One conversation.A scored breakdown that tells you what to fix.
No essays. No multi-week feedback loops. Just a live role-play, then a fast and detailed report so you know exactly which sub-skill is dragging your band down.
iPhone · iOS 16 or later. Android is not out yet.
Not on an iPhone? The app is iOS-only for now — but you can hear a full role-play with an AI patient, scored turn by turn, without installing anything.
Listen to a scored role-playNot installing today? Leave your email — 60 free practice minutes (≈ 12 role-plays) go on the account you create, whenever you create it.
Pick. Practice. See your weak spots.
- 01
Pick a case
Browse by topic, filter by criterion, or hit Recommended. The picker biases toward your two weakest bands and topics you haven't touched.
- 02
Practice live
A 5-minute role-play with an AI patient who replies to what you actually said. Your role-card lists the tasks; the patient stays in character throughout.
- 03
Get scored
About a minute after you finish, the full report lands: 0–500 overall, all 9 criteria, cue hit/miss per task, mispronounced word list, and the case you should practice next.
A five-stage scoring pipeline.
Each session runs through five stages — transcription, pronunciation, cue verification, criteria evaluation, and recommender. Each stage is independently testable, which lets us measure agreement against examiner calibration sets and improve over time.
- 01 · 01
Speech-to-text
High-accuracy speech transcription splits the conversation into candidate vs roleplayer turns. Word-level timing is preserved for downstream scoring.
- 02 · 02
Pronunciation assessment
A specialised pronunciation engine scores every syllable in your candidate turns. We aggregate to per-word accuracy and rank the words that hurt you most.
- 03 · 03
Cue verification
For each task on the role-card, an LLM verifier searches the transcript for evidence the cue was addressed. Returns hit / partial / miss + the quote.
- 04 · 04
9-criteria evaluation
A purpose-built rubric prompt scores each of the 9 OET criteria 1–5 with examiner-style reasoning. We aggregate to a 0–500 overall and an A–E grade — OET calls the overall a grade and the per-criterion marks bands, and so do we.
- 05 · 05
Next case selected
A weighted recommender picks your next case to target your weakest two criteria + an under-practiced topic. Repeat until the bands move.
Run one yourself. Your first exam session is free.
Pick a case, talk it through, and read the scoring about a minute later — all nine OET communication criteria, quoted against what you actually said.
On Android, Windows or a Mac? The app is iPhone-only for now — but you can hear a full role-play, scored turn by turn, right here.
Listen to a scored role-playiPhone · iOS 16 or later. Android is not out yet.
Not installing today?Want the 60 minutes waiting when you do get an iPhone? Leave your email — 60 free practice minutes (≈ 12 role-plays) go on the account you create.