Home · Detect · Amazon Polly

Detect Amazon Polly AI voices.

Updated July 2026

Suspect a clip was made with Amazon Polly? Drop it in and get a citable verdict with the model named, in under half a second. AWS cloud text-to-speech, including neural (NTTS) voices, common in apps, IVR, and notifications.

Synthetic detectedAmazon Polly
Confidence
high
Model
Amazon Polly
Yes, you can check. Drop the clip into the detector and it returns the probability that the speech was generated by Amazon Polly, a confidence level, and the named model, in under half a second. It reads the audio's synthesis signature, so it works on cloned and stock Amazon Polly voices alike, and gives you a citation URL to quote.
What it is

Amazon Polly, and why it shows up in suspicious audio

Amazon Polly is Amazon Web Services' text-to-speech engine, embedded in a vast range of apps, phone systems, and notification pipelines. Its neural voices are deployed at enormous scale.

Because Polly is so widely available through AWS, its audio appears in everything from accessibility features to automated call systems, and occasionally in scripted impersonation.

Where you tend to see it: IVR and phone systems, app narration, and automated notifications.

Amazon Polly is a legitimate product; misuse is the problem, not the tool. You can read about it on the official Amazon Polly site.

The tells

How to tell a Amazon Polly voice

The human ear is unreliable on current Amazon Polly audio. These are the signals a detector weighs. We report which ones drove the verdict rather than handing you a bare number.

  • 01Production-TTS pacing that does not react to meaning the way a human reader would.
  • 02Synthesis artifacts that persist through telephony-grade compression.
  • 03Uniform spectral balance across a clip a real microphone and room would not hold.
  • 04Even, unvarying energy across long passages.
Spectral view · artifacts concentrate where synthesis smooths what a human voice would not
How the detector identifies Amazon Polly

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.

Step 1

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.

Step 2

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. Amazon Polly, when it recognizes it.

Step 3

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.

0.48s
Median verdict
99%
Accuracy on clean audio
24+
Generators covered
24h
Audio deleted after
If a clip turns out synthetic

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.

FAQ · Amazon Polly

Common questions

Can you detect Amazon Polly on a phone-quality clip?
Often, yes. Compression lowers confidence but rarely erases the signal, and we report the confidence so a low-quality clip is not mistaken for certainty.
Does it matter which app used Polly?
No. The detector reads the audio itself, so it does not matter whether Polly was called from an app, an IVR, or the AWS API directly.
Is there an API for bulk checks?
Yes. The developer API returns the same JSON verdict with webhooks for bulk jobs.
Free to try?
Yes, a single verdict is free with no card.
Will it name Polly specifically?
When the signature is recognizable we name it; otherwise we return 'unknown synthesis'.

Is this a Amazon Polly voice? Find out.

Free verdict, model named, in under a second. No card to start.

Open detectorUse the API