Summary
Nabla holds the only randomised win in this category. It cut note-writing time 9.5 percent against a control group across roughly 72,000 encounters.2 Every other vendor here, ourselves included, is quoting someone else research or none.
It also never stores your encounter.1 If evidence or data residency decides this for you, buy Nabla and we mean that.
Leave the room with the note, the letters, the codes and the cited answers already written. Fourteen days free, then one published price.
Book a demo| What you get | Nabla | WA\ |
|---|---|---|
| Randomised evidence of effect | Yes, the only one22Lukac 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. | None published |
| Encounter stored | Never11Nabla 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 with Epic, athenahealth, Oracle Health, NextGen, Greenway and Altera. Approximately 85,000 clinicians. Pricing unpublished, third-party estimates $119 to $239 per month. | Yes, on the record you own |
| The note drafted from the room | Yes | Yes |
| A briefing before the patient sits down | Not possible by design | Yes, built from the chart |
| ICD-10 coding attached to the decision | Yes | Yes, drafted against MDM |
| The phone, email and WhatsApp answered | Not offered | Yes, same record |
| Eligibility checked at booking | Not offered | Yes |
| Published price | Not published | See pricing |
What Nabla has that we do not
A randomised controlled trial. UCLA assigned 238 physicians across 14 specialties to DAX Copilot, to Nabla, or to usual care. Nabla won. DAX showed no statistically significant change. No other vendor in this category holds evidence of that grade, and we hold nothing comparable.
And the privacy architecture. Audio, transcript and note stay in the browser and never reach Nabla servers, which removes the retention question rather than answering it. We store your encounter. If that is your line, this comparison is over and Nabla wins it.
What the architecture costs
A product that never stores your encounter cannot open a briefing before your next patient sits down, because it has nothing to open. The same choice that makes the privacy position possible is what caps the scope.
The trade is real engineering rather than oversight, and which side you want depends on whether your problem is the note or the day around it.
What the trial also found
Nine and a half percent is about 41 seconds a note. And neither arm reduced time in the record outside scheduled hours at all. The trial that proves Nabla works also marks the edge of what a microphone in a room reaches.
The half nobody compares
Nabla covers the consultation. It does not answer your phone, book, take a deposit, check eligibility or backfill a cancellation.
By design it cannot. A product holding nothing after the encounter has nothing to answer the Saturday phone call with. Roughly 13 to 19 percent of appointments are missed at about $196 each and the backfill window closes when your practice does.
The number this comparison misses
The randomised 41 seconds is real and it is not where your money goes. From 2026 your E/M level turns on Medical Decision Making, so the note is the evidence for the code and the code is the money.55From 2026, Medical Decision Making is the primary basis for E/M level selection. AAPC reports up to 19 percent of E/M visits undercoded at roughly $37 each. Reported Medicare Advantage downcoding runs $42 to $74 per visit and $28,000 to $74,000 per family physician per year. Up to 19 percent of E/M visits are undercoded at roughly $37 each, and Medicare Advantage downcoding takes $42 to $74 off a visit and a reported $28,000 to $74,000 a physician a year, without ever appearing as a denial.
Nabla proved a scribe can save measurable time. No trial has yet tested whether a scribe can defend a code, and someone should run that one.
Price
Nabla does not publish. Third-party estimates run $119 to $239 a month and may be wrong. We publish on one page.
Which one
Choose Nabla if
- You want the only ambient scribe with randomised evidence behind it.
- You will not let a vendor store your encounters, at any price.
- The note is the whole problem and the rest of your day is handled.
Choose WA\ if
- Your evening is letters, codes, results and callbacks rather than notes.
- You want the briefing assembled from the chart before the patient sits down.
- You want the front desk and the consultation on one record.
What we are not claiming
We have no randomised evidence and Nabla does. That fact outranks every row in the table above and we are not going to arrange the page so it looks otherwise. Forty-one seconds measured under randomisation is worth more than any claim we can currently make.
Frequently asked questions
Should I buy Nabla or WA\?
They are built for different jobs, so the comparison only works once you decide what you are buying. At drafting a note, Nabla is excellent, and it has the only randomised result in this category to prove it. The result itself is worth having. Nabla cut note-writing time by 9.5 percent, about 41 seconds, and did not reduce after-hours time in the record at all. The best scribe ever tested moved the note and left the evening alone, and a scribe stops at that ceiling. WA\ is not a scribe. It is the briefing before the patient sits down, the note, the letters, the coding, the cited answers, the front desk that answers at 9pm and the patient record underneath, at one published price a published price. If you want a faster note, Nabla is a fine buy. If you want a shorter day, a faster note has been measured and it does not get you one.
What did the Nabla trial actually find?
At UCLA, 238 physicians across 14 specialties were randomly assigned to Microsoft DAX Copilot, Nabla or usual care for two months. Nabla users cut time spent writing each note by 9.5 percent against control, about 41 seconds. DAX showed no statistically significant change. Neither reduced time in the record outside scheduled hours. Both improved physician wellbeing scores. It is one trial at one academic centre over two months, and the authors say the findings need confirmation in larger multicentre trials. Read it the way a buyer should. The category was measured, and the measurement says the note was never where your time was going.
How much does Nabla cost?
Nabla does not publish list pricing. Independent reviews converge on roughly $119 per clinician per month at entry and roughly $239 at the higher tier, and buying generally involves a sales conversation. Confirm any figure directly with Nabla. WA\ Clinician is published at a published price with a 14 day free trial and no minimum term, and the letters, the coding, the cited evidence answers and the pre-consult briefing are included on every plan rather than gated to a tier above. At the higher tier the two are within a few dollars of each other, and the difference is what the money reaches.
Go home when your last patient does.
Thirty minutes, your own workflow, running live. The briefing, the note, the letters and the codes out of one consultation.
About this article. Written and published by WA\, a competitor of Nabla, and we have said where Nabla is the better purchase. Nabla holds the only randomised win in this category and the strongest data-residency position, and we hold neither. Nabla does not publish pricing so figures quoted are third-party estimates. The randomised trial cited is independent of us, and Nabla, not WA\, holds the only randomised win in this category. Undercoding and downcoding figures are third-party RCM analysis, not our data. WA\ has no peer-reviewed clinical trials published to date and does not claim any. All names are marks belonging to their owners.