Home · Audio authentication

Audio authentication.

Updated July 2026

When a recording is disputed, you need more than a hunch. Get a citable, reproducible verdict on whether a voice is real or AI-generated, with the source model named, in under half a second.

Verdict savedPermanent record
Citation
Permanent URL
Fingerprint
One-way hash
What it is

Authentication, in the practical sense

Audio authentication here means a documented, reproducible analysis of whether a recording is a real human voice or machine-generated. Run the clip through the detector and you get a probability (never rounded up), a confidence level, the recognized source model, a methodology version stamp, and a permanent citation URL, in under half a second.

The word "authentication" gets used loosely, so it is worth being precise. This is not verifying who is speaking, and it is not a watermark. It is answering one question that increasingly decides disputes: is this voice real, or was it synthesized? Because that answer is now contested in fraud cases, custody matters, employment disputes, and newsroom decisions, it has to be more than an opinion. It has to be repeatable and citable.

How it works

The audio, measured

The detector reads the acoustic fingerprint of the clip, the spectral, prosodic, and timing traces synthesis leaves behind, rather than the words. It works on cloned and stock voices and names the generator where it recognizes one, returning an honest "unknown synthesis" when it cannot attribute the source. The method is published and version-stamped, so the same test can be reproduced later against the same snapshot. See how to verify AI audio for the step-by-step.

Upload the original file, not a re-recording, to preserve the artifacts the analysis relies on
What a verdict gives you

A record, not just a number

Probability

How likely, honestly

A 0 to 1 likelihood the speech is machine-generated, never rounded up, paired with a confidence level driven by clip length and quality.

Attribution

The source, named

The recognized generator where the signature is clear, or a plain "unknown synthesis" when it is not.

Citation

Reproducible record

A permanent URL, a methodology version stamp, and a one-way fingerprint of the file, so an opposing expert can rerun the test.

0.48s
Median verdict
99%
Accuracy on clean audio
24+
Generators named
24h
Audio deleted after
Where it is used

Disputes, investigations, and the newsroom

Investigators and legal teams authenticate recordings that enter disputes and cases; see the legal and investigations use case. Fraud teams authenticate flagged voicemails and call recordings before acting; see fraud detection. Newsrooms authenticate audio before publishing; see newsrooms. For the underlying detection, see deepfake voice detection, and to build it into a workflow, the API returns the same verdict as JSON.

Honest scope

Analysis, not a ruling

We authenticate the audio, not the speaker, and we analyze recordings after the fact rather than monitoring live calls. We provide a probability with a published method behind it; we do not determine court admissibility, we are not a law firm, and we never claim a guaranteed 100% result. We are voice and audio only, so we read a video's audio track but not its images. For provenance on genuine media, content-authenticity standards like C2PA attach tamper-evident origin data and complement detection.

FAQ · Audio authentication

Common questions

What is audio authentication?
In practice, it is a documented, reproducible analysis of whether a recording is genuine or machine-generated. Here it means running the audio through a detector that returns a probability, a confidence level, the recognized source model, a methodology version stamp, and a permanent citation URL.
Is this the same as verifying a speaker's identity?
No. Speaker identification and voice biometrics ask whose voice it is. Audio authentication in our sense asks whether the voice is a real human voice at all, or synthetic. The two are complementary.
Can an authenticated verdict be used as evidence?
It is a citable, reproducible analysis with a published methodology, which supports your own records and any report you file. Whether and how it is used in a proceeding is for counsel and the court; we do not determine admissibility or give legal advice.
How accurate is it, and what are the limits?
About 99% on clean audio. Short, noisy, or heavily compressed clips lower confidence, and the detector reports that rather than guessing. No detector should claim a guaranteed 100% result.
Can we authenticate audio at volume?
Yes, through the API with webhooks for bulk and async jobs, so it fits an investigations, e-discovery, or newsroom workflow.

Authenticate a recording now.

Free for a single verdict. API and volume on Starter and above.

Open detectorSee pricing