# ysharma3501/LuxTTS

A high-quality rapid TTS voice cloning model that reaches speeds of 150x realtime.

Repository: https://github.com/ysharma3501/LuxTTS
Canonical: https://ross.abutalabs.com/products/luxtts
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-06-05T21:24:15+00:00

## Health v2 (maintenance only)
Score: 54/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 86, release rhythm 35, longevity 15
- inputs: {"age_days": 222, "days_push": 89, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5306, forks 675 (observed 2026-08-28T04:09:15.388518+00:00)

## What it is
LuxTTS is a lightweight zipvoice-based text-to-speech model for high-quality zero-shot voice cloning, generating clear 48kHz speech at up to 150x realtime speed. It fits within 1GB of VRAM and runs on GPU, CPU, and Apple MPS.

## Use cases
- clone a voice from a short reference audio clip
- generate realistic speech from text locally
- run fast text-to-speech on a low-VRAM GPU or CPU
- produce high-quality 48khz speech audio
- build a TTS feature into a Python app
- try voice cloning in a notebook without setup

## When to choose
- you need fast, high-quality voice cloning with a small footprint
- you want 48kHz output rather than typical 24kHz TTS models
- you need realtime or faster-than-realtime synthesis on modest hardware
- you want a simple Python API with GPU, CPU, and MPS support

## When to avoid
- you need fine-grained control over prosody or phoneme-level editing
- you require multi-speaker training or fine-tuning pipelines
- you need a production hosted TTS service with scaling out of the box
- you need languages beyond those the model supports

## Facets
- artifact type: library
- maturity: active
- function: tts, machine-learning, llm-inference
- domain: speech-processing, artificial-intelligence
- platform: python, cross-platform, cli
- tags: voice-cloning, text-to-speech, zipvoice, lightweight, realtime-inference, 48khz-audio, audio, gpu

## Member repositories
- ysharma3501/LuxTTS (main) score 54

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:15.388518+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:59:00.192054+00:00, confidence not recorded.
  - readme: https://github.com/ysharma3501/LuxTTS (fetched 2026-08-28T04:09:15.388518+00:00, sha 86b360c09615)
- Data as of 2026-08-30T08:39:29.467469+00:00.