Qwen3-TTS Demo

A unified Text-to-Speech demo featuring three powerful modes:

• Voice Design: Create custom voices using natural language descriptions
• Voice Clone (Base): Clone any voice from a reference audio
• TTS (CustomVoice): Generate speech with predefined speakers and optional style instructions

Built with Qwen3-TTS by Alibaba Qwen Team.

Note: This demo uses HuggingFace Spaces Zero GPU. Each generation has a time limit. For longer texts, please split them into smaller segments.