Back

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

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

2026-04-06 health informatics
10.64898/2026.04.05.26350190 medRxiv
Show 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.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

1
Nature Medicine
○ 125 papers in training set
Top 0.1%
18.8%
Similar papers in this journal
2
Nature Communications
○ 5641 papers in training set
Top 14%
12.6%
Similar papers in this journal
3
eBioMedicine
○ 183 papers in training set
Top 0.1%
12.1%
Similar papers in this journal
4
Nature Aging
○ 60 papers in training set
Top 0.3%
6.3%
Similar papers in this journal
5
Cell Reports Medicine
○ 153 papers in training set
Top 0.3%
5.6%
Similar papers in this journal
50% of probability mass above
6
Science Advances
● 1243 papers in training set
Top 7%
4.4%
7
Aging Cell
○ 165 papers in training set
Top 0.8%
4.1%
8
Advanced Science
○ 286 papers in training set
Top 2%
3.5%
9
GeroScience
○ 109 papers in training set
Top 0.7%
3.3%
10
Neurobiology of Aging
○ 107 papers in training set
Top 0.5%
3.2%
11
Scientific Reports
○ 3612 papers in training set
Top 45%
2.2%
12
iScience
○ 1154 papers in training set
Top 13%
2.2%
13
eLife
● 5828 papers in training set
Top 54%
1.5%
14
Alzheimer's Research & Therapy
○ 57 papers in training set
Top 1%
1.1%
15
Cell Metabolism
○ 57 papers in training set
Top 1.0%
1.1%
16
npj Aging
○ 22 papers in training set
Top 0.3%
1.1%
17
Communications Biology
○ 993 papers in training set
Top 24%
1.1%
18
Advanced Biology
○ 29 papers in training set
Top 0.7%
0.9%
19
Biogerontology
○ 10 papers in training set
Top 0.2%
0.9%
20
Annals of Neurology
○ 64 papers in training set
Top 2%
0.9%
21
Patterns
○ 78 papers in training set
Top 3%
0.6%

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.