Qwen3 TTS 12Hz 1.7B VoiceDesign

提供商Qwen
分类text-to-speech
许可证apache-2.0
下载量312.0K
星标86

简介

Qwen3 TTS 12Hz 1.7B VoiceDesign 是阿里通义千问团队推出的一款轻量化语音合成模型。它打破了传统 TTS 机械感强的局限，重点优化了音色的自然度与情感表达。1.7B 的参数规模在保证高质量输出的同时，极大降低了端侧部署的门槛，非常适合需要低延迟实时交互的场景。对于开发者而言，它不仅能高效完成文本转语音，更在音色定制化方面表现出色，是构建 AI 助手或虚拟数字人时，替代昂贵商业 API 的一个高性能开源选择。

核心亮点

  • 极低延迟，支持端侧实时语音合成
  • 音色自然，具备强情感表达能力
  • 1.7B 轻量规模，部署成本低且高效
  • Apache-2.0 协议，商业应用灵活便捷

使用方法

安装依赖
# 安装 Hugging Face transformers
pip install transformers torch
SDK 使用
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign")

Hugging Face 下载

我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 huggingface_hub：

操作指引 
pip install -U huggingface_hub

命令行下载

下载完整模型库

下载完整模型库 
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例）

下载单个文件到指定本地文件夹（以下载 config.json 到当前路径下 ./dir 目录为例） 
huggingface-cli download Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign config.json --local-dir ./dir

更多命令行下载选项，可参见官方文档

SDK 下载

SDK 下载 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign

模型文件托管在 Hugging Face Hub，使用 HF CLI / SDK / Git 直接下载，不经过本站。

PyTorch / Transformers 使用

安装 Transformers

安装 Transformers 
pip install -U transformers torch

模型加载和推理

模型加载和推理 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign')
tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign')

模型下载

我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。

操作指引：在下载前，请先通过如下命令安装 ModelScope：

操作指引 
pip install modelscope

命令行下载

下载完整模型库

下载完整模型库 
modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例）

下载单个文件到指定本地文件夹（以下载 README.md 到当前路径下 dir 目录为例） 
modelscope download --model Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign README.md --local_dir ./dir

更多更丰富的命令行下载选项，可参见具体文档

SDK 下载

SDK 下载 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign')

Git 下载

请确保 lfs 已经被正确安装

Git 下载 
git lfs install
git clone https://www.modelscope.cn/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign.git

如果您希望跳过 lfs 大文件下载，可以使用如下命令

跳过 LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign.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 快速开发

下载并安装 ModelScope library

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

模型加载和推理

模型加载和推理 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign')

完整文档

来源: HuggingFace

---
license: apache-2.0
pipeline_tag: text-to-speech
library_name: qwen-tts
tags:

  • audio

  • tts

  • qwen

  • multilingual

---

Qwen3-TTS

<br>

<p align="center">
<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-TTS-Repo/qwen3_tts_logo.png" width="400"/>
<p>

<p align="center">
&nbsp&nbsp🤗 <a href="https://huggingface.co/collections/Qwen/qwen3-tts">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp🤖 <a href="https://modelscope.cn/collections/Qwen/Qwen3-TTS">ModelScope</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://qwen.ai/blog?id=qwen3tts-0115">Blog</a>&nbsp&nbsp | &nbsp&nbsp📑 <a href="https://huggingface.co/papers/2601.15621">Paper</a>&nbsp&nbsp | &nbsp&nbsp💻 <a href="https://github.com/QwenLM/Qwen3-TTS">GitHub</a>
</p>

We release Qwen3-TTS, a series of powerful speech generation models developed by Qwen, offering comprehensive support for voice cloning, voice design, ultra-high-quality human-like speech generation, and natural language-based voice control.

Overview

Qwen3-TTS covers 10 major languages (Chinese, English, Japanese, Korean, German, French, Russian, Portuguese, Spanish, and Italian) as well as multiple dialectal voice profiles. 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 to bypass traditional information bottlenecks.
  • Extreme Low-Latency Streaming Generation: Supports streaming generation with end-to-end synthesis latency as low as 97ms.
  • Intelligent Voice Control: Supports speech generation driven by natural language instructions for flexible control over timbre, emotion, and prosody.

Quickstart

Environment Setup

Install the qwen-tts Python package from PyPI:

bash
pip install -U qwen-tts

Python Package Usage

python
import torch
import soundfile as sf
from qwen_tts import Qwen3TTSModel

Load the model

model = Qwen3TTSModel.from_pretrained(
    "Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice",
    device_map="cuda:0",
    dtype=torch.bfloat16,
    attn_implementation="flash_attention_2",
)

Custom Voice Generation

wavs, sr = model.generate_custom_voice(
    text="其实我真的有发现，我是一个特别善于观察别人情绪的人。",
    language="Chinese",
    speaker="Vivian",
    instruct="用特别愤怒的语气说",
)
sf.write("output.wav", wavs[0], sr)

Evaluation

Zero-shot speech generation on the Seed-TTS test set (Word Error Rate (WER, ↓)):

| Model | test-zh | test-en |
|---|---|---|
| Qwen3-TTS-12Hz-1.7B-Base | 0.77 | 1.24 |

Citation

If you find our paper and code useful in your research, please consider giving a star ⭐ and citation 📝:

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}
}
查看官方来源