QW

Qwen3-TTS 0.6B

Audio modelQwen3

Qwen3-TTS-12Hz-0.6B-Base

Release date: 2026-01-15Updated: 2026-01-22 22:19:30483
Parameters
600M
Context length
4K
Chinese support
Supported
Reasoning ability

Qwen3-TTS-12Hz-0.6B-Base is an AI model published by 阿里巴巴, released on 2026-01-15, for Audio model, with 600M parameters, and 4K context length, requiring about 1.2GB 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-TTS 0.6B

Model basics

Reasoning traces
Not supported
Thinking modes
Thinking modes not supported
Context length
4K tokens
Max output length
2K tokens
Model type
Audio model
Modality (in / out)
Text → Audio
Release date
2026-01-15
Model file size
1.2GB
MoE architecture
No
Total params / Active params
600M / N/A
Knowledge cutoff
No data
Qwen3-TTS 0.6B

Open source & experience

Qwen3-TTS 0.6B

Official resources

Paper
No paper available
DataLearnerAI blog
No blog post yet
Qwen3-TTS 0.6B

API details

API speed
5/5
No public API pricing yet.
Qwen3-TTS 0.6B

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-TTS 0.6B

Publisher

Qwen3-TTS-12Hz-0.6B-Base

Model Overview

Qwen3-TTS-12Hz-0.6B-Base is an AI model published by 阿里巴巴, released on 2026-01-15, for Audio model, with 600M parameters, and 4K context length, requiring about 1.2GB 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