Skip to main content
Speech Recognition

qwen-audio-3.1-asr-flash-streaming

Qwen-Audio-3.1-ASR-Flash-Streaming is an end-to-end real-time speech recognition model designed for scenarios such as real-time conferencing, live subtitles, and intelligent interaction. It features low latency and high accuracy in streaming speech transcription. The model supports multilingual and multi-regional Chinese dialect recognition, seamless switching between Chinese and English, hot word and context enhancement, punctuation prediction, and text normalization. It also exhibits strong noise robustness and can adapt to complex acoustic environments. Furthermore, this version supports controllable ASR/AST output for multiple dialects.

Inference Service Provider

The inference service provider for qwen-audio-3.1-asr-flash-streaming is Alibaba Cloud Model Studio.

Model Capabilities

CapabilitySupportCapabilitySupport
Input ModalityAudioOutput ModalityText
Model ExperienceUnsupportedFunction CallingUnsupported
Structured OutputsUnsupportedWeb SearchUnsupported
Prefix CompletionUnsupportedContext CachingUnsupported
Batch InferenceUnsupportedFine-tuningUnsupported

Context Limits

ParameterValueParameterValue
Max Input Length8192 TokenMax Output Length1024 Token
Context Window8192 Token

Pricing

This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
  • China (Beijing)
  • Singapore
Billing ItemPrice (USD)Unit
Input0.848Per million tokens
Output0.636Per million tokens

Rate Limits

  • China (Beijing)
  • Singapore
ParameterValue
RPM (requests per minute)600

API usage

Token Plan
Model Playground
  • Audio generation
  • Music generation
Statistics and Monitoring