Home · Detect · Tortoise

Detect Tortoise AI voices.

Updated July 2026

Suspect a clip was made with Tortoise? Drop it in and get a citable verdict with the model named, in under half a second. Open-source TTS known for high-quality, natural output and multi-voice cloning, at slow generation speeds.

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

Tortoise, and why it shows up in suspicious audio

Tortoise-TTS is an open-source text-to-speech model prized for unusually natural, high-quality output and the ability to mimic a voice from samples. It trades speed for fidelity, which is part of why its clips can be so convincing.

As with other self-hosted tools, there is no account or platform trail; the audio is the record, and the detector reads the synthesis signature the fidelity cannot hide.

Where you tend to see it: High-quality cloned narration, self-hosted projects, and impersonation.

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

The tells

How to tell a Tortoise voice

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

  • 01High fidelity paired with prosody that is more regular than a real speaker's.
  • 02Consistent timbre across a passage a human would color differently.
  • 03Clean phoneme transitions that are slightly too smooth.
  • 04A uniform noise floor with no room signature.
Spectral view · artifacts concentrate where synthesis smooths what a human voice would not
How the detector identifies Tortoise

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. Tortoise, 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 · Tortoise

Common questions

Does Tortoise's high quality defeat detection?
No. Fidelity does not remove the synthesis signature; the detector reads acoustic traces that survive even clean, natural-sounding output.
Can you detect a cloned voice from Tortoise?
Yes. Cloning is in scope, with confidence depending on audio quality and clip length.
Is a single check free?
Yes, a single verdict is free with no card.
Can I check a video's audio?
Yes. The detector reads the audio track, so video files work too.
Will it name Tortoise specifically?
When recognizable, yes; ambiguous clips return 'unknown synthesis'.

Is this a Tortoise voice? Find out.

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

Open detectorUse the API