Expose AI-generated voice fraud in real time. Powered by Resemble Detect inside the Telnyx Voice API, deepfake detection analyzes audio frame-by-frame to distinguish real voices from spoofed ones — at the network layer, with no impact on call audio or latency.

Built into the Telnyx Voice API, deepfake detection gives you real-time protection against AI-generated voice fraud — no extra infrastructure, no added latency.

Resemble Detect uses a deep neural network trained to distinguish real audio from spoofed versions. It analyzes audio frame-by-frame, so any amount of inserted or altered audio is accurately detected.
Enable deepfake_detection when dialing or answering a call. Telnyx streams the remote party's audio to the detection service, which returns a result within your configured timeout. You receive a call.deepfake_detection.result webhook with the classification — or a call.deepfake_detection.error webhook if something went wrong. The call proceeds normally while detection runs in the background.

AI-generated voice content is growing in volume and sophistication. The ability to verify what's real is no longer optional. Deepfake Detection catches fraud at the network layer — on the same platform where your calls already happen.
The EU Data Act also requires transparency around AI-generated content and data usage. Deepfake Detection with Resemble Detect gives you a documented way to identify and flag synthetic voice content, helping you meet those requirements.
Full API reference, parameters, and code examples for enabling deepfake detection.
Learn how to create a Voice API application and place your first call.
Webhook payload reference for detection results, including signature verification.
Announcement and overview of deepfake detection with Resemble Detect.
Buy a number, create your Voice API application, and manage your account.