Alibaba Cloud · Speech to text
Qwen Audio 3.1 ASR Filetrans
Long-audio transcription across languages and Chinese dialects
ASRFile transcription
Pricing
Charged by actual usage
Unit: points / 1M tokens
Pricing
- Input
- 104≈ $0.208Member price 62.4≈ $0.125
- Output
- 351≈ $0.702Member price 211≈ $0.421
| Input | Output | |
|---|---|---|
| List price | 104≈ $0.208 | 351≈ $0.702 |
| Member price (40% off) | 62.4≈ $0.125 | 211≈ $0.421 |
- Paid members are charged the member price, 40% below the list price.
- Input and output are billed separately by actual tokens; reasoning tokens count as output.
Lifetime and Team members get 40% off this model. See plans
About this model
Qwen Audio 3.1 ASR Flash Filetrans is an offline model for long recordings, multiple languages, and Chinese dialects. It supports contextual recognition, hotwords, speaker diarization, punctuation, and text normalization for meetings and content production.
Use in Beav
- 01Download Beav and sign in
- 02Choose Qwen Audio 3.1 ASR Filetrans in the model picker
- 03Use it for turning audio and video into text and subtitles
