Home · Detect · Google WaveNet

Detect Google WaveNet AI voices.

Updated July 2026

Suspect a clip was made with Google WaveNet? Drop it in and get a citable verdict with the model named, in under half a second. Google Cloud's WaveNet and Neural2 voices, a widely embedded, natural-sounding cloud TTS.

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

Google WaveNet, and why it shows up in suspicious audio

WaveNet is the DeepMind-derived neural voice technology behind Google Cloud Text-to-Speech, alongside the newer Neural2 voices. It is one of the most widely embedded cloud TTS systems, appearing in apps, assistants, and automated phone systems worldwide.

Its reach means WaveNet audio shows up in a huge variety of content, so attributing the source is often as useful as the synthetic-or-not verdict itself.

Where you tend to see it: App and assistant voices, automated calls, and narrated content.

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

The tells

How to tell a Google WaveNet voice

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

  • 01Natural but metronomic pacing on longer output.
  • 02A consistent spectral signature across a clip.
  • 03Clean fricatives and phoneme transitions.
  • 04A uniform noise floor uncharacteristic of a live microphone.
Spectral view · artifacts concentrate where synthesis smooths what a human voice would not
How the detector identifies Google WaveNet

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. Google WaveNet, 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 · Google WaveNet

Common questions

Can you detect Google WaveNet voices?
Yes. The detector reads the synthesis signature, though confidence still depends on audio quality and clip length.
Does WaveNet versus Neural2 matter?
Not for whether it is detectable. Both are neural cloud voices the detector treats as in scope; attribution names the source where the signature is clear.
Is a single check free?
Yes, a single verdict is free with no card.
Can I check audio inside a video?
Yes. The detector reads the audio track, so video files work too.
Will it name Google specifically?
When recognizable, yes; ambiguous clips return 'unknown synthesis'.
Detect another generator

We attribute 24+ voice models

ElevenLabsVoice cloning · TTS OpenAI TTSText-to-speech PlayHTTTS · voice cloning Resemble AIVoice cloning · real-time Murf AIStudio TTS SpeechifyRead-aloud TTS DescriptEditing · voice cloning WellSaid LabsStudio TTS Amazon PollyCloud TTS Azure Neural TTSCloud neural TTS SunoAI music · vocals
See all generators → How to detect AI voices → How to verify AI audio → AI voice vs human voice → Spotting AI voice scams →

Is this a Google WaveNet voice? Find out.

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

Open detectorUse the API