QW

Qwen3-ASR

Audio modelQwen3

Qwen3-ASR

Release date: 2026-01-29Updated: 2026-01-29 23:00:45923
Parameters
800M
Context length
128K
Chinese support
Supported
Reasoning ability

Qwen3-ASR is an AI model published by 阿里巴巴, released on 2026-01-29, for Audio model, with 800M parameters, and 128K context length, requiring about 16GB storage, under the Apache 2.0 license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Qwen3-ASR

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
8K tokens
Model type
Audio model
Modality (in / out)
Text, Audio → Text
Release date
2026-01-29
Model file size
16GB
MoE architecture
No
Total params / Active params
800M / N/A
Knowledge cutoff
No data
Qwen3-ASR

Open source & experience

Qwen3-ASR

Official resources

DataLearnerAI blog
No blog post yet
Qwen3-ASR

API details

API speed
3/5
No public API pricing yet.
Qwen3-ASR

Benchmark Results

No benchmark data to show.

Compare with other models

No curated comparisons for this model yet.

Want a custom combination? Open the compare tool

Qwen3-ASR

Publisher

Qwen3-ASR

Model Overview

Qwen3-ASR is an AI model published by 阿里巴巴, released on 2026-01-29, for Audio model, with 800M parameters, and 128K context length, requiring about 16GB storage, under the Apache 2.0 license.

DataLearner on WeChat

Follow DataLearner on WeChat for AI model updates and research notes.

DataLearner WeChat QR code