Detect Resemble AI AI voices.
Suspect a clip was made with Resemble AI? Run it through the free detector to check whether the voice is AI-generated. Resemble AI in short: expressive, low-latency cloning built for dubbing, games, and live calls.
Resemble AI, and why it shows up in suspicious audio
Resemble AI is a voice-cloning platform used for dubbing, game characters, and real-time synthesis. The real-time capability is what makes it relevant to live-call and voicemail fraud, where a voice has to be produced on the fly.
Real-time generation trades a little fidelity for speed, and that trade leaves its own set of artifacts a detector can key on.
Where you tend to see it: Live-call and voicemail fraud, dubbing, and game or media voiceover.
Resemble AI is a legitimate product; misuse is the problem, not the tool. You can read about it on the official Resemble AI site.
How to tell a Resemble AI voice
The human ear is unreliable on current Resemble AI audio. These are the kinds of artifacts a detector is trained to pick up.
- 01Timing and micro-latency patterns that differ from a naturally recorded human.
- 02Expressive but slightly synthetic emotional contours, especially on emphasis.
- 03Spectral artifacts introduced by streaming synthesis.
- 04Consistency across a call that a live human voice, affected by room and movement, would not maintain.
What the detector tells you
The detector reads the audio, not the speaker. Cloned or stock voice, clean or compressed, it looks for the signs of synthesis.
Drop the clip
Upload an MP3, WAV, M4A, OGG, FLAC or AAC file. Three seconds or more of clear speech gives the most reliable result.
The model scores it
The model scores the clip. On longer recordings it scores each segment separately, so you can see which part sounds synthetic.
Read the verdict
You get a verdict on a four-step scale, from Human to AI Generated, plus an AI probability score. It tells you whether the voice is AI-generated, not which tool made it.
What to do next
A verdict is evidence, not proof. Sign in to keep the result in your detection history and share it with a link. If you are a journalist or investigator, use it 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, and a Chrome extension for checking audio in any tab is in development.