Qwen3-TTS-GGUF provides GGUF quantized weights for the Qwen3-TTS family, including base, customvoice, and voicedesign variants at 0.6B and 1.7B scales. It enables efficient local text-to-speech inference on consumer hardware using tools like llama.cpp or Hugging Face. Designed for developers integrating open voice synthesis into applications without relying on proprietary cloud APIs.
In the Voice, TTS & speech space, Qwen3 TTS takes a focused approach. It focuses on running high-quality open text-to-speech models locally without cloud dependency. Qwen3 TTS is an open-source project aimed at developers. The project is open source (MIT). Qwen3 TTS is available on the web and the command line, and it can be self-hosted.
Serveurperso builds and maintains Qwen3 TTS, and the product first shipped in 2026. The project is developed in the open on GitHub with 87 stars and 115 commits in the last 90 days. PulseGate's similarity index places it among 6 comparable tools. Among its 4 catalogued features are GGUF Quantization, text-to-Speech, and Voice Design.
Latest indexed changes and source events
Serveurperso/Qwen3-TTS-GGUF verified by the PulseGate indexer
Other apps tracked under the same category.
