Detect Bark AI voices.
Suspect a clip was made with Bark? Drop it in and get a citable verdict with the model named, in under half a second. Open-source generative audio model that produces speech plus nonverbal sounds like laughs and sighs.
Bark, and why it shows up in suspicious audio
Bark is an open-source generative audio model, originally from Suno, that produces speech and can add nonverbal cues such as laughter, sighs, and background music. It is popular in open-source projects and creative tools.
Its expressive, sometimes unpredictable output has a recognizable texture, and being open-source it runs anywhere, so the clip itself is the only thing to go on.
Where you tend to see it: Open-source projects, creative audio, and social clips.
Bark is a legitimate product; misuse is the problem, not the tool. You can read about it on the official Bark site.
How to tell a Bark voice
The human ear is unreliable on current Bark audio. These are the signals a detector weighs. We report which ones drove the verdict rather than handing you a bare number.
- 01Expressive but slightly unstable prosody, with energy that wavers in a characteristic way.
- 02Nonverbal inserts (laughs, sighs) that sound synthesized on close listen.
- 03Artifacts at phoneme boundaries audible to a model.
- 04A texture that shifts mid-clip more than a real recording would.
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. Bark, 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 Bark-generated speech?
Do the laughs and sound effects matter?
Is a single check free?
Does running Bark locally hide it?
Will it name Bark specifically?
We attribute 24+ voice models
Is this a Bark voice? Find out.
Free verdict, model named, in under a second. No card to start.