Qwen3 TTS 12Hz 0.6B Base

ProviderQwen
Categorytext-to-speech
Licenseapache-2.0
Downloads78.9K
Stars33

Overview

Qwen3 TTS 12Hz 0.6B Base is a lightweight, open-weights text-to-speech model designed for low-latency audio synthesis. With a compact 0.6B parameter footprint, it is optimized for edge deployment and real-time applications where memory overhead is a constraint. Unlike massive proprietary TTS engines, this base model provides a flexible foundation for fine-tuning on specific voice datasets or integrating into local pipelines via Apache-2.0 licensing. Developers can leverage it for lightweight voice assistants, accessibility tools, or as a component in a larger multimodal agent. Its architecture focuses on balancing synthesis quality with inference speed, making it a viable alternative for those moving away from heavy cloud-based APIs toward self-hosted, efficient audio generation.

Highlights

  • Compact 0.6B parameter size for efficient edge deployment
  • Apache-2.0 license allows flexible commercial integration
  • Optimized for low-latency, real-time audio synthesis
  • Ideal base for custom voice fine-tuning projects

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("Qwen/Qwen3-TTS-12Hz-0.6B-Base")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-TTS-12Hz-0.6B-Base")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download Qwen/Qwen3-TTS-12Hz-0.6B-Base

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download Qwen/Qwen3-TTS-12Hz-0.6B-Base config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('Qwen/Qwen3-TTS-12Hz-0.6B-Base')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/Qwen/Qwen3-TTS-12Hz-0.6B-Base

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('Qwen/Qwen3-TTS-12Hz-0.6B-Base')
tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen3-TTS-12Hz-0.6B-Base')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance 
pip install modelscope

CLI Download

Download the full repository

Download the full repository 
modelscope download --model Qwen/Qwen3-TTS-12Hz-0.6B-Base

Download a single file to a local folder (e.g. README.md into ./dir)

Download a single file to a local folder (e.g. README.md into ./dir) 
modelscope download --model Qwen/Qwen3-TTS-12Hz-0.6B-Base README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('Qwen/Qwen3-TTS-12Hz-0.6B-Base')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://www.modelscope.cn/Qwen/Qwen3-TTS-12Hz-0.6B-Base.git

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/Qwen/Qwen3-TTS-12Hz-0.6B-Base.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

Install the ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

Load the model and run inference 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'Qwen/Qwen3-TTS-12Hz-0.6B-Base')

Full Documentation

来源: HuggingFace

---
license: apache-2.0
pipeline_tag: text-to-speech
language:

  • zh

  • en

  • ja

  • ko

  • de

  • fr

  • ru

  • pt

  • es

  • it

tags:
  • audio

  • tts

  • voice-clone

---

Qwen3-TTS-12Hz-0.6B-Base

Qwen3-TTS Technical Report | GitHub Repository | Hugging Face Demo

Qwen3-TTS is a family of advanced multilingual, controllable, robust, and streaming text-to-speech models. Trained on over 5 million hours of speech data spanning 10 languages, Qwen3-TTS supports state-of-the-art 3-second voice cloning and description-based control.

This specific checkpoint is the 0.6B Base model, which is capable of rapid voice cloning from a user-provided audio input.

Quickstart

Installation

bash
pip install -U qwen-tts

Optional: for optimized performance

pip install -U flash-attn --no-build-isolation

Sample Usage (Voice Clone)

To clone a voice and synthesize new content using the Base model, you can use the following code snippet:

python
import torch
import soundfile as sf
from qwen_tts import Qwen3TTSModel

Load the model

model = Qwen3TTSModel.from_pretrained(
    "Qwen/Qwen3-TTS-12Hz-0.6B-Base",
    device_map="cuda:0",
    dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
)

Reference audio for cloning

ref_audio = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/clone.wav"
ref_text  = "Okay. Yeah. I resent you. I love you. I respect you. But you know what? You blew it! And thanks to you."

Generate speech

wavs, sr = model.generate_voice_clone(
    text="I am solving the equation: x = [-b ± √(b²-4ac)] / 2a? Nobody can — it's a disaster (◍•͈⌔•͈◍), very sad!",
    language="English",
    ref_audio=ref_audio,
    ref_text=ref_text,
)

Save the resulting audio

sf.write("output_voice_clone.wav", wavs[0], sr)

Overview

Introduction

<p align="center">
<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/qwen3_tts_introduction.png" width="90%"/>
<p>

Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles to meet global application needs. Key features:

  • Powerful Speech Representation: Powered by the self-developed Qwen3-TTS-Tokenizer-12Hz, it achieves efficient acoustic compression and high-dimensional semantic modeling.
  • Universal End-to-End Architecture: Utilizing a discrete multi-codebook LM architecture, it realizes full-information end-to-end speech modeling.
  • Extreme Low-Latency Streaming Generation: End-to-end synthesis latency as low as 97ms, meeting the rigorous demands of real-time interactive scenarios.
  • Intelligent Text Understanding and Voice Control: Supports speech generation driven by natural language instructions, allowing for flexible control over multi-dimensional acoustic attributes.

Model Architecture

<p align="center">
<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/overview.png" width="80%"/>
<p>

Citation

If you find this work useful, please consider citing the technical report:

BibTeX
@article{Qwen3-TTS,
  title={Qwen3-TTS Technical Report},
  author={Hangrui Hu and Xinfa Zhu and Ting He and Dake Guo and Bin Zhang and Xiong Wang and Zhifang Guo and Ziyue Jiang and Hongkun Hao and Zishan Guo and Xinyu Zhang and Pei Zhang and Baosong Yang and Jin Xu and Jingren Zhou and Junyang Lin},
  journal={arXiv preprint arXiv:2601.15621},
  year={2026}
}
View official source
Join our Telegram