qwen-audio-3.1-asr-flash

No monitoring data
Audio
Speech recognition
Multilingual
Dialects

Standard & Paid Price

Standard Price
MeterStandard Price
Input price$0.1500 / 1M tokens
Completion price$0.4700 / 1M tokens
Audio input price$0.1500 / 1M tokens
Billing details
Vendor list price comparison

Description

Alibaba Qwen-Audio-3.1-ASR-Flash transcribes short audio into text across multiple languages and Chinese dialects. The synchronous transcription endpoint returns a text transcript. Billing uses supplier-reported audio input tokens and text output tokens, rather than audio duration.

Capabilities

Input modalities
audio
Output modalities
text
Tasks
transcription

API endpoints

  • POST /v1/audio/transcriptions (audio-transcription)