Model Marketplace

Qwen-Audio-ASR-Flash-Streaming

Copy success!
Add to Compare

Overview

qwen-audio-3.0-asr-flash-streaming is a flagship speech recognition model developed by Tongyi Labs specifically for low-latency, high-concurrency real-time interactive scenarios. It not only achieves an extremely smooth "speak and hear" experience but also deeply integrates context (enhanced context) capabilities. Furthermore, it has undergone in-depth reinforcement training for specialized industry vocabulary, making it the top choice for building applications such as real-time conference interpretation, intelligent customer service agent assistance, and voice assistants.

Input

Audio

Output

Text

Features

Prefix Completion

Enable Partial Mode when calling the Qwen API to make the model continue strictly from your provided prefix text.View docs

Function Calling

Use function calling to connect large language models with external tools and systems.View docs

Cache

Context Cache stores shared prefixes for long-context requests to reduce repeated computation, improve latency, and lower cost.View docs

Structured Outputs

Structured Outputs help ensure the model returns a JSON string in the expected format.View docs

Batches

Asynchronously process requests in batches to reduce costs.View docs

Web Search

Enable web search so the model can answer with real-time retrieved data.View docs

Fine-tuning

Train models on sample data to better adapt them to specific tasks.View docs

Pricing

  • Audio Duration
    $0.00009Per second

Rate Limits

  • RPMRequests Per Minute
    1K

API Reference

Call API
Copy success!
123456789101112131415161718192021222324252627
from http import HTTPStatus
import dashscope
from dashscope.audio.asr import Recognition
import os


dashscope.api_key = os.environ.get('DASHSCOPE_API_KEY')
dashscope.base_websocket_api_url='wss://dashscope-intl.aliyuncs.com/api-ws/v1/inference'

recognition = Recognition(model='qwen-audio-3.0-asr-flash-streaming',
                          format='wav',
                          sample_rate=16000,
                          callback=None)
result = recognition.call('{YOUR_AUDIO_FILE}')
if result.status_code == HTTPStatus.OK:
    print('Recognition result: ')
    print(result.get_sentence())
else:
    print('Error: ', result.message)
    
print(
    '[Metric] requestId: {}, first package delay ms: {}, last package delay ms: {}'
    .format(
        recognition.get_last_request_id(),
        recognition.get_first_package_delay(),
        recognition.get_last_package_delay(),
    ))