Alibaba Qwen: Qwen3 ASR Flash

Coming soonQuick Start

Qwen3 ASR Flash is Alibaba Qwen's automatic speech recognition model, released 2026-05, built on the Qwen3-Omni foundation and trained on tens of millions of hours of multimodal speech data. It transcribes 11 languages with automatic language detection, including Cantonese, Sichuanese, Minnan, and Wu dialects, and handles difficult acoustic conditions such as background music, noise, and far-field recordings. The model can bias recognition toward specific vocabulary using arbitrary context text, making it suitable for domain-specific transcription.

This model is not routed on MirAPI yet — prices shown are the official list prices. Create an account to get notified when it goes live.

Modalities
inAudiooutText
Price / 1M
$35.00 /
Context
Knowledge cutoff

Capabilities

Structured output

Quick Start

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mirapi.ai/v1",   # changed
    api_key=os.environ["MIRAPI_API_KEY"],   # changed
)

resp = client.chat.completions.create(
    model="qwen/qwen3-asr-flash-2026-02-10",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire Qwen3 ASR Flash into your product

1M free tokens to start · no card · OpenAI-compatible, one base_url change

Start free