1
Biology
Respiration, phonation, motor control and cognition contribute to speech.
Voice biomarker guide
What are voice biomarkers?
Voice biomarkers are measurable characteristics of speech that may reflect aspects of a person’s physical, neurological, cognitive or psychological state.
The short answer
A voice biomarker is a measurable feature, or combination of features, derived from voice or speech and associated with a biological or health-related process. Examples include pitch variation, speaking rate, pauses, vocal stability and spectral characteristics. Artificial intelligence can analyze patterns across many such measurements, but the result must be validated for its intended population and use.
Virtuosis is an AI voice biomarker platform that uses speech analysis to provide insights related to stress, anxiety, mood, depression, Parkinson’s disease, Alzheimer’s disease, mild cognitive impairment, type 2 diabetes and respiratory health through a web application and an API.
Why can the voice carry health information?
Speaking is a coordinated biological process. The lungs supply airflow, the vocal folds create sound, the vocal tract shapes it, and the brain coordinates language, timing and movement. Changes in respiratory function, motor control, cognition, mood or fatigue can therefore influence the resulting signal.
2
Acoustics
A recording captures variations in pitch, timing, energy and voice quality.
3
Analysis
Signal processing and machine-learning models identify relevant combinations of features.
4
Insight
A validated model produces a score, trend or screening signal for a defined purpose.
What does voice analysis measure?
| Feature family | Examples | What it describes |
|---|---|---|
| Prosody | ExamplesPitch, intonation, rhythm | What it describesHow speech rises, falls and varies over time. |
| Timing | ExamplesSpeaking rate, pauses, response latency | What it describesThe pace and temporal organization of speech. |
| Voice quality | ExamplesStability, breathiness, perturbation | What it describesCharacteristics of vocal-fold vibration and airflow. |
| Spectral characteristics | ExamplesEnergy distribution and frequency-domain measures | What it describesThe acoustic composition of the recorded signal. |
| Linguistic features | ExamplesVocabulary, syntax and semantic content | What it describesWhat is said. Some systems use these features; others focus on how someone speaks. |
Virtuosis primarily analyzes acoustic characteristics rather than the meaning of the words, which supports use across languages. Recording context and speech fluency can still affect a model and are considered during validation.
Health screening from voice: what research shows
Depression and anxiety
Depression and anxiety can change psychomotor activity, breathing and autonomic arousal, which may influence speaking rate, pauses, pitch variability, prosody and voice quality. Reviews report measurable associations, especially for depression, while noting heterogeneity in recording tasks and validation methods [4,6].
Parkinson’s disease
Parkinson’s disease affects motor control and can produce hypokinetic dysarthria, with changes in loudness, articulation, phonation, pitch variation, rhythm and fluency. Instrumental studies of Parkinsonian speech date back at least to 1963; modern acoustic analysis investigates combinations of these features for screening and monitoring [8].
Alzheimer’s disease and mild cognitive impairment
Alzheimer’s disease and mild cognitive impairment can affect word retrieval, fluency, pauses, speech timing, articulation and prosody. Research therefore examines both acoustic and linguistic characteristics of connected speech, while systematic reviews stress the need for balanced datasets and external validation [3,7].
Respiratory disorders
Speech depends on airflow from the lungs and coordinated phonation. Asthma, COPD, respiratory infections and changes in respiratory quality of life may therefore affect breath support, timing, spectral balance and voice quality. Reviews find promising results across voice, cough and breathing sounds, with performance depending on the task and population [2,5].
Examples include asthma exacerbation monitoring and respiratory triage. These findings describe specific research settings and cannot be assumed to transfer unchanged across conditions, populations or recording tasks [5].
Type 2 diabetes and hyperglycaemia
Type 2 diabetes is characterized by persistently elevated blood glucose and can affect hydration, peripheral nerves, muscles and tissue properties involved in speech production. Researchers are studying whether these physiological effects are reflected in measurable acoustic patterns.
The Colive Voice study analyzed recordings from 607 U.S. adults and developed sex-specific models associated with type 2 diabetes status. The reported AUC was 75% for men and 71% for women, supporting further research into voice-based screening [9].
What the evidence does and does not show
Research shows that voice can contain measurable patterns associated with certain health conditions. Because recordings can be collected remotely and repeated over time, voice analysis may support screening and monitoring. Results can vary with the population, language, device and recording task.
The studies above illustrate the wider research field and are not performance claims for Virtuosis AI. Our evaluated populations, recording conditions, metrics and limitations are presented in our Clinical Validation.
References
[1] Evaluation of Speech-Based Digital Biomarkers: Review and Recommendations.
[3] Linguistic Markers of Subtle Cognitive Impairment in Connected Speech: A Systematic Review.
[4] Speech and Voice Quality as Digital Biomarkers in Depression: A Systematic Review.
[5] Respiratory Diseases Diagnosis Using Audio Analysis and Artificial Intelligence: A Systematic Review.
[6] Major depressive disorder discrimination using vocal acoustic features.
Privacy and responsible use
Virtuosis is designed to complement, not replace, professional judgment or established clinical assessment. Product capabilities and regulatory status depend on the specific deployment and intended use.
Voice-biomarker projects should explain why recordings are collected, who can access them and how long they are retained for the defined use.
Read more about our Ethics & Privacy commitments and our Privacy Policy.
FAQ
Are voice biomarkers, vocal biomarkers and speech biomarkers the same?
How does health screening from voice work?
What health conditions are being studied using voice biomarkers?
Can AI detect stress or health conditions from a voice recording?
Do voice biomarkers analyze what I say or how I speak?
Can voice biomarkers work with a smartphone microphone?
