People are poorly equipped to detect AI-powered voice clones

Abstract As generative artificial intelligence (AI) continues its ballistic trajectory, everything from text to audio, image, and video generation continues to improve at mimicking human-generated content. Through a series of perceptual studies, we report on the realism of AI-generated voices in ter...

Full description

Saved in:
Bibliographic Details
Main Authors: Sarah Barrington, Emily A. Cooper, Hany Farid
Format: Article
Language:English
Published: Nature Portfolio 2025-03-01
Series:Scientific Reports
Online Access:https://doi.org/10.1038/s41598-025-94170-3
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Abstract As generative artificial intelligence (AI) continues its ballistic trajectory, everything from text to audio, image, and video generation continues to improve at mimicking human-generated content. Through a series of perceptual studies, we report on the realism of AI-generated voices in terms of identity matching and naturalness. We find human participants cannot consistently identify recordings of AI-generated voices. Specifically, participants perceived the identity of an AI-generated voice to be the same as its real counterpart approximately $$80\%$$ of the time, and correctly identified a voice as AI generated only about $$60\%$$ of the time.
ISSN:2045-2322