← Speech-to-Text 
Batch lane
Alibaba
Qwen-Audio-3.1-ASR-Flash
Vendor-direct DashScope batch, Singapore / FLEURS n=50 + EdAcc n=82 / 2026-09-24
Build voice agents on Speko →Qwen-Audio-3.1-ASR-Flash is measured here for comparison — it is not one of the models Speko routes.
WER · batch
2.0%
Measured 2026-09-24. The Nova-3 anchor re-scored at its published 11.96% the same day.
WER · streaming
—
Batch-only endpoint
Finalize
—
Batch-only endpoint
Time to first token
—
Batch-only endpoint
Cost / min
$0.00024
Billed tokens at $0.15/M input and $0.47/M output, Singapore.
Share this result
Embed the live badge
Markdown
[](https://benchmarks.speko.ai/stt/alibaba-qwen-audio-3-1-asr-flash)
HTML
<a href="https://benchmarks.speko.ai/stt/alibaba-qwen-audio-3-1-asr-flash"><img src="https://benchmarks.speko.ai/badge/stt/alibaba-qwen-audio-3-1-asr-flash.svg" alt="Speko stt rank"></a>
URL
https://benchmarks.speko.ai/stt/alibaba-qwen-audio-3-1-asr-flash