Submit a recording
Send a supported speech recording through the API.
Voice biomarkers are measurable characteristics of speech that may reflect aspects of a person’s physical, neurological, cognitive or psychological state.
Virtuosis AI provides a voice biomarker API that lets product and research teams submit speech recordings and receive structured acoustic insights for supported health, wellbeing and communication applications.
Integrate the API in four clear steps. Exact audio formats, authentication requirements and response fields are maintained in the developer documentation.
Send a supported speech recording through the API.
Virtuosis measures patterns such as pitch, pace, rhythm and voice quality.
Your application receives model outputs for the selected supported use case.
Use the results within your research, screening, monitoring or communication workflow.
Feature family
Examples
What it describes
Prosody
Pitch, intonation, rhythm
How speech rises, falls and varies over time.
Timing
Speaking rate, pauses, response latency
The pace and temporal organization of speech.
Voice quality
Stability, breathiness, perturbation
Characteristics of vocal-fold vibration and airflow.
Spectral characteristics
Energy distribution and frequency-domain measures
The acoustic composition of the recorded signal.
Semantic content
Words, vocabulary and meaning
Not the primary focus of Virtuosis acoustic analysis.
Virtuosis primarily analyzes acoustic characteristics rather than the meaning of the words. Recording context, language, device quality and speech fluency can still influence performance and are considered during validation.
Use voice-derived acoustic measurements within approved studies and validation programmes for defined populations and intended uses.
Integrate supported voice biomarkers into workflows that help professionals identify changes and prioritize follow-up.
Add voice analysis to telehealth, remote monitoring and digital-health services through a documented API.
Support applications that analyze fatigue, stress and communication patterns while keeping intended-use boundaries clear.
API availability does not make every output clinically valid for every context. Performance depends on the intended use, population, recording conditions, reference standard and deployment environment.
Each model should be used only for the purpose, population and workflow for which it has been developed and evaluated.
Performance should be assessed across relevant populations, languages and recording conditions before deployment.
Validation compares model outputs with appropriate clinical, behavioral or operational reference measures.
Results complement professional judgment and should not be treated as a standalone medical diagnosis.
Deployment requirements depend on the selected use case and integration. Virtuosis documents authentication, supported inputs and response fields in the API reference, while project-specific validation and hosting requirements are confirmed during implementation.
Voice recordings can be sensitive personal data. Collection, access, retention and deletion should follow the agreed legal basis, consent process and deployment configuration.
Confirm authentication, supported audio inputs and the response fields required by your workflow.
Submit recordings through the documented API endpoints.
Test the integration with representative recordings and evaluate performance for the intended use.
Monitor data quality, model scope and user communication after launch.
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.
Data handling depends on the agreed deployment. Voice recordings should be collected transparently, protected appropriately and retained only for the documented purpose and duration.
Read more about our Ethics & Privacy commitments and our Privacy Policy.