Standard & Paid Price
Standard Price
| Meter | Standard Price |
|---|---|
| Input price | $0.0740 / audio hour |
Billing details
Description
Xiaomi MiMo v2.5 ASR — speech recognition model optimized for Chinese and English plus Chinese dialects, handling noisy, far-field, and multi-speaker audio as well as lyrics transcription.
Capabilities
- Tasks
- transcription
API endpoints
POST /v1/audio/transcriptions(audio-transcription)