Corti vs Nabla (2026)
The two European vendors in this category, and the two best data positions in it, reached by different means. Nabla publishes the full lifecycle: audio not stored, no training on user data, a configurable 14 day retention sized around clinician review, and backups expiring seven days later so deletion actually completes. Corti removes the question instead of answering it, with a sovereign cloud that runs on premise or on any cloud so the audio need not leave your estate. Nabla holds the only positive randomized efficiency result in this category. Corti holds the stronger transparency and oversight position, naming its models, describing its architecture as a mechanism and letting clinicians accept or adjust facts as the consultation runs. Buy Nabla if you want a proven scribe across a mixed record estate. Buy Corti if you are building the documentation layer yourself or cannot let audio leave the building.
- Deployment control is the whole argument. Sovereign cloud, any cloud or on premise, deliberately portable, which is the most substantive protection available for clinical audio because it removes the transfer rather than governing it.
- The transparency posture is the strongest here. Models are named and shipped through documented API endpoints, the architecture is described as a four stage recursive loop rather than as advanced reasoning, and language specific models address accent degradation by engineering.
- It sits below the record system rather than beside it, so a health system or software vendor can embed clinical speech and reasoning into its own product instead of adopting someone else's interface.
- The only ambient scribe in this index with a positive result in a randomized controlled trial it did not run: 9.5 percent reduction in time in note against control, the only arm to meet its primary endpoint, across roughly 72,000 encounters.
- The widest record system footprint in the category, more than 15 platforms named including Epic, Oracle Health, athenahealth, NextGen, Greenway and Altera, which for a mixed estate is one contract instead of several.
- It stayed in its lane. Where nearly every competitor expanded into coding, clinical reasoning or chart question answering and quietly changed its regulatory object, this product remained ambient documentation with clinician review, which is a cleaner risk position than any feature list.
This comparison is published by AI Health Index, an independent research platform that compares healthcare AI vendors objectively. Corti and Nabla 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
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 Corti its top capability grade on several axes, including AI Centrality, Autonomy and Oversight Model and Model and Technology Transparency. Set against Nabla, Corti grades higher on several axes, including Autonomy and Oversight Model, Model and Technology Transparency and AI Governance and Bias Disclosure. 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 Nabla its top capability grade on several axes, including AI Centrality, Clinical and Operational Evidence and AI Safety and PHI Stewardship. Set against Corti, Nabla grades higher on several axes, including Clinical and Operational Evidence, AI Safety and PHI Stewardship and HIPAA and BAA Posture. 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 Corti or Nabla?
On the axes where the AI Health Index separates them, Corti grades higher on several axes, including Autonomy and Oversight Model, Model and Technology Transparency and AI Governance and Bias Disclosure, and Nabla grades higher on several axes, including Clinical and Operational Evidence, AI Safety and PHI Stewardship and HIPAA and BAA Posture. Neither leads on the greater share of scored axes, so the decision turns on which constraint is binding rather than on an overall winner.
Where do Corti and Nabla differ most?
The widest separation the AI Health Index records between Corti and Nabla is on Model and Technology Transparency, where Corti grades A and Nabla 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 Corti and Nabla grade the same?
The AI Health Index grades Corti and Nabla the same on several axes, including AI Centrality, Model Supply Chain Disclosure 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.
Corti's clinical evidence for the documentation product is thin: the 65 percent note bloat figure is vendor generated with no methodology and its clinician attitude statistics come from commissioned surveys. Nabla's published per month pricing was withdrawn during 2026 in favour of a sales motion, so evaluate on the tier you would contract.
An earlier version of this note said its free tier did not include a business associate agreement; that claim traced to competitor comparison pages and Nabla's own terms say the opposite, making agreement to the attached instrument a precondition of use for any customer subject to HIPAA. Corrected 13 September 2026.
Nabla publishes no AI governance artefact, no bias or fairness position and no subgroup performance analysis, which is a distinct gap from its strong security and data governance and is easy to conflate with it.