# Qwen Unveils Open Model for Custom Voice Synthesis

> The new 1.7-billion-parameter text-to-speech model from Alibaba's Qwen team can generate novel voices from short audio prompts.

Published by The Open Weights on Jan 21, 2026. Canonical: https://theopenweights.com/news/qwen3-tts-12hz-1-7b-voicedesign-jyno

## Key facts

- Company: Qwen · Alibaba
- Model: Qwen3-TTS-12Hz-1.7B-VoiceDesign
- Version: Qwen3-TTS
- Category: Text → Speech
- Modalities: Text → Speech
- License: Apache 2.0 (Open weights, commercial use allowed)
- Parameters: 1.7B
- Architecture: Qwen3TTSForConditionalGeneration
- Precision: BF16
- Weights size: 3.8 GB
- Languages: 10 languages
- Significance: notable
- Published: 2026-01-21
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign
- Canonical URL: https://theopenweights.com/news/qwen3-tts-12hz-1-7b-voicedesign-jyno

Alibaba's Qwen team has expanded its open-source offerings with Qwen3-TTS, a new model dedicated to high-quality speech synthesis. Released under a permissive Apache 2.0 license, this 1.7-billion-parameter system marks a significant entry into the growing field of open text-to-speech (TTS) models.

The model's standout feature is its "Voice Design" capability. Unlike traditional TTS systems that rely on a fixed set of pre-recorded voices, Qwen3-TTS can generate speech in a novel voice by analyzing a short audio prompt. This allows developers to create unique voices or clone existing ones for custom applications, a feature previously common in proprietary, API-driven systems.

## Multilingual and Prompt-Driven

Qwen3-TTS is designed to be multilingual and is controlled through a combination of text and audio inputs. A user provides the text to be spoken along with a reference audio clip, and the model generates speech that matches the voice characteristics of the reference. The "12Hz" in the model's name likely refers to the sampling rate of its internal audio representation, a technique used in modern neural audio codecs to efficiently model speech.

The release of a powerful, commercially-permissive voice design model like [Qwen3-TTS](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign) is a notable development for the open-source AI community. It provides a foundational tool for a wide range of applications, including personalized digital assistants, dynamic video game character dialogue, and accessibility tools, without the restrictions of closed platforms.

## Get the model

- [Hugging Face](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign)

## Sources

- [Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign](https://huggingface.co/Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign) — Hugging Face, Jan 21, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Qwen Unveils Open Model for Custom Voice Synthesis", The Open Weights, Jan 21, 2026, https://theopenweights.com/news/qwen3-tts-12hz-1-7b-voicedesign-jyno