models

Manage TTS model downloads and installations.

Subcommands

models list

List all installed models.

qwen-tts models list

Shows each installed model variant along with its size on disk. Models are stored in the models directory (~/.qwen-tts/models/ by default).

models download

Download a model from Hugging Face.

qwen-tts models download [--variant <VARIANT>]
OptionDescription
--variant <VARIANT>Model variant to download: pro or lite. Defaults to pro.

Example:

# Download the full-precision model
qwen-tts models download --variant pro

# Download the smaller quantized model
qwen-tts models download --variant lite

Model Variants

VariantBackendHugging Face RepositoryNotes
proMLXmlx-community/Qwen3-TTS-bf16Full bf16 precision. Best quality on Apple Silicon.
liteMLXmlx-community/Qwen3-TTS-4bit4-bit quantized. Lower memory usage, slightly reduced quality.
proCUDA / CPUQwen/Qwen3-TTSOfficial PyTorch checkpoint.
liteCUDA / CPUQwen/Qwen3-TTSSame checkpoint (quantization handled at runtime).

The download command uses the huggingface_hub Python library to fetch model files. The appropriate repository is selected automatically based on your configured backend.

Storage

Downloaded models are saved to ~/.qwen-tts/models/<variant>/. You can change the models directory with:

qwen-tts config set models_dir /path/to/models