Back to GitHub trending

QwenLM/Qwen3-TTS

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.

Python13K stars1.7K forks
View on GitHubShare on X

What it does

Qwen3-TTS is an advanced open-source text-to-speech model series by Alibaba Cloud, enabling high-quality, expressive speech generation and voice cloning. It supports multiple languages and offers extensive features for developers and users alike.

Star history

2026-08-23 → 2026-09-12+292 stars

Tracking

Last trending
2026-02-21

Creator kit

Hook

Transform your projects with lifelike speech generation using Qwen3-TTS—where technology meets creativity!

Content angles

  • Create a tutorial on how to implement Qwen3-TTS for custom voice applications.
  • Explore the differences between traditional TTS and Qwen3-TTS's advanced features.
  • Showcase a comparison of voice quality and expressiveness between Qwen3-TTS and other TTS models.

Who should care

Developers, content creators, and researchers interested in AI-driven speech technologies.