Qwen/Qwen3-TTS-12Hz-0.6B-Base
Qwen3 TTS
Custom reusable voices
Languages
10
Training data
5M+ hours
License
Apache 2.0
OpenVox fit
Voice control
Model overview
Built into OpenVox for private local voice generation.
Qwen3-TTS is a multilingual, controllable, robust, and streaming TTS model family with voice cloning and description-based control.
Qwen3-TTS is multilingual, controllable, robust, and streaming, with training across over 5 million hours of speech.
The base checkpoint supports rapid voice cloning from user-provided audio input.
OpenVox uses Qwen3 TTS for voice design, custom reusable voices, and instruction-aware generation.
OpenVox does not provide celebrity voice models and does not permit cloning, impersonating, or commercially using any person's voice without proper rights or consent.
Source: Qwen/Qwen3-TTS-12Hz-0.6B-Base.