Real-time AI patient
A 5-minute role-play with a live-audio AI patient. They listen for pauses, ask clarifying questions, and stay in character. No scripted branches, no canned replies — every conversation is shaped by what you say.
OET Live scores every OET Speaking criterion, surfaces the exact words you fluffed, and tells you which cues you missed — automatically, in under a minute. And it now marks your OET Writing letters on all six official criteria too.
A 5-minute role-play with a live-audio AI patient. They listen for pauses, ask clarifying questions, and stay in character. No scripted branches, no canned replies — every conversation is shaped by what you say.
Every role-play is scored on the four linguistic criteria (intelligibility, fluency, appropriateness, resources of grammar and expression) and the five clinical communication criteria (relationship building, understanding the patient perspective, providing structure, information gathering, information giving). Plus a 0–500 overall and band letter.
Industry-grade pronunciation analysis scores every syllable for accuracy, completeness, and fluency. We surface the specific words you mispronounced, ranked by how much they would hurt an examiner — so you drill what matters.
Every OET role-card has 4–5 tasks. We verify each one against your transcript — hit, partial, miss — with the exact quote you used as evidence. No more guessing whether you covered all the cues.
A weighted recommender targets your two weakest criteria, suggests topics you haven't tried, and adjusts difficulty as your scores climb. Hit Recommended and you get a case engineered to move your weakest band.
Write a referral letter against a profession-specific case — timed under exam conditions or untimed with hints and model answers — then get it scored on all six official OET Writing criteria, with inline annotations on the phrases that cost you marks and band-5 + band-7 sample answers to compare against.
OET Speaking examiners grade against four linguistic criteria and five clinical-communication criteria. We mirror the public rubric and give you both the band and the why.
How easy you are to understand at the sound and stress level.
Speed, rhythm, hesitations, fillers.
Vocabulary, register, hedging — does it fit a real consultation?
Range and accuracy across complex structures.
Greeting, rapport, empathy, closing.
Eliciting concerns, ideas, expectations.
Signposting, transitions, agenda-setting.
Open + closed questions, screening, summarising.
Chunks, checks, jargon control.
The OET Writing sub-test is graded on six official criteria — one scored 0–3, five scored 0–7. We mark each one against the public rubric, annotate the phrases that earned or cost marks, and give you band-5 and band-7 model answers for the same task. There is no word-count penalty: length is judged only through relevance and summarising.
Is it clear in the first sentence why the letter was sent — and is the right reader addressed?
The clinical facts the reader needs, accurate and relevant — no omissions, no errors.
Relevance and summarising quality. Length is never penalised on its own.
Reads like a clinical letter to this recipient — register, salutation, sign-off.
Logical flow, sensible paragraphing, and a letter structure the reader can follow.
Grammar, vocabulary, spelling, punctuation, and cohesion.
Join the waitlist and we'll email you the moment your build is ready. Free during early access.