arrow_back Back to models
mic Voice

MiMo v2.5 ASR

Bilingual Chinese-English ASR with automatic code-switching, no language tags needed

Automatically detects and transcribes mixed-language speech without language tags. Handles major Chinese dialects — Wu, Cantonese, Hokkien, Sichuan — plus lyrics, classical poetry, and technical terms, and stays robust under noise, far-field capture, and multiple speakers.

verified

Single price — no hidden costs

Input
Audio → text
Context
8K tokens
Max output
2K tokens
Languages
Chinese-English code-switching + major Chinese dialects
Price
$0.074 / audio hour
30-day uptime
99.9%
Time to first response
~600ms
Throughput
Up to 100 requests/min

Measured by meshcode across our own infrastructure — redundancy means uptime holds even if one upstream has issues.

Quality

Accuracy
Noise robustness
Speed

Good fit for

Automated meeting notes Multilingual subtitles and captions Call center transcription Noisy field-recording transcription

FAQ

Which company built this model? expand_more

Xiaomi's MiMo team develops and operates this model directly. meshcode contracts API access and passes calls straight through.

Are there any hidden costs? expand_more

No. The input/output prices shown here are the whole story — no subscription fee, no minimum commitment. You're only charged for what you use, deducted from your wallet balance.