Standard & Paid Price
Standard Price
| Meter | Standard Price |
|---|---|
| Input price | $0.1260 / audio hour |
Billing details
Description
Alibaba Qwen-Audio-3.0-ASR-Flash — non-realtime speech recognition on the Qwen-Audio 3.0 foundation, covering 30 languages and the seven major Chinese dialect groups (Mandarin, Wu, Xiang, Gan, Hakka, Min, Yue) plus 20+ regional accents. Punctuation prediction and text normalisation turn numbers, dates, and amounts into standard form; hot words and prompt context raise accuracy on domain vocabulary. Accepts audio up to 5 minutes or 2 GB per request.
Capabilities
- Tasks
- transcription
API endpoints
POST /v1/audio/transcriptions(audio-transcription)