Speech read on your trial’s own scale between visits, and a check of every recorded rating interview

Participants record a few minutes of speech at home on their own phone, and each reading is joined to the visit score. Trial QC returns flags per rater from the rating interviews that your sites or central rating vendor record.

Talk to our team

A rater conducting a recorded rating interview

A participant speaking into his own phone at home

A participant recording a short speech session at home

Built for regulated clinical trials

For clinical programs

Speech readings between visits

Each reading sits on the scale your protocol already carries, joined to the visit score and pre‑specified in your SAP as an exploratory endpoint.

See speech biomarkers

For clinical operations

Every recorded interview checked

At every site, screening interviews are read as their audio and scores arrive, so a score can be queried before randomization; baseline interviews are read before the next data transfer. Flags per rater go to your blinded study team or central rating vendor; Cephalgo never changes a score or contacts a rater.

CDR and NPI MADRS and HAM‑D PANSS

See Trial QC

Why speech

Speech carries motor, cognitive and psychiatric signs

Speaking uses the brain, breathing, the voice box and the muscles of the mouth together, so one short session can hold all of these signs.

More readings between visits
Short sessions at home between site visits, so a change in grade can show up before the next visit. In a dose-finding study, each dose arm has more readings before the dose decision; readings per arm are seen only by the independent statistician and data monitoring committee.
Nothing to wear
A tap to start on the participant’s own phone. No wearable to ship, charge or return, and no extra site visit.
State of the art, and no black box
Named voice and language features behind every reading. The reference model is calibrated on your study’s screening and baseline ratings, blind to arm and locked before any post‑baseline reading; success criteria are fixed in writing with your statisticians. For your statistician ›

A participant reading on his own phone at home

Why Cephalgo

Your scale, your audio, stable when phones change

Your scaleNo new scale

Readings on the scale your trial already scores, so rater, scale and scoring stay unchanged.

How a reading is made Your audioAudio you hold

Re‑analysis of the audio or video a completed or ongoing trial holds, as consented under its protocol, with no new collection or protocol change. From a completed trial, variance components to size your next study.

Re-analysis pilot Phone changesStable readings

Recalibrated from the audio alone, blind to arm, when a phone or its software changes.

Device changes

Ways to start

Pick a starting scope

Start from recordings you already hold, from baseline in a new study, from rating interviews at each data transfer, or before the screening visit. The fee and timeline are fixed in writing before any data moves.

News and resources

What’s new at Cephalgo

Our methods are presented at scientific meetings on neurology, CNS trials and digital biomarkers. White papers on Alzheimer’s, Parkinson’s, Huntington’s and ALS are available on request from our research page.

White paper