Assess Mandarin speech with the linguistic detail tonal languages require. Chivox exposes tone, syllable and fluency evidence so applications can explain errors clearly and coach the next attempt.
A generic speech score can hide the difference between a segment error and a tone error. The response keeps those signals available for better diagnosis.
Use the structured result to highlight the precise syllable, compare the expected contour and prompt a focused second attempt.
English and Mandarin responses follow a consistent product integration model, while preserving the language-specific fields each assessment needs.
A beginner orders coffee in a role-play. Most syllables are clear, but 买 (mǎi) is produced with a falling contour. Instead of returning “74/100,” the tutor can preserve the successful sentence and focus the retry on the meaning-bearing tone.
“我想买一杯咖啡。” — I’d like to buy a cup of coffee.
A low, dipping third tone in this phrase.
The initial and final are clear; the contour is the mismatch.
Keep the word in a short phrase so the tone remains conversational.
“Your sentence was clear. On 买, let your voice dip low before 一杯: mǎi yì bēi. Listen once, then order the coffee again.”
Implementation note. Tone evidence can be combined with your own vocabulary, translation and HSK lesson logic; it does not force a single teaching method.
Each syllable carries the expected and detected tone plus a sandhi-aware verdict — so 你好 spoken as (T2, T3) is marked normal, not mispronounced. This is the evidence your tutor explains from.
{
"overall": 78,
"pron": 74,
"fluency": { "overall": 81, "speed": 72 },
"details": [
{
"char": "你",
"score": 85,
"tone_ref": "T3",
"tone_detected": "T2",
"dp_type": "normal"
},
{
"char": "好",
"score": 72,
"tone_ref": "T3",
"tone_detected": "T3",
"dp_type": "normal"
}
]
}Preserve tone and Pinyin evidence through the assessment, then turn the most important mismatch into a focused second attempt.
In Mandarin, tone can change meaning. Keeping tone evidence separate from general pronunciation makes the correction more precise and useful.
Yes. A shared integration can route each activity to the appropriate assessment while keeping the rest of the agent workflow consistent.
Keep the reference text, detected tone and returned verdict together, then apply the result in context. For example, the surface tone in 你好 should not be explained as if each character were spoken in isolation.
Tell us what you’re building. We’ll reply within one business day with pilot credits, pricing, or a deployment plan — whichever you need first.