This model is an quantized gguf-format export of
Qwen/Qwen3-TTS-12Hz-0.6B-Base
for ease of use in edge devices and CPU-based inference environments.
The original model is transformed into gguf with F16 tensors by the script
convert_hf_to_gguf.py
and then further quantized, if needed, using the tool
quantize from the same repo.
1from py_qwen3_tts_cpp.model import Qwen3TTSModel
2
3# Initialize the model (it handles downloading from this repo)
4model = Qwen3TTSModel(
5 tts_model="qwen3-tts-0.6b-q4-k-m",
6 n_threads=4
7)
8
9# Synthesize from text
10result = model.synthesize("Hello, world!", language="en")
11model.save_audio(result, "output.wav")
The license is derived from the original model: Apache 2.0. For more details, please refer to
Qwen/Qwen3-TTS-12Hz-0.6B-Base.
