken.
Why is my export limited on my phone? +
Phone browsers cap how much memory one tab can use, and rendering audio needs to hold the source and finished file in memory at the same time. On a phone we warn above 30 minutes of audio and stop at 90 minutes or 200 MB. Past that, a computer will handle it more reliably than crashing partway through. On a computer the ceiling is much higher: a warning above 2 hours or 300 MB, a stop above 4 hours or 1 GB.
What audio formats are supported? +
Most common recording formats, plus video files with an audio track: we'll read the audio out of the video for you. Export is WAV (lossless, the safer choice for court or compliance use) or MP3 (smaller, universal). Video output isn't available yet: you'll get back the redacted audio track, not a video file.
Does it work offline? +
Yes. After the page loads once, disconnect your internet and keep working: transcribing, flagging, redacting, and exporting all still happen normally.
What's the difference between bleep and mute? +
Mute silences the redacted span completely. Bleep replaces it with the classic tone, so a listener can hear that something was intentionally removed rather than wondering if the recording just cut out. You can set the mode per redaction, or change a whole group at once in the review list.