Callyope vs Ellipsis Health (2026)
Two companies built on the idea that a voice carries clinical information, pointed at completely different jobs. Callyope is French and measures. It trained its own audio and language foundation model on psychiatric data rather than adapting a general speech system, and it reads speech for symptom signal in serious mental illness. Its published research is genuine, including cross linguistic and disordered speech work, and it has declared a device class under the European regime, which is more than most voice health companies will do. Ellipsis is American and converses. Sage is an agentic care manager that calls members for health plans and at risk providers, handling enrollment, assessments, surveys and care coordination, powered by what the company calls its Empathy Engine, built on patented vocal biomarker technology and trained on millions of live clinical calls. Its governance has a named process behind it: an ethics committee approving healthcare applications and a clinical team validating every update before release. The buyer is different in each case. Callyope is bought by a clinical or research organization that wants a measurement. Ellipsis is bought by a payer that wants member contact at a scale humans cannot reach.
- The purpose is measurement. It reads speech for psychiatric symptom signal, and the model was built in house on psychiatric data rather than adapted from a general speech system.
- A device position exists and is declared under the regime that governs the company, which is more than almost anything else reading voice for clinical signal publishes.
- European buyers get the governing framework they need: GDPR, ISO 27001 certification and hosting certified under the French health data scheme.
- The purpose is contact. Sage conducts inbound and outbound member conversations at the scale a health plan needs, for enrollment, assessments, surveys and care coordination.
- The named process behind its governance is real: an AI ethics committee approving healthcare applications and a clinical team validating every product update before deployment.
- It is built for the American payer market, where the buyer is a plan or an at risk provider group rather than a clinic.
This comparison is published by AI Health Index, an independent research platform that compares healthcare AI vendors objectively. Callyope and Ellipsis Health are each graded against the same capability taxonomy, from each vendor's own public materials and the regulatory record, under the AI Health Index verification standard. No vendor pays for placement, and no vendor has reviewed this page. How this evidence is graded
Plain facts
| Fact | Callyope | Ellipsis Health |
|---|---|---|
| Primary category | Behavioral Health AI | Patient Voice Agents |
| Founded | 2023 | 2017 |
| Headquarters | Neuilly-sur-Seine, France | San Francisco, California |
| Website | callyope.com | ellipsishealth.com |
Side by Side
Select any grade to read the note behind it.
Each vendor in one paragraph
Written to be quoted whole. Each paragraph opens the AI Health Index profile of the vendor: what the product is, who buys it and what it does.
Callyope is a French company building an audio and language foundation model trained specifically on psychiatric data rather than adapted from a general purpose speech model. It describes the model as transdiagnostic by design, one model across the spectrum of mental health conditions rather than one per diagnosis, trained on voice, language, clinical context and behavioral signals.
Source: AI Health Index, September 2026
Voice AI care management for health plans and at risk providers. The company originated in vocal biomarker research for detecting depression and anxiety from acoustic features, backed by more than ten peer reviewed publications, and that technology is still the engine.
Source: AI Health Index, September 2026
Questions buyers ask
How do Callyope and Ellipsis Health work with the EHR?
For Callyope, the company states that it integrates directly with major record systems to eliminate double data entry, that clinical information flows automatically, and that its outputs, summaries, reports and notes, can be pushed back into the record in the right format, with secure data exchange offered for systems without a direct integration.
With Ellipsis Health, the company names two: a major customer relationship platform's health cloud, where it maintains a listing in that vendor's marketplace, and through a 2026 partnership, a care management suite where it draws on member data and returns outcomes to the platform. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 20, 2026. No vendor pays for placement.
How do Callyope and Ellipsis Health handle patient data?
In Callyope's case, each of those is a figure a customer could hold the company to.
For Ellipsis Health, a privacy policy, a terms of use and, separately, a consumer health data privacy policy are all published, the last being the notice that state consumer health data statutes require. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 20, 2026. No vendor pays for placement.
Which settings and specialties do Callyope and Ellipsis Health cover?
With Callyope, the company names depression, anxiety, insomnia, fatigue, cognitive decline, bipolar disorder, schizophrenia and psychosis, and frames its own scope as the psychiatric, cognitive and motor symptoms of brain disorders more broadly.
In Ellipsis Health's case, the customer boundary is explicit: health plans and at risk provider organizations, not consumers and not clinical settings. The workflow boundary is equally clear and enumerated on the product page across three groups. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 20, 2026. No vendor pays for placement.
What evidence is published for Callyope and Ellipsis Health?
For Callyope, the marketed headline is that thirty seconds of speech assesses ten or more mental health symptoms at over ninety percent accuracy. No published evaluation is tied to that number, the production model is a different artifact from the research models, weights are not released and the proprietary psychiatric training corpus is uncharacterized.
With Ellipsis Health, a partnership embeds the agent into a major care management suite drawing on member data and returning outcomes to the platform, a second places it inside a large customer relationship platform's health cloud, and a third, announced with a leading artificial intelligence hardware company, concerns more natural conversation. From the AI Health Index, drawn from each vendor's own published materials and the regulatory record, verified September 20, 2026. No vendor pays for placement.
Related comparisons
Other published head to head assessments involving these vendors or their closest peers. The full set for this category is on the Remote Monitoring & Chronic Care page.
Both rest on the same premise, that a voice carries clinical signal, and both assert that the signal holds across languages or populations while publishing no per group result. Callyope states that its multilingual capability ensures consistent performance regardless of patient language, and its own registered relapse trial recruits French speakers only and excludes anyone whose condition impairs French.
Ellipsis states equitable service across diverse populations and regular bias audits, and publishes no audit result. Ask both for per group figures before believing either sentence, because speech models vary by accent, dialect, age and first language, and in psychiatric populations medication alters the very features these models read. Neither publishes a price. Callyope names no record system behind its integration claim.
Ellipsis publishes no escalation criterion for a voice agent making outbound calls to recently discharged members, and its consent question is sharper than most: the vendor says vocal cue detection runs in production, so a member who rang about a refill may have an inference drawn from their voice.