Detect Descript AI voices.
Suspect a clip was made with Descript? Drop it in and get a citable verdict with the model named, in under half a second. Editor-native voice cloning (Overdub) plus stock AI voices, tuned to blend into a real recorded track.
Descript, and why it shows up in suspicious audio
Descript is a widely used audio and video editor whose Overdub feature clones a voice from a training sample, letting an editor fix or add speech by typing rather than re-recording. It is a staple of podcast and video production.
Because Overdub is built to blend seamlessly into a genuine recording, an unlabeled synthesized insert can sit inside otherwise-real audio, which is exactly the case worth checking.
Where you tend to see it: Podcast and video edits, corrections spliced into real recordings, and cloned-voice inserts.
Descript is a legitimate product; misuse is the problem, not the tool. You can read about it on the official Descript site.
How to tell a Descript voice
The human ear is unreliable on current Descript audio. These are the signals a detector weighs. We report which ones drove the verdict rather than handing you a bare number.
- 01Seams where a cloned insert meets real recorded audio, heard as small shifts in room tone or level.
- 02Prosodic evenness in the synthesized segments that the surrounding human speech does not share.
- 03Timbre that stays fixed across an insert where a re-recorded take would drift.
- 04Vocoder artifacts in fricatives that survive the editor's export and re-encoding.
A verdict you can cite, not a vibe
The detector reads the audio, not the speaker. Cloning or stock voice, clean or compressed, it looks for the synthesis signature and attributes the source.
Drop the clip
Upload a file or paste a URL. MP3, WAV, M4A, WebM, or the audio track of a video. About half a second of clear speech is enough.
The model scores it
The same model behind the public detector reads the acoustic signature and weighs the artifacts, then attributes the source, e.g. Descript, when it recognizes it.
Get a citable verdict
You get a probability, a confidence level, the named model, and a permanent citation URL you can quote, file, or subpoena.
What to do next
A verdict is evidence, not a verdict of intent. Save the result to get a permanent citation URL and a one-way audio fingerprint you can reference later without storing the file. If you are a journalist or investigator, cite the verdict alongside your own reporting; if this is a suspected scam, treat the contact as unverified and confirm through a channel you already trust. The FTC's advice on suspected scam calls is a sensible baseline.
Building this into a workflow? The API returns the same verdict as JSON with webhooks for bulk jobs, and the browser extension checks audio in place on WhatsApp Web, YouTube, and podcasts.
Common questions
Can you detect a Descript Overdub insert inside a real recording?
Does it work on a whole edited episode?
Is a single check free?
Will it name Descript specifically?
What happens to my audio?
We attribute 24+ voice models
Is this a Descript voice? Find out.
Free verdict, model named, in under a second. No card to start.