The science · vocal biomarkers

Voice carries respiratory, neuromuscular, cognitive, and affective signal — at the same time.

Decades of phoniatrics and speech science give us a defensible map between what the voice does and what's happening upstream. Audexia operationalizes that map. Click around — this page is interactive.

Conditions

Pick a condition. See which acoustic features matter.

Each condition fingerprint is built from peer‑reviewed feature‑to‑condition associations. Audexia scores all of them in parallel from a single 90‑second session.

Acoustic features

Hover or tap any feature. See the waveform, hear the intuition.

Each feature has a clean physical interpretation — and a known set of conditions it's sensitive to. Audexia ships them as a single, model‑agnostic feature vector.

Try it · /a/

Say "ahhhh" for ten seconds. Watch your voice get scored.

This is a one‑task demo of the same engine clinicians use. Pitch, jitter, shimmer, and HNR compute live from your microphone. Nothing is uploaded — audio stays in your browser tab and is discarded the moment you leave.

idle

No microphone? Run a synthetic sample instead.

sustained /a/ · live 00:00 / 00:10
F0
— Hz
Jitter
— %
HNR
— dB
Task battery

Six standardized voice tasks. Ninety seconds, end to end.

Each task isolates a different speech subsystem. The clinician picks the bundle; Audexia handles the order, prompts, and quality gates.

TASK 01

Sustained vowel /a/

Phonatory stability and respiratory support. Drives jitter, shimmer, HNR, F0 stability.

10s minimum
TASK 02

DDK · /pa‑ta‑ka/

Diadochokinetic rate and regularity. Primary bulbar marker — sensitive to early ALS.

10s · ~6 reps/s
TASK 03

Read‑aloud passage

Standardized phonetic content. Rate, prosody, articulation precision in controlled context.

~25s
TASK 04

Picture description

Connected speech under planning load. Articulatory deficits surface here when sustained /a/ looks normal.

45s
TASK 05

Counting · automatic

Overlearned motor program. Reveals reduced loudness scaling and festination.

15s
TASK 06

Cognitive stressor

Brief verbal fluency or serial 7s. Elicits state‑level affective and cognitive modulation.

30s
Honest framing

Voice is a correlate. Not a verdict.

Many factors beyond pathology shape acoustic features — age, sex, individual style, medication, fatigue, microphone, environment, and task choice all leave fingerprints. Audexia is built to augment clinical assessment, not replace it. Every observation we write to the chart includes its provenance, the model version that produced it, and the quality envelope of the underlying capture. Clinicians decide.