Speech generation

Qwen3-TTS VoiceDesign

Voice design from a written description, 10 languages, on Apple Silicon.

  • QwenBy
  • 10Languages

Can do

  • Voice cloningNo. NoSpeaks in a voice copied from a short reference clip.
  • Voice designYes. YesBuilds a new voice from a written description.
  • Emotion controlNo. NoTakes graded emotion from a clip, a vector or text.
  • Preset voicesNo. NoShips fixed voices; no reference clip needed.

Languages

10languages
  • Chinesezh
  • Englishen
  • Frenchfr
  • Germande
  • Italianit
  • Japaneseja
  • Koreanko
  • Portuguesept
  • Russianru
  • Spanishes

Runs on

  • MLX-Audio

    MLXApple Silicon

    Apple Silicon only.

    Engine doc

Hardware

EngineCUDAROCmIntel ArcApple SiliconVulkanNPUCPU
MLX-AudioNot supportedNot supportedNot supportedSupportedNot supportedNot supportedNot supported

Supported Needs a build Experimental

Licence

Terms
Not stated in the app's docs. Check the model card before commercial use.

VoiceStudio is AGPL-3.0 and doesn't relicense model weights. Licence guide

Related

From the VoiceStudio app at 0834c8b. 27 models listed.

Quick answers