Microsoft Dragon Copilot vs TORTUS (2026)
The two vendors in this category that take error seriously, and they treat it differently. Microsoft names its failure modes in a transparency document and asks the clinician to review the draft. TORTUS filters before the clinician sees anything: the Shell verifies every generated statement against the consultation and removes what it cannot support, then publishes the rate, 92.7 percent of detected hallucinations removed, with a 75 percent reduction in major hallucinations published in npj Digital Medicine. It also co ran a nine site NHS evaluation across more than 17,000 patients with public funding and independent assessment. Naming a risk is good practice; measuring and filtering it is better. The constraint is geography. TORTUS is deep in the NHS and unevidenced outside it, so for a United States health system Dragon Copilot is the practical answer and TORTUS is the benchmark to hold it to.
- Availability and reach. Native Epic embedding, SMART on FHIR, a partner developer kit for other record systems, and clinician availability across ten countries, against a product whose evidence and integrations are concentrated in the NHS estate.
- Role based products for physicians, nurses and radiologists, with flowsheet capture at the bedside, plus multilingual multi party capture and generated referral and patient letters.
- Enterprise contracting your organisation already has, with a central trust portal, published privacy and security documentation and a support relationship that does not require a new vendor onboarding.
- It filters hallucinations before the clinician rather than relying on the clinician to catch them, and publishes how well that works: 92.7 percent of detected hallucinations removed as a live platform metric, and a 75 percent reduction in major hallucinations in a peer reviewed journal.
- The evidence base is prospective, multi site and publicly funded rather than vendor commissioned, spanning nine clinical sites and more than 17,000 patients with NHS England backing and independent evaluation, plus a paediatric study at Great Ormond Street.
- Accent performance was tested by the deploying hospital, not the vendor, and the hospital states publicly that transcription held accurate across a wide variety of accents. That is the failure mode every speech product carries, measured by the party with the regulatory exposure.
This comparison is published by AI Health Index, an independent research platform that compares healthcare AI vendors objectively. Microsoft Dragon Copilot and TORTUS 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 | Microsoft Dragon Copilot | TORTUS |
|---|---|---|
| Primary category | Ambient Scribes | Ambient Scribes |
| Founded | 2025 | 2022 |
| Headquarters | Redmond, Washington, United States | London, United Kingdom |
| Website | microsoft.com | tortus.ai |
Side by Side
Each record in one paragraph
Written to be quoted whole. Each paragraph states what the AI Health Index verified about the vendor, with the caveats attached. Generated from this pair’s live capability grades, so it moves when a grade moves.
The AI Health Index awards Microsoft Dragon Copilot its top capability grade on several axes, including AI Centrality, Model Supply Chain Disclosure and FDA and Regulatory Status. Set against TORTUS, Microsoft Dragon Copilot grades higher on Model Supply Chain Disclosure, FDA and Regulatory Status and EHR and Interoperability Depth. Grades reflect evidence the AI Health Index could verify at the last review, so a low grade records disclosure the vendor has not published rather than a capability it has been shown to lack.
Source: AI Health Index, August 2026
The AI Health Index awards TORTUS its top capability grade on several axes, including AI Centrality, Autonomy and Oversight Model and Model and Technology Transparency. Set against Microsoft Dragon Copilot, TORTUS grades higher on several axes, including Autonomy and Oversight Model, Model and Technology Transparency and Clinical and Operational Evidence. Grades reflect evidence the AI Health Index could verify at the last review, so a low grade records disclosure the vendor has not published rather than a capability it has been shown to lack.
Source: AI Health Index, August 2026
Questions buyers ask
Should we choose Microsoft Dragon Copilot or TORTUS?
On the axes where the AI Health Index separates them, Microsoft Dragon Copilot grades higher on Model Supply Chain Disclosure, FDA and Regulatory Status and EHR and Interoperability Depth, and TORTUS grades higher on several axes, including Autonomy and Oversight Model, Model and Technology Transparency and Clinical and Operational Evidence. TORTUS leads on the greater share of scored axes, but the split means the decision turns on which constraint is binding rather than on an overall winner.
Where do Microsoft Dragon Copilot and TORTUS differ most?
The widest separation the AI Health Index records between Microsoft Dragon Copilot and TORTUS is on Model Supply Chain Disclosure, where Microsoft Dragon Copilot grades A and TORTUS grades C. That axis sits in the AI Capability group, so it should carry the most weight for a buyer whose binding constraint is how much of the work the model itself is trusted to do.
Where do Microsoft Dragon Copilot and TORTUS grade the same?
The AI Health Index grades Microsoft Dragon Copilot and TORTUS the same on several axes, including AI Centrality, HIPAA and BAA Posture and Security Certifications and Trust Center. Neither holds an advantage the index can evidence on those axes, so they should not carry weight in a selection between these two.
Related comparisons
Other published head to head assessments involving these vendors or their closest peers. The full set for this category is on the Ambient Scribes page.
An earlier version of this comparison described TORTUS as holding a UKCA Class I registration, self certified by the manufacturer. The vendor's own homepage lists UKCA Class IIa, which is a different regime and is not self certified. Corrected 15 September 2026, and the class should be confirmed against the certificate before either figure is relied on.
TORTUS's selection for the United Kingdom regulator's AI Airlock sandbox is engagement with a pathway rather than approval under one.
The privacy position is documented, in the wrong regime for a United States buyer. HIPAA alignment appears only in third party listings, with no business associate agreement template or scope statement located, and the subscriber terms are limited to clinicians authorised to treat patients in the United Kingdom, so a United States buyer cannot verify the position before contracting and should ask directly whether an agreement is offered and on what scope. The home regime is documented to real depth: the published subscriber terms carry a full UK GDPR data processing addendum with the Article 28 obligations in full, including processing only on documented instructions, controller audit rights, flow down to subprocessors with a copy of any subprocessor agreement on request, breach notification without undue delay, and deletion or return at termination, alongside an ICO registration number and an NHS Data Security and Protection Toolkit organisation code. Those terms date from November 2024 and predate the product's current device certification, so what a trust signs today may differ.
Neither vendor publishes a rate card. Dragon Copilot's own randomized result, a 1.7 percent reduction in time in note, was not statistically significant, and TORTUS reports an average saving of four minutes per consultation from early adopters rather than from a controlled comparison.