Summary
Nabla holds the only randomised win in this category. It cut note-writing time by 9.5 percent against a control group across roughly 72,000 encounters, and no competitor has produced evidence of that quality.2
It also never stores the encounter, which is a stronger privacy position than anyone else has taken.1 If evidence or privacy is your deciding question, buy Nabla.
The briefing before the patient sits down, the coding attached, the phone answered.
Book a demoWhat Nabla has that nobody else does
The randomised trial. UCLA assigned 238 physicians across 14 specialties to DAX Copilot, to Nabla, or to usual care. Nabla cut note-writing time by 9.5 percent, about 41 seconds. DAX showed no statistically significant change.22Lukac PJ, Turner W, Vangala S, et al. Ambient AI Scribes in Clinical Practice, A Randomized Trial. NEJM AI 2025;2(12). 238 physicians, 14 specialties, approximately 72,000 encounters. Every other vendor in this market, ourselves included, is quoting somebody else's trial or none at all.
And the privacy architecture. Audio, transcript and note stay in the browser and patient information does not reach Nabla servers.11Nabla reports audio, transcript and note remain in the clinician browser and do not reach Nabla servers. HIPAA, GDPR, SOC 2 Type 2, ISO 27001. SMART on FHIR. Approximately 85,000 clinicians. Pricing unpublished, third-party estimates $119 to $239 per month. That removes the retention question rather than answering it, which is a genuinely different engineering choice and a defensible one.
Why people look anyway
No published price. Third-party estimates put it around $119 to $239 a month, which means you cannot compare it against anything without a call.
And scope. Nabla drafts the note. The trial that proves it works also measured after-hours record time and found no change, and that marks the honest limit of what the product reaches.
The architecture that makes the privacy position possible is also what caps it. A product that never stores your encounter cannot open a briefing before your next patient sits down, because it has nothing to open.
The options
Freed publishes $39 to $119 and signs you up in four minutes, with letters and coding on the top tier. Heidi publishes $150 and has the only real free tier, with EHR push gated above the entry plan. Abridge holds Best in KLAS and the deepest Epic integration at roughly $2,500 a clinician a year with a three to six month procurement. DAX Copilot is the Microsoft path and was the trial arm that showed no significant change.
The number none of them touch
Every product above drafts a note, and the best measured result any of them has is 41 seconds.
Meanwhile up to 19 percent of E/M visits are undercoded at roughly $37 each, and Medicare Advantage downcoding runs a reported $28,000 to $74,000 per family physician per year without ever appearing as a denial.44AAPC Audit Services reports up to 19 percent of E/M visits are undercoded nationwide at roughly $37 each. Reported Medicare Advantage downcoding exposure runs $28,000 to $74,000 per family physician per year. See our guide to downcoding. Switching from Nabla to another scribe changes your invoice. It does not touch that.
What WA\ does instead
WA\ Clinician drafts against the Medical Decision Making criteria and attaches the coding at the point the decision was made. WA\ Admin runs eligibility at booking and answers the phone on the same record. The briefing opens before the patient sits down because the record is there to read.
What we are not claiming
We have no randomised trial and Nabla does. No feature comparison on this page outweighs that, and we are not going to arrange one so it looks like it does. Forty-one seconds measured under randomisation is worth more than any claim we can currently make.
We also store your encounter and Nabla does not. If that is your line, Nabla is the better product and we are not the right purchase.
Availability
WA\ Clinician runs a 14-day free trial with no minimum term. Pricing is on one page.
Frequently asked questions
Is Nabla the best AI medical scribe?
It holds the best evidence, which is not the same claim but is close. UCLA randomised 238 physicians across 14 specialties to DAX Copilot, to Nabla, or to usual care across roughly 72,000 encounters. Nabla cut note-writing time by 9.5 percent, about 41 seconds. DAX showed no statistically significant change. No other vendor in this market has produced evidence of that quality, and everyone else including us is quoting somebody else trial or none at all. Nabla also never stores the encounter, which removes the retention question rather than answering it.
Why would you switch away from Nabla?
Price opacity and scope. Nabla publishes no per-clinician price, with third-party estimates around $119 to $239 a month, so you cannot compare it against anything without a call. And it drafts the note, while the trial that proves it works also measured after-hours record time and found no change. The architecture that makes the privacy position possible is also what caps it. A product that never stores your encounter cannot open a briefing before your next patient sits down, because it has nothing to open.
Does Nabla store patient data?
Nabla reports that audio, transcript and note remain in the clinician browser and that patient information does not reach Nabla servers, alongside HIPAA, GDPR, SOC 2 Type 2 and ISO 27001. It integrates via SMART on FHIR with Epic, athenahealth, Oracle Health, NextGen, Greenway and Altera, and is reported at approximately 85,000 clinicians. That is a genuinely different engineering choice from every competitor including us, and if data residency is your line then Nabla is the better product. Confirm current terms directly, since architecture claims change.
A published price and no discovery call.
Start the trial and run it beside Nabla for a fortnight. If it does not move your evening, you have lost two weeks and nothing else.
About this article. Written and published by WA\, a competitor of Nabla, and we have said plainly that Nabla holds the only randomised evidence in this category and the strongest privacy position, and that we hold neither. The randomised trial cited is independent of us and tested a version of Nabla current in 2025. Nabla does not publish pricing so the figures quoted are third-party estimates. Undercoding and downcoding figures are third-party RCM analysis. All names are marks belonging to their owners.