Qwen Releases a Compact Custom-Voice TTS Model

Alibaba's Qwen team has released a new open-source model for text-to-speech, Qwen3-TTS-12Hz-0.6B-CustomVoice. This compact model, with just 600 million parameters, introduces a powerful feature to the open-source audio landscape: custom voice cloning.

With this capability, developers can use a short audio sample to create a digital version of a specific voice. The model can then use this cloned voice to synthesize new speech from text in multiple languages, opening up possibilities for personalized applications, custom voice assistants, and dynamic content creation.

A More Accessible Approach

The model's relatively small size makes it more accessible for researchers and developers to run and fine-tune compared to larger, proprietary systems. The "12Hz" in its name likely points to its internal audio representation, suggesting a design that balances quality with computational efficiency, making it suitable for a wider range of hardware.

This release provides a significant new tool for the open-source AI community. While high-quality TTS models exist, those with built-in, easy-to-use voice cloning are less common. The model is available for download on Hugging Face under the Qwen license, which developers should review for commercial use terms.