What Is an AI Medical Scribe? How It Works in 2026

An AI medical scribe is software that listens to a clinical visit and writes the note for you. It transcribes the conversation, pulls out the clinically relevant parts, and drafts structured documentation, usually a SOAP note, that you review and sign. No keyboard during the visit, no chart waiting for you at 9pm.

That's the short answer. The longer answer is worth ten minutes, because the products sold under this label differ in ways that matter clinically: what they do with your audio, which languages they understand, what they draft beyond the note, and what "review" actually means when you're 14 patients deep on a Tuesday.

Key takeaways

• An AI scribe converts visit audio into a draft note. You stay the author; it does the typing.
• Primary-care physicians log a median of 36.2 minutes of EHR time per 30-minute visit. The note now outlasts the appointment it describes.
• Published US pricing runs roughly $39–$199 per clinician per month. India-native pricing starts around ₹1,499.
• The two questions that separate vendors fastest: what happens to the audio, and what happens in languages other than English.

How does an AI medical scribe actually work?

Four steps, all of them during or right after the visit.

It listens. You start a session on your phone or laptop, get the patient's consent, and see the patient like normal. The scribe captures the conversation ambiently. Nobody dictates anything.

It transcribes. Speech becomes text. The good systems handle two speakers, interruptions, and the way real consultations loop back on themselves. The genuinely hard version of this problem is a noisy OPD where the patient switches between Hindi and English mid-sentence. More on that below.

It structures. A language model turns the transcript into clinical documentation: subjective, objective, assessment, plan. This is the step where products diverge. Some stop at the note. Others draft the downstream artifacts too. AI Scribe by Patient Square also returns ICD-10 suggestions and a prescription draft with the SOAP note.

You review and sign. The draft appears about two minutes after the visit ends. You read it, fix what needs fixing, and sign. Nothing enters the record without you.

The honest framing: this is a very fast, very patient junior scribe with perfect recall of the last conversation, not a colleague. It drafts. You decide.

What does an AI scribe hand back after the visit?

Baseline, every credible product: a structured note. Beyond that, read the feature list carefully, because the word "scribe" covers a wide range.

AI Scribe by Patient Square is an ambient AI medical scribe that listens during the visit and hands back a structured SOAP note, ICD-10 suggestions, and a prescription draft, ready to review and sign about two minutes after the visit. The prescription draft also passes through a deterministic safety screener that checks for drug interactions, renal dosing, and pregnancy flags. It re-runs at sign time and hard-blocks unsafe combinations unless you explicitly override with an attestation. We built that because a draft an LLM wrote is still a draft an LLM wrote, and the safety layer shouldn't be probabilistic.

Things some vendors include that we currently don't: after-visit patient summaries, referral letters, per-specialty note templates, and direct EHR write-back. If those are must-haves for your workflow today, weigh that honestly. Our pricing page lists exactly what ships now.

AI scribe vs human scribe vs dictation: what's the difference?

Dictation was the first wave: it moved typing to talking, but you still spent evenings narrating visits you'd already done once. Human scribes solve the time problem and create a staffing one. Ambient AI is the first version where the documentation happens while the medicine happens.

What happens to the visit audio?

Ask this before you ask about price. Seriously.

A visit recording is among the most sensitive artifacts in healthcare. It's more revealing than the note, because it contains everything that didn't make the note. Vendors handle it very differently. Some retain audio for days or weeks for model improvement or dispute resolution. Some let you opt out. Some are vague.

Our position: visit audio is processed in memory and discarded the moment the note is drafted. There is no audio archive, not for us, not for the practice, not for anyone. What survives is the note you reviewed and signed. Notes are encrypted in transit (TLS 1.2+) and at rest (AES-256), they belong to your practice, and you can export or delete any visit at any time. The full posture is on our security page.

In the US, the floor for any vendor is a signed BAA. In India, the DPDP Act 2023 sets the frame: consent-first, purpose-limited handling with reasonable security safeguards. Wherever you practice, a vendor who can't answer "where does the audio live and for how long" in one sentence has answered the question.

How much does an AI medical scribe cost in 2026?

From published pricing pages (fetched June 2026):

• US self-serve band: Freed runs $39–$119 per month across its tiers depending on billing; Commure Scribe lists $59–$89; Twofold $49–$69; Sunoh lists $149 promotional ($199 regular). Several large vendors (Suki, DeepScribe, Nabla) publish no pricing at all and route you to sales.
• India: EkaScribe Pro, the published India-native anchor, is ₹1,499 per doctor per month. US products bought from India effectively cost ₹6,000–12,500 per month at current exchange rates, which is several times the established Indian clinic-software budget.
• Us: AI Scribe by Patient Square launches at $89/clinician/month in the US and ₹1,199/clinician/month in India (ex-GST) on annual billing. Month-to-month and committed-annual rates are on the pricing page, with no feature gating between tiers. Every plan starts with a 7-day free trial.

One opinion, stated as one: we think pricing pages that say "talk to sales" for a per-clinician software subscription tell you something about how the renewal conversation will go. Transparent list pricing keeps vendors honest, including us.

Does the subscription pay for itself? The arithmetic is short. Primary-care physicians in a 2023 JAMA Network Open study logged a median of 36.2 minutes of EHR time per 30-minute visit, and an earlier time-motion study in Annals of Internal Medicine found nearly two hours of EHR and desk work for every hour of direct patient care, plus another one to two hours of after-hours "pajama time" most nights. Recovering even a fraction of that against a $89 or ₹1,199 monthly line item isn't a close call. Still, run the numbers for your own visit volume, not ours.

Where do AI scribes still fall short?

Anyone selling you perfection is selling. The failure modes worth knowing:

Noisy, multi-speaker rooms. A quiet US consult room is the easy case. A crowded OPD with a relative answering half the questions is the real test, and transcription quality varies sharply across products there.

Language. Several popular US scribes publish language lists that don't name Hindi or any Indian language. That's a gap for one of the largest bodies of clinical conversation on earth. We built India-first: English, Hindi, and 20+ Indian languages, code-mixing included, with notes always returned in clinical English. In low-connectivity clinics, capture works offline with on-device encryption and syncs later.

Drafts contain errors. Models mishear drug names, compress two complaints into one, occasionally write something plausible that didn't happen. This is why the review-and-sign step is load-bearing, why our Rx drafts pass a deterministic safety screen, and why you should distrust any vendor whose pitch implies you can skip reading the note.

The chart is yours, legally. No scribe, silicon or human, moves the documentation responsibility off the signing clinician. In India, where the average primary-care consultation runs about two minutes and medical-council conduct rules expect records to be maintained for years and produced when a patient or court asks, a tool that writes a complete record at consultation pace is the difference between having a defensible chart and having a queue. In the US, it's the difference between signing at 6pm and signing in bed.

Five questions to ask before you sign with any vendor

1. "What happens to the visit audio, and when is it deleted?" Accept only a one-sentence answer with a timeline. Ours: processed in memory, discarded at note draft.
2. "Will you sign a BAA?" (US), or, in India: "How do you map to DPDP consent and purpose limitation?" Vague answers here are disqualifying.
3. "What exactly is in the draft: note only, or codes and prescriptions too? What checks them?" Make the demo show a wrong drug pairing and watch what happens.
4. "What does my actual patient mix sound like to your model?" Test with your accents, your languages, your interruptions, during a free trial, on day one, not after procurement.
5. "What's the price after year one?" Launch rates, annual commitments, and month-to-month rates differ. Get the whole ladder in writing. Ours is published.

A scribe that survives those five questions will probably survive your Tuesday clinic. Take the 7-day trial, run it on real visits, and read every draft closely for the first week. That's the evaluation that matters, and it costs you nothing but the week.