ENGLISH SUBJECT PRODUCT

AI English Oral Assessment

English oral — live speaking practice

HK-tuned AI English oral coach. Built-in TSA, DSE Paper 4 (Individual Response + Group Interaction), and secondary/university interview scenarios. Real-time dialogue with SEN-friendly adaptations. At partner schools every student talks to AI ~4×/month; weaker students average +59% score gain.

TeachersStudents
English oralTSADSE Paper 4InterviewSENP3–P6S1–S6

DSE / TSA / interview scenarios · ~4 AI convos/student/month · weaker students +59%

TSA Oral Practice
Prompt

“Tell us about your favourite hobby.”

0:000:07
Overall
4.0/ 5
Clear enunciationConfident tone
Pronunciation
4.2/5
Fluency
3.8/5
Content
4.3/5
Vocabulary
3.9/5
Add more detail
Transcript

“Hi, my favourite hobby is playing basketball every Saturday with my classmates. It helps me stay healthy and happy.”

Weaker students +59%
DSE / TSA / interview

English teacher pain · Essai solution

30-student class — teachers can’t give 1-on-1 English speaking practice to each kid.

AI as personal practice partner. At partner schools, every student talks to AI ~4 times a month.

Students are shy to speak English in front of peers — actual practice time is tiny.

Private AI dialogue + SEN mode (slower pace, repeat prompts, forgiving feedback). Weaker students +59%.

Generic AI speaking tools sound American — disconnected from HK English exam standards.

HK English scenarios natively trained — TSA / DSE Paper 4 prompts, vocabulary, and HKEAA scoring logic.

Key features

HK English natively trained

TSA, DSE Paper 4, and HK interview scenarios trained in. Not an American ESL AI with a HK accent layer.

TSA · DSE · interview scenarios

Built-in simulations: TSA read-aloud, DSE Paper 4 Group Interaction, secondary/university English interviews.

Self-intro & public speaking

Practise self-introduction, public speaking, and debate — per-dimension scoring for pronunciation, fluency, vocabulary, logic.

Real-time dialogue · SEN support

Genuine back-and-forth conversation. SEN mode: slower pace, repeat prompts, extended response windows.

School-based prompt bank

HK-curriculum English oral prompts plus teacher-uploaded school-based questions and marking criteria.

Word class report

Class weakness heatmap, improvement recs, per-dimension distribution. One-click Word export.

How it works

1

Pick the scenario

Teacher assigns a prompt or students pick — TSA / DSE simulation, self-intro, debate, or free dialogue.

2

Student talks with the AI

AI responds live in English. Pronunciation, fluency, content, vocabulary, and grammar scored in real time.

3

Instant feedback + class report

Student sees scored feedback immediately; teacher gets a class weakness heatmap and can export a Word report.

Scenario + grade coverage

 P3P4P5P6S1S2S3S4S5S6
TSA Oral
DSE Paper 4 Group Interaction
DSE Paper 4 Individual Response
Secondary / university interview
Recitation / public speaking
+59%

Average score gain for weaker students after 8+ weeks of practice · ~4 AI convos/student/month · HK English natively trained

HK primary English teacher

“Clean UI across desktop, tablet, and mobile. Content draws heavily from TSA — great pre-exam practice. Students get far more speaking reps than in class.”

— HK primary school English teacher

FAQ

What powers the English oral feature?
VAPI real-time voice + Azure Speech pronunciation analysis. Natural British/HK English dialogue, tuned for HK English scenarios.
What does SEN support include?
Slower speech rate, keyword repeat prompts, extended response windows, forgiving feedback, optional picture cues. Teachers can configure per student.
How is scoring broken down?
Per dimension: Pronunciation, Fluency, Content, Vocabulary, Grammar. Teachers can customise weights or upload the school’s own marking criteria.
Can we use our school’s own oral prompts?
Yes. Upload or type them in; AI adapts scoring and follow-up questions accordingly.
How was the "+59%" measured?
Students using Essai AI Oral 8+ weeks; pre/post in-school oral scores compared. Weaker-ability group averaged +59% gain; higher groups saw smaller gains.
Is student audio used to train AI models?
No. Audio is used only for that session’s scoring. Each school’s data is isolated; contract forbids training on school data.
Can we fund this with the EDB HK$500k programme?
Yes. Essai meets EDB Circular 221/2025. Book a strategy session to get the application template.

AI Tutor

General chat

Reply

How can I help?

Ask me anything or pick a suggestion below.