Assess 13 English and 4 Japanese task types with the real API

[01]LIVE DEMO

Pick a task type and record.

Choose a language and assessment type, check the prompt and record. Results arrive in seconds, down to individual phonemes.

LANGUAGE

Assessment type

Basic
PROMPT

Kana

Demo records up to 15s

Selected kana

あ

a

Script
Your audio is sent for assessment.

This demo is for evaluating the features. Your recording is sent to DolphinSOE for assessment. Please do not say anything personal or confidential.

[02]TASK TYPES

17 task types for every use case.

From pronunciation basics to Q&A, retelling and free-talk speaking tests. Every type can be tried in the demo.

Japanese4

Basic

English13

Basic
Advanced
[03]REPORT

One recording, one full report.

Everything comes back as JSON, ready for your learning app's screens and score history.

  • 01

    Overall score

    overall

    0–100 rating of overall pronunciation; bands show proficiency.

  • 02

    Accuracy

    accuracy

    How close each sound is to the reference; flags misread or unclear sounds.

  • 03

    Fluency

    fluency.overall

    Few breaks and restarts; how naturally words connect.

  • 04

    Completeness

    integrity

    How much of the text was read; reflects missing and extra words.

  • 05

    Prosody

    rhythm

    English stress, intonation and phrasing, scored per sentence.

  • 06

    Phonemes & morae

    phonemes[]

    Score per phoneme; Japanese also returns the reading (katakana) and pitch.

  • 07

    Pauses & speed

    fluency.pause · speed · wpm

    Number of pauses, speaking speed (slow / normal / fast) and WPM.

  • 08

    Misreadings & judgement

    type · hitAnswer · index

    Missing, inserted, substituted and repeated words; choice correctness and which sentence was read.

[04]HOW IT WORKS

Token, stream, result: three steps.

  1. TOKEN

    Get a token on your server

    Sign with your AppID and Secret to issue a token. The Secret never reaches the browser.

  2. STREAM

    Send audio over WebSocket

    Stream 16 kHz, 16-bit PCM while recording. The task type and reference text go in the start message.

  3. RESULT

    Receive the assessment as JSON

    As soon as recording stops, the overall score, metrics, phonemes and misreadings come back.

[—]GET STARTED

Bring this assessment to your service.

Complete the form to request a free API key, which will be sent by email.

Get a free API key

Complete the form to request a free API key, which will be sent by email.

Open the request form in a new window