/demo/mcp · MCP walkthrough
A one-minute tour of what your LLM actually gets.
Hit Play — no recording required. Watch the MCP payload, the LLM diagnosis, and the targeted drill your agent can generate — all from the same response. Mandarin is first: it's the moat most developers underestimate.
locale: zh-CN·ready to play·waiting for play
Scenario 01 · tonal hard-mode
The learner tries to order dumplings.
They say “shuǐ jiǎo” (水饺, dumplings). A generic STT mishears it as “shuì jiào” (睡觉, to sleep) — same syllables, different tones, completely different meaning. Watch what MCP actually hears.
reference_text
我想吃水饺
“I want to eat dumplings.”
01ready
Record learner audio
Capture · then submit to Chivox MCP
Watch the 60-second tour
No mic · 4 steps · hover the control bar to pause
02
Evaluation result
Phonetic matrix · ~40 fields
Waiting for the previous step
03
LLM diagnosis
Your model reads the matrix
Waiting for the previous step
04
Auto-generated drill
Agent plans next-session practice
Waiting for the previous step
Ready to wire it up?
Same payload. Your agent. Your production loop.
Drop Chivox MCP into Cursor, Claude Desktop, or any agent SDK. One npxand you're reading the same JSON you just saw above.