Simon Willison 1/22/2026

Qwen3-TTS Family is Now Open Sourced: Voice Design, Clone, and Generation

Read Original

The article announces the open-source release of the Qwen3-TTS family of text-to-speech models. These models support multilingual, controllable, and robust speech generation, including 3-second voice cloning and description-based voice design. Trained on over 5 million hours of speech data, they are available under Apache 2.0 license, with demos accessible via Hugging Face.

Qwen3-TTS Family is Now Open Sourced: Voice Design, Clone, and Generation

Comments

No comments yet

Be the first to share your thoughts!

Browser Extension

Get instant access to AllDevBlogs from your browser

Top of the Week