AI-powered multi-voice audiobook generator — LLM script annotation, voice cloning, voice design, LoRA training, per-line style control, and export to MP3, chaptered M4B, or Audacity multi-track. Built on Qwen3-TTS.

Industry leading face manipulation platform

Clean, polished interface for Tencent’s SongGeneration. Create songs from text prompts or reference audio, with batch processing and smart model selection. Minimum Requirement: 10GB of VRAM

TTS-Story is a web-based multi‑voice TTS studio for turning tagged scripts into audiobooks—featuring full speaker management, chunk review/regeneration, a job queue and library system, and local GPU or API backends including Kokoro, Chatterbox, VOX CPM, Pocket-TTS, Kitten-TTS, IndexTTS-2, QWEN3 TTS and Omnivoice engines

MFLUX-WEBUI using MLX and the FLUX DEV and Schnell models

A Pinokio application to manage ComfyUI environments with Docker.

One-click launcher for Audiocraft MusicGen + AudioGen Gradio Web UI

Creative Image Enhancer/Upscaler. Powered By Refiners. 8GB VRAM | 10GB Install

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

Local generative video panel for Apple Silicon. Wraps LTX-2 MLX, joint audio+video, one-click Pinokio install.

Voice-powered AI assistant platform — connect any LLM, any TTS, with a live web canvas, music generation, and agent orchestration using openclaw. Install: npx openvoiceui setup

KittenTTS is an ultra-lightweight, CPU-friendly text-to-speech model with 15M params for real-time, high-quality voices. Open source, fast start. 😺

Team Tonic Super AGI Autonomous Agents Hackathon GitHub Repository.

A 1-click launcher for https://github.com/comfyanonymous/ComfyUI

deep hermes, but decides how to respond based on its OWN decision, no need for system prompts.

Qwen3-TTS, Apple MLX, WebUI, API Server

Local, GPU-accelerated music video generator: upload a track, analyze it, align lyrics, generate stylized backgrounds, composite reactive shaders and kinetic type, and encode with ffmpeg (NVENC on NVIDIA GPUs by default). Examples (progress log, newest = current state): [voidcat on YouTube](https://www.youtube.com/@voidcatalog)