A new artificial intelligence tool that analyzes speech could give users a glimpse of how they are aging and whether they are at risk of dementia, a new study suggests. The tool analyzes hundreds of speech and language patterns to estimate the user’s chronological age from the way they talk. In a study involving nearly 3,000 Spanish-speaking adults, those whose estimated age was higher than their actual age were more likely to have cognitive problems, dementia, and signs of accelerated biological aging.
Researchers reported the findings in the journal Science Advances. Furthermore, people with older-sounding speech were also more likely to have less favorable social and economic circumstances than other participants.
How the Speech Aging Clock Works
This voice-analyzing tool is similar to other aging clocks, which use various biological markers to predict risk of age-related diseases. Existing aging clocks often rely on brain scans or blood tests that are expensive, invasive, or difficult to repeat regularly.
“Existing aging clocks are very powerful, but many of them rely on brain scans or blood tests that are expensive, invasive or difficult to repeat regularly,” said study co-author Adolfo García, director of the Cognitive Neuroscience Center at the University of San Andrés in Argentina. “All of these limitations can be overcome with speech.”
However, the approach still needs testing over time and in other languages before doctors can use it to assess individual patients’ dementia risk, experts said.
Inside the Study: 2,900 Adults Across 5 Latin American Countries
Researchers used data from the ReD-Lat consortium, a large dementia research project in Latin America. The analysis included over 2,900 Spanish-speaking adults from Argentina, Chile, Colombia, Mexico, and Peru, with ages ranging from 18 to 88. Of them, about 1,500 were cognitively healthy, while others had mild cognitive impairment, usually marked by mild memory problems and trouble thinking, Alzheimer’s disease, or frontotemporal dementia.
Each person completed seven tasks, such as describing an animated video, naming as many words, vegetables, or animals as possible in 60 seconds, and retelling a short story immediately after hearing it and again 20 to 30 minutes later.
Scientists recorded, transcribed, and then identified more than 700 distinct features, including pauses, speaking speed, pitch, vocabulary, and emotional expression. They trained a machine-learning model using those features and participants’ chronological ages, teaching it to estimate age from speech. The model generated a predicted age for each participant, and researchers compared it with actual age to calculate what they called a speech-age gap.
What Older-Sounding Speech Revealed
Some people’s speech appeared older than expected for their age, the AI tool determined. Cognitively healthy people had the smallest gaps between true age and AI-assigned age, while people with mild cognitive impairment or dementia had larger gaps. The largest gaps were seen in people with language-dominant frontotemporal dementia, which primarily affects communication. Moreover, people with older-sounding speech also performed worse on various tests of memory, language, and attention, and they had more difficulty with everyday function.
Blood tests showed a similar pattern. Larger gaps were associated with greater age acceleration on three epigenetic clocks, which estimate biological age by looking at chemical tags on DNA that affect gene expression. Among people with Alzheimer’s disease, larger gaps were also linked to higher levels of p-tau217, a protein associated with the disease. Larger gaps were also correlated with dementia risk factors such as financial difficulties, food insecurity, limited healthcare, difficult childhoods, or less education. The pattern was similar across all five countries despite social and cultural differences, García noted.
What the Speech Clock Cannot Tell Us Yet
The approach is “a huge leap toward making brain health assessments accessible to everyone,” said Dr. Manisha Parulekar, co-director of the Center for Memory Loss and Brain Health at Hackensack University Medical Center in New Jersey, who was not involved in the study. But the speech clock is not a crystal ball. “The human voice is incredibly sensitive to our overall well-being, which means a person’s speech could sound ‘older’ simply because they are severely depressed, exhausted, or navigating serious life stress,” Parulekar told Live Science in an email. “As a clinician, I wouldn’t use this tool to definitively diagnose someone with dementia in isolation.”
Instead, the speech measure could serve as an additional tool that prompts doctors to take a closer look at a patient’s cognitive health, she suggested. In the study, many participants were assessed at a single point in time rather than monitored over a longer period. Therefore, researchers could not determine whether an older-sounding voice can predict whether a patient will soon experience cognitive decline, or whether certain voice changes occur as dementia progresses.
Plus, the model was trained and tested only in Spanish-speaking participants from five Latin American countries. “We cannot just take the Spanish model and plug English into it,” Parulekar said. The language-specific features would need adaptation and testing in other populations. The researchers now plan to test the approach with other languages and follow people over time to see whether speech changes can signal future decline.
“I truly believe that there is a very, very strong signal in speech to anticipate dementia and conversion in the future,” García said, “but we need many more diverse studies.”
Analysis: Why Speech Could Be the Most Accessible Aging Clock
1. Non-invasive and low-cost: Unlike MRI or blood-based epigenetic clocks, speech can be recorded remotely via smartphone, making repeat testing feasible.
2. Multidimensional signal: The tool captures 700+ features including pause duration, speech rate, pitch variability, vocabulary richness, and emotional expression, reflecting both cognitive and socio-economic determinants.
3. Socioeconomic link: Larger speech-age gaps correlated with financial hardship, food insecurity, and limited education, highlighting how social determinants accelerate biological aging.
4. Not ready for diagnosis: Current evidence is cross-sectional and Spanish-only. Clinical use will require longitudinal validation and language-specific models to avoid misinterpreting depression, fatigue, or stress as dementia.
Q&A
Q: What does the new AI speech tool do?
A: It analyzes over 700 speech features to estimate chronological age from speech and calculates a speech-age gap between predicted and actual age.
Q: What did the study of 2,900 people find?
A: People whose speech sounded older than their actual age were more likely to have mild cognitive impairment, Alzheimer’s or frontotemporal dementia, worse memory and function, and signs of accelerated biological aging on epigenetic clocks and p-tau217.
Q: Can this AI tool diagnose dementia now?
A: No. Experts say it is not a diagnostic tool yet. It needs longitudinal testing and validation in other languages like English before clinical use.
FAQ
1. What is a speech-age gap?
The difference between the age AI predicts from your speech and your real chronological age. A larger gap means speech sounds older than expected.
2. What is an aging clock?
Aging clocks are models that estimate biological age and disease risk using biomarkers. This new clock uses speech instead of blood or brain scans.
3. Who conducted the study?
Researchers from the ReD-Lat consortium and University of San Andrés, led by co-author Adolfo García, published in Science Advances, with data from Argentina, Chile, Colombia, Mexico, and Peru.
4. Is the tool affected by mood or stress?
Yes. Experts note voice is sensitive to depression, exhaustion, and life stress, which could make speech sound older without dementia.
5. Will it work in English?
Not yet. The model was trained only on Spanish speakers. Language-specific features must be adapted and tested for English and other languages.
Disclaimer: It is for general news and educational purposes only and does not provide medical advice, diagnosis, or dementia screening.
