Qwen3 ASR 0.6B
qwen/qwen3-asr-0.6bQwen3 ASR 0.6B is the smaller open-weight speech recognition model from Qwen. Transcribes 30 languages and 22 Chinese dialects with automatic language detection. Language hints may be ignored. Accepts MP3, WAV, FLAC, and OGG recordings up to 10 minutes, with direct uploads up to 4 MB or audio URLs up to 25 MB. Returns a completed JSON transcript without timestamps, speaker labels, or translation. Billed per started input second.
- Speech to text
Pricing
Includes our margin. Charged per request from your balance.
- Per minute
- $0.00022
- Per second
- $0.0000037
- Rounding
- Ceil
- Billing increment seconds
- 1 s
Details
- Provider
- Qwen
- Context
- 4.1K tokens
- Added
- Nov 22, 2026
Options
Parameters this model accepts.
- Languages
- auto
- zh
- en
- yue
- ar
- de
- fr
- es
- pt
- id
- it
- ko
- ru
- th
Show 17 moreShow fewer
- vi
- ja
- tr
- hi
- ms
- nl
- sv
- da
- fi
- pl
- cs
- fil
- fa
- el
- hu
- mk
- ro
- Features
- 30 languages and 22 Chinese dialects, Automatic language detection, JSON transcription, Billed per started second
- Response formats
- json
- Input formats
- MP3, WAV, FLAC, OGG
- Max file size
- 25 MB
- Max upload in the request
- 4 MB
- File URLs
- Supported