#7676th of 81 in VoiceFor voice, speech and music
luxtts
Text-to-speech model with voice cloning and 48 kHz output
- Stars
- 5.6k
- License
- Apache-2.0
- Last commit
- Jun 2026
- Language
- Python
3,645 on 21 Apr 20265,554 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
LuxTTS is a ZipVoice-based text-to-speech model that clones a voice from a short reference clip (wav or mp3, at least 3 seconds recommended). It is distilled to 4 sampling steps and uses a custom 48 kHz vocoder instead of the default 24 kHz one. It runs from Python on CUDA, CPU or Apple MPS, and the README claims 150x realtime on a single GPU.
Who it is for: Developers needing fast local voice cloning TTS from Python
Strengths
- Outputs 48 kHz audio rather than the usual 24 kHz
- README says it fits in 1 GB VRAM and runs faster than realtime on CPU
- Supports CUDA, CPU and Apple MPS devices
- Tunable sampling parameters: num_steps, t_shift, speed, return_smooth, ref_duration
Weaknesses
- Python library only; web UIs and ComfyUI nodes are community projects
- Runs in float32; float16 inference code is still on the roadmap
- Needs a 3+ second reference clip; artifacts may require tuning
- No tagged releases; speed and quality claims are not benchmarked in the README
What it needs
- GPU optional
- Needs Python, Hugging Face model YatharthS/LuxTTS, librosa, soundfile
- Models: LuxTTS (ZipVoice-based, 4-step distilled), 48 kHz vocoder
Quick answers
Is luxtts open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Does luxtts need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Voice
See all 81| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 98 out of 100 |
| 2 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 91 out of 100 |
| 3 | whisper.cppC/C++ speech-to-text engine running OpenAI Whisper models locally | 90 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 83 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 83 out of 100 |