TAAFT
Free mode
100% free
Freemium
Free Trial
Deals
Companies
ysharma3501
Models
LuxTTS

LuxTTS

By ysharma3501
LuxTTS is a lightweight text to speech and voice cloning model distilled from ZipVoice. It produces clear 48 kHz audio with state of the art cloning quality while running up to 150x real time on a single GPU and even real time on CPUs. The model is designed to fit in small VRAM budgets, making local deployment practical, and exposes simple APIs for cloning and generation.
New Audio Gen 4
Released: February 2, 2026

Overview

ZipVoice-based voice cloning TTS that generates 48 kHz speech at up to 150x real time, fitting in about 1 GB VRAM for local, high quality synthesis

About ysharma3501

View Company Profile

Tools using LuxTTS

No tools found for this model yet.

Related Models

  • Gen 4
    Qwen3 TTS VD Flash
    Qwen3-TTS-VD-Flash is Alibaba Qwen's voice-design TTS model that creates fully custom voices from natural-language instructions, letting users control timbre, rhythm, emotion and persona for expressive, multilingual speech via the Qwen API.
    NewAudio
    Released 1mo ago
  • Gen 4
    WaveNet
    WaveNet is a neural, sample-level generative model for raw audio. It uses dilated causal convolutions to predict the next sample distribution, yielding highly natural speech and expressive prosody, although generation is expensive without acceleration.
    Audio
    Released 9y ago
  • Gen 4
    VoxCPM 1.5
    VoxCPM1.5 is OpenBMB’s tokenizer-free TTS model that generates expressive, context-aware speech and realistic zero-shot voice clones in Chinese and English, with real-time streaming and open-source weights that support full and LoRA fine-tuning.
    NewAudio
    Released 2mo ago
Last updated: February 5, 2026
0 AIs selected
Clear selection
#
Name
Task