Alibaba Fun-ASR Flash
fun-asr-flash-2026-06-15Alibaba Cloud DashScope non-realtime speech recognition with multilingual transcription, punctuation, and sentence/word timestamps.
- Speech to text
Pricing
Includes our margin. Charged per request from your balance.
- Per minute
- $0.0041
Details
- Provider
- Alibaba
- Added
- Nov 5, 2026
Options
Parameters this model accepts.
- Languages
- auto
- zh
- en
- ja
- ko
- vi
- th
- id
- ms
- fil
- hi
- ar
- fr
- de
Show 17 moreShow fewer
- es
- pt
- ru
- it
- nl
- sv
- da
- fi
- nb
- el
- pl
- cs
- hu
- ro
- bg
- hr
- sk
- Features
- Automatic language detection, Sentence timestamps, Word-level timestamps, Context enhancement, Supports audio and video URLs
- Response formats
- json
- Input formats
- MP3, WAV, AAC, M4A, FLAC, OGG, OPUS, MP4, MOV, AVI, MPEG, WEBM, MKV
- Max file size
- 500 MB
- Max upload in the request
- 4 MB
- File URLs
- Supported