# LuxTTS
LuxTTS is a lightweight [[Text-to-Speech (TTS)]] model designed for high-quality [[Voice Cloning]] at extreme speed. Built on the zipvoice architecture. Licensed under Apache 2.0.
## Key features
- 150x real-time speed on a single GPU, faster than real-time on CPUs
- Voice cloning quality on par with models 10x larger
- 48kHz output (most TTS models are limited to 24kHz)
- Fits within 1GB VRAM, compatible with any local GPU
- Lightweight and efficient
## References
- Source code: https://github.com/ysharma3501/LuxTTS
- HuggingFace model: https://huggingface.co/YatharthS/LuxTTS
- HuggingFace demo: https://huggingface.co/spaces/YatharthS/LuxTTS
## Related
- [[Text-to-Speech (TTS)]]
- [[Voice Cloning]]
- [[Voice Clone Studio]]
- [[Qwen3-TTS]]
- [[VibeVoice]]