A patient who actually responds
A live 5-minute role-play with an AI patient that listens, pauses, and replies to what you actually said — no scripts, no canned answers, no awkward turn-taking.
Live role-plays, instant scoring on all 9 OET communication criteria, and a bank of 11,000+ medically-verified scenarios across 12 healthcare professions — plus an AI marker that scores every OET Writing letter against the official six-criterion rubric.
Every role-play graded against the official OET rubric, plus a 0–500 overall.
Profession-specific schemas, audited by a leading reasoning model against a 9-criteria rubric.
Live-audio AI — listens, pauses, and responds in real time.
Referral letters scored on all 6 official Writing criteria, with inline annotations.
Real-time AI conversation, objective pronunciation scoring, 9-criteria Speaking feedback, and full OET Writing letter marking — all grounded in the official OET rubric, for the 12 professions that use OET for registration.
A live 5-minute role-play with an AI patient that listens, pauses, and replies to what you actually said — no scripts, no canned answers, no awkward turn-taking.
Intelligibility, fluency, appropriateness, grammar, vocabulary, empathy, patient perspective, clinical accuracy, organisation — plus a 0–500 overall and band letter. The full official rubric, automated.
Industry-grade pronunciation analysis scores every syllable. We surface the exact words that tripped you up so you drill the right things — not your whole accent.
Every role-card has 4–5 tasks. We verify each one against your transcript — hit, partial, miss — with the exact quote from your role-play as evidence.
A weighted recommender targets your two weakest criteria, suggests topics you haven't tried, and adjusts difficulty as your scores climb. No grinding through the same case twice.
OET Writing is here too. Write a referral letter against a profession-specific case, then get it scored on all six official criteria — purpose, content, conciseness, genre, organisation, language — with inline annotations on the exact phrases that cost you marks.
Your recordings, transcripts, and scores stay on infrastructure we control. Export everything in one tap; delete your account and your data is gone — no soft-delete, no archive.
The Speaking flow below ends in a full score breakdown in about 30 seconds. OET Writing follows the same pick → practise → scored loop — a timed letter under exam conditions, marked on the six official Writing criteria.
Browse by topic, filter by criterion, or hit Recommended and let the algorithm pick the case that targets the most weak spots today.
A 5-minute role-play with an AI patient who responds to what you actually say. Your role-card lists the tasks; the patient stays in character.
Within about 30 seconds, you see your full OET score, every criterion, cue hit/miss per task, mispronounced word list, and the next case to practice.
Every Speaking case is generated against a profession-specific topic schema, audited against a 9-criteria rubric, and tagged with the criteria it strengthens — and every profession gets OET Writing referral tasks marked on the official six-criterion letter rubric.
We'll email you the moment the app is in TestFlight. No spam, no marketing blasts — just one notification when you can start practicing.