Home · Detect · PlayHT

Detect PlayHT AI voices.

Updated July 2026

Suspect a clip was made with PlayHT? Drop it in and get a citable verdict with the model named, in under half a second. Smooth production TTS tuned for narration and IVR, with optional cloning.

Synthetic detectedPlayHT
Confidence
high
Model
PlayHT
Yes, you can check. Drop the clip into the detector and it returns the probability that the speech was generated by PlayHT, 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 PlayHT voices alike, and gives you a citation URL to quote.
What it is

PlayHT, and why it shows up in suspicious audio

PlayHT is a text-to-speech and voice-cloning platform popular for content narration, podcasts, and phone-system (IVR) prompts. Its cloned voices show up in both legitimate media and impersonation attempts.

Its focus on long-form and telephony audio means PlayHT clips often arrive already compressed, which is exactly the harder case a good detector has to handle honestly.

Where you tend to see it: IVR and phone prompts, narrated content, and cloned-voice impersonation.

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

The tells

How to tell a PlayHT voice

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

  • 01Prosodic regularity typical of production TTS, especially in long narration.
  • 02Vocoder fingerprints that persist through telephony-grade compression.
  • 03Consistent pacing that does not react to punctuation the way a human reader would.
  • 04Uniform spectral balance across a clip that a real microphone-and-room recording would not hold.
Spectral view · artifacts concentrate where synthesis smooths what a human voice would not
How the detector identifies PlayHT

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. PlayHT, 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 · PlayHT

Common questions

Can you detect a PlayHT cloned voice?
Yes. Cloning does not remove the underlying synthesis signature, though confidence still depends on audio quality and clip length.
Does phone-line quality defeat it?
Compression lowers confidence but rarely erases the signal. We report the confidence so a low-quality clip is not mistaken for a certain verdict.
What do you do with my audio?
It is deleted within 24 hours. Saved verdicts keep a one-way fingerprint, never the file itself.
Is there an API for PlayHT detection?
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.

Is this a PlayHT voice? Find out.

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

Open detectorUse the API