Store

🗣️ PersonaPlex - NVIDIA's real-time speech-to-speech conversational AI model. Natural full-duplex conversations with customizable personas and voices. Requires powerful NVIDIA GPU (16-24GB VRAM), 32GB RAM, and Hugging Face account.

Multi-Voice Text-to-Speech for Stories and Audiobooks. Supports Kokoro and Chatterbox TTS engines with GPU acceleration.

One-click installer for Microsoft TRELLIS.2: High-quality 3D asset generation from images with PBR textures.

Super Optimized Gradio UI for AI video creation for GPU poor machines (6GB+ VRAM). Supports Wan 2.1/2.2, Qwen, Hunyuan Video, LTX Video and Flux. https://github.com/deepbeepmeep/Wan2GP

The AI that actually does things https://www.molt.bot

Z-Image, Flux2 Klein, & SeedVR2 with a Gradio UI. Uses a built-in ComfyUI backend for speed and efficiency! [8GB+VRAM, 16GB+ RAM]

Distill and quantize models using TorchAO with intelligent GPU/CPU management

AI Song Generation with Full Style Control - Generate complete songs with lyrics, vocals, and instrumental tracks using Tencent AI Lab's SongGeneration (LeVo) model. [NVIDIA ONLY]

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team

Video Matting with complete cross-platform support for Windows, macOS, and Linux

Self-hosted Whisper API for Open WebUI

Fast, high-quality image generation using comfyui via a Gradio UI

AI Song Generation on Mac Apple Silicon, with Full Style Control - Generate complete songs with lyrics, vocals, and instrumental tracks using Tencent AI Lab's SongGeneration (LeVo) model.

One-click 3D Gaussian Splatting generation from a single image.

Gradio-based web interface for the LuxTTS voice cloning and text-to-speech model, enabling users to generate customized speech from text using uploaded or recorded audio references with adjustable parameters like speed, guidance scale, and inference steps.

Local AI Workstation

Qwen3-TTS is an open-source series of TTS models developed by the Qwen team