Summary:
A multicenter study of nearly 3,000 individuals published in Science Advances reveals that machine-learning models can infer a person’s biological age and brain health from vocal patterns. This newly developed “speech clock” calculates a “speech age gap” that correlates strongly with neuroimaging brain age, DNA methylation aging, Alzheimer’s blood biomarkers (plasma p-tau217), and lifelong social adversity, providing a scalable, non-invasive window into systemic biological aging.
Key Facts:
- The “Speech Age Gap”: By extracting hundreds of acoustic and linguistic parameters (pitch, pause duration, speech rate, semantic precision, and syntax), machine-learning algorithms estimate chronological age; discrepancies between chronological age and vocal age define accelerated or decelerated biological aging.
- Multimodal Biological Convergence: Accelerated speech age corresponds with structural and functional MRI brain atrophy, three independent epigenetic DNA-methylation clocks, and elevated plasma p-tau217 levels in Alzheimer’s disease.
- Underrepresented Cohort & Social Determinants: Conducted across 2,928 Spanish-speaking participants in five Latin American nations, the model demonstrated that lifelong social adversity (e.g., lower education, food insecurity, reduced healthcare access) measurably accelerates speech aging.
Source: Trinity College Dublin / Global Brain Health Institute
Quantifying how rapidly a human body and brain age relative to chronological time typically demands invasive, expensive, or resource-heavy clinical technology: high-resolution structural MRI, PET scans, whole-genome epigenetic methylation arrays, or fluid biomarker assays. While effective, these diagnostics remain inaccessible to the vast majority of the global population, particularly in developing or rural communities.
Yet every time a person speaks, their voice reflects the coordination of respiratory mechanics, neuromuscular vocal fold control, auditory feedback loops, and high-level cognitive and linguistic processing networks.
Now, an international team led by researchers at the Global Brain Health Institute (GBHI) and Trinity College Dublin has developed a computational “speech clock” capable of assessing biological aging and dementia risk solely through voice recordings.
Published in Science Advances, the study reveals that the difference between chronological age and speech-predicted age, termed the “speech age gap”, serves as a multi-system readout of neurodegeneration, epigenetic aging, and accumulated environmental adversity.
“Our voice appears to contain much more information about aging than we previously recognised,” said senior author Agustín Ibáñez, Ph.D., Professor in Brain Health at Trinity College Dublin’s School of Medicine and GBHI.
“It captures both the passage of chronological time and signals coming from cognition, the brain, systemic biology, and even our accumulated social environment. This raises the possibility that something as simple and accessible as speech clocks, maybe combined with biomarkers, could eventually complement much more expensive measures of aging.”
Analyzing Nearly 3,000 Individuals Across Latin America
Dementia biomarker research has historically been skewed toward high-income cohorts in North America and Western Europe. Addressing this disparity, the researchers evaluated 2,928 Spanish-speaking participants across five Latin American nations: Argentina, Chile, Colombia, Mexico, and Peru. The diverse cohort encompassed cognitively unimpaired older adults, individuals with mild cognitive impairment (MCI), and patients diagnosed with Alzheimer’s disease or frontotemporal dementia (FTD) variants.
Rather than isolating individual vocal metrics, the team deployed machine-learning architectures trained on hundreds of acoustic and linguistic parameters simultaneously. Features included:
- Acoustic Dynamics: Fundamental frequency (pitch), speech cadence, pause length, vocal timbre, and emotional modulation.
- Linguistic Architecture: Vocabulary richness, lexical density, semantic coherence, syntactic complexity, and total verbal output structure.
The algorithm combined these parameters into a composite index to estimate chronological age, generating an individualized speech age gap.
A Unified Signal of Brain, Epigenetic, and Molecular Decline
Participants exhibiting an accelerated speech clock, whose voices sounded older than their chronological years—showed widespread evidence of accelerated aging across multiple physiological domains:
- Structural and Functional Brain Age: Higher speech gaps correlated with MRI-derived brain atrophy, particularly cortical thinning and compromised functional connectivity.
- DNA Methylation Clocks: The vocal gap tracked with accelerated biological age measured across three independent epigenetic DNA-methylation clocks.
- Plasma Biomarkers: In patients with Alzheimer’s disease, accelerated speech aging was linked to elevated plasma levels of phosphorylated tau 217 (p-tau217), one of the most sensitive fluid biomarkers of Alzheimer’s pathology.
- Global and Non-Linguistic Cognition: Increased speech gaps reflected poorer executive functioning, working memory deficits, and decreased daily functional independence, even on cognitive tasks that did not involve language.
The speech clock clearly discriminated between diagnostic tiers: healthy participants exhibited the smallest speech age gaps, while progressively wider gaps appeared across MCI, Alzheimer’s disease, and clinical variants of frontotemporal dementia.
The Social Exposome Leaves Its Mark on Speech
The researchers discovered that speech aging is shaped not only by internal biology, but also by external socioeconomic realities. Across both healthy controls and dementia cohorts, individuals who experienced adverse lifelong social conditions, characterized by lower educational attainment, food insecurity, limited medical access, and financial precarity, showed pronounced acceleration in their speech age gap.
The authors caution that the speech clock remains an investigational research framework rather than an off-the-shelf diagnostic test. Because the primary findings were derived from cross-sectional data, prospective longitudinal investigations will be essential to verify whether an older speech profile can predict prospective cognitive decline before symptoms surface.
“From chronological age to brain aging, epigenetic aging, cognition, Alzheimer’s-related pathology, social exposures, and dementia phenotypes, information traditionally obtained through very different and often expensive measurements appears to converge, at least partly, in the way we speak,” said Prof. Ibáñez. “If confirmed longitudinally and across populations, speech could ultimately become one of the most scalable tools for monitoring healthy and accelerated aging.”
Editorial Notes:
- This article was edited by a Neuroscience News editor.
- Journal paper reviewed in full.
- Additional context added by our staff.
About this genetics and neurodevelopment Research:
- Media Contact: Thomas Deane
- Source: TCD
- Image Credit: Image credited to Neuroscience News
- Original Research is Open Access: Science Advances (Sept 30, 2026). “Speech clocks decode dementia phenotypes, social exposome, and biological aging.” Authors: Hernan Hernandez, Lizeth Katherine Pedraza, Hernando Santamaria-Garcia, Sebastian Moguilner, Agustina Legaz, Pavel Prado, Jhosmary Cuadros, Lucía Amoruso, Liset Gonzalez, Damián Dellavale, Juan Pablo Espinoza–Puelles, Javier Palma Espinosa, Cecilia Jarne, Fabio Mattiussi, Matías Caccia, Alejandro Sosa Welford, Nicolás Pelella, Jeremías Inchauspe, Franco J. Ferrante, Gonzalo Pérez, Marcelo Adrián Maito, Guido Rocatti, Maria Eugenia Godoy, Joaquin Migeot, Paulina Orellana, Ariel Caviedes, Martin Bruno, Leonel Takada, Andrea Slachevsky, Maria I. Behrens, Bárbara Bruna, David Aguillon, Lina Zapata, Jose Alberto Avila-Funes, Nilton Custodio, Bruce Miller, Maria Luisa Gorno-Tempini, Stefanie Pina Escudero, Pablo Reyes, Kun Hu, Maira Okada de Oliveira, Carlos Coronel-Oliveros, Josephine Cruzat, Juan Felipe Cardona, Michael Corley, Irene B. Meier, Vaibhav A. Narayan, Enzo Tagliazucchi, Sandra Baez, Claudia Duran-Aniotz, Adolfo M. García, and Agustin Ibanez.
- DOI: 10.1126/sciadv.aef9864
Abstract
Speech clocks decode dementia phenotypes, social exposome, and biological aging
Biological aging clocks offer estimations of aging and dementia, yet scalability is limited. We introduce a large-scale, cross-national speech clock derived from 2928 individuals across five Latin American countries, spanning healthy controls (HCs), mild cognitive impairment (MCI), Alzheimer’s disease (AD), and non-language/language-dominant frontotemporal dementia (nldFTD/ldFTD).
Multimodal acoustic and linguistic features were trained with supervised models to estimate chronological age, generating speech age gaps (SAGs) as cross-sectional markers of deviations from chronological age, with positive values interpreted as relatively older-appearing speech profiles.
SAGs differentiated diagnostic groups (HCs < patient groups, with AD < nldFTD < ldFTD). This pattern was associated with clinical/cognitive domains. SAGs correlated with phosphorylated tau (p-Tau217) in AD and social exposome in HCs and AD. Brain clocks (structural/functional/combined) were associated with SAG in AD, nldFTD, and ldFTD.
Epigenetic age correlated with SAGs in HCs and AD across Hannum, Retroclock, and OMICmAge, whereas ldFTD associations were limited to Retroclock and OMICmAge.
These results indicate that SAGs capture cross-sectional multilevel aging-related variation and may offer a scalable, culturally adaptable, low-cost biomarker candidate for research in underrepresented global settings.
