luxtts
LuxTTS is a lightweight text-to-speech model for cloning a voice from reference audio and generating clear 48 kHz speech. Use it locally through Python, Colab, or Hugging Face Spaces.
Pick a small issue you can reproduce, then fix it with your AI coding agent.
Share on XLicense: Apache-2.0
Overview
LuxTTS is a lightweight, ZipVoice-based text-to-speech model for cloning a voice from reference audio and generating spoken text. It addresses the need for clear, realistic speech generation without requiring a large model or extensive GPU memory. Load it through Python on a GPU, CPU, or Apple MPS device, encode a reference audio file, then generate and save 48 kHz speech. The README also provides Colab and Hugging Face Spaces options for trying it.
Key features
- Clones a voice using reference audio, with at least 3 seconds recommended.
- Generates speech at 48 kHz.
- The README reports speeds up to 150x realtime on a single GPU and faster than realtime on CPU.
- Runs on GPU, CPU, or Apple MPS; the README says it fits within 1 GB of VRAM.
Best for
Developers who want to generate speech in Python using a reference voice, including on local hardware with limited GPU memory. Colab and Hugging Face Spaces are options for trying the model.
- Upstream
- ysharma3501/LuxTTS
- Fork on GitHub
- Guo-astro/luxtts
- Upstream stars
- 5.5k
- Category
- Documents, media and content
- Language
- Python
- License
- Apache-2.0
- Forked
- 2026-10-19
- Sync status
- In syncLast synced 2026-10-20
More in Documents, media and content
A self-hosted knowledge base for writing, organizing, searching, and sharing Markdown notes. It supports offline access and team workspaces for personal or collaborative documentation.
Forked 2026-10-19Last synced 2026-10-20License: MITDocuments, media and contentGitHub
Textus is a free, open-source Markdown editor with an AI writing assistant for drafting and editing on macOS, Windows, and Linux.
Forked 2026-10-18Last synced 2026-10-20License: MITDocuments, media and contentGitHub
Clypra is a free, open-source video editor for editing and arranging footage on a frame-accurate timeline. It uses Rust and GPU acceleration for video decoding and rendering.
Forked 2026-10-14Last synced 2026-10-20License: MITDocuments, media and contentGitHub
A self-hosted app for turning audio recordings into searchable notes. Use it to transcribe, summarize, organize, and ask questions about recordings while keeping the library on your own infrastructure.
Forked 2026-10-12Last synced 2026-10-20License: AGPL-3.0Documents, media and contentGitHub