Sound of Aging: Large-Scale Evidence for a Voice-Based Biological Clock

Krongauz, D., Marmor, Y., Zulti, A., Godneva, A., Weinberger, A., Segal, E.

Weizmann Institute of Science · medrxiv

Abstract

Using 30-second voice recordings from 7,081 adults aged 40-70, we trained gender-specific models to estimate voice-predicted age (Voice Age). Voice Age correlated with chronological age comparably to established omic and physiological aging clocks, while capturing an independent dimension of biological aging. Accelerated vocal aging showed association with higher adiposity, impaired sleep physiology, and cardiometabolic risk markers, supporting voice as a scalable, non-invasive functional aging biomarker.

The following analysis is generated by AI and may contain errors. It is separate from the authors’ abstract and is not peer review.

Research summary

The paper claims that voice-based biological aging can serve as a non-invasive biomarker for assessing biological age. This research is relevant as it explores a novel approach to measuring biological aging, which could contribute to understanding and potentially addressing the root causes of aging.

Author of this paper? Send a correction.