Store

Tokenizer-free multilingual TTS and voice cloning with low-VRAM and VoxCPM2 Web UI/API launch modes.

[MAC ONLY] Local generative video panel for Apple Silicon. Joint audio+video via LTX 2.3 (MLX). T2V, I2V, FFLF, Extend. Lossless h264. LoRA picker + CivitAI browser. Free, open source.

Strip image metadata locally in the browser.

Automatically discover local Codex sessions and browse them with Euphony.

[NVIDIA] Pinokio launcher for the released WorldMirror 2.0 reconstruction app from HY-World 2.0. Uses a cu128 PyTorch baseline with gsplat from PyPI/JIT. https://github.com/Tencent-Hunyuan/HY-World-2.0

Describe any song in plain English, compose it locally with an embedded Qwen GGUF model, and generate it with ACE-Step v1.5.

Self-hosted, open-source video and audio downloader with a clean web UI. Supports YouTube, TikTok, Instagram, X, and 1000+ other sites via yt-dlp.

Generate novel views from a single image with an auto-downloading OVIE web UI.

Run a minimal IOC sweep for the March 30-31, 2026 axios npm compromise.

A full Hermes skin manager for browsing, editing, saving, and activating CLI skins directly from Pinokio.

Self-improving CLI agent by Nous Research with local memory, skills, and messaging workflows.

Organize the Pinokio home screen with nested categories, drag-and-drop folders, per-category sorting, grid/list views, and reversible installation.

Run and train AI models with a unified local interface. https://github.com/unslothai/unsloth

Local-first voice synthesis studio powered by Qwen3-TTS.

Professional-grade browser-based video editor with multi-track editing, keyframe animations, real-time preview, and high-quality exports. No uploads — everything runs locally.

High-quality text-to-speech with Beautiful Web UI & API, optimized for Apple Silicon using MLX. Features include Custom Voice (preset speakers), Voice Design (natural language), and Voice Cloning. With enhanced features for saving custom voices and long-form / endless TTS streaming.

Browser-based 3D avatar head and mouth controller with keyboard and gamepad support. https://github.com/promptpirate-x/discord-id-bypass-tool

Unified AI VFX pipeline with CPE prompt engineering, storyboard canvas, and multi-node orchestrator. https://github.com/NickPittas/DirectorsConsole

State-of-the-art 1B OCR model (83.2% on OlmOCR-Bench). Local version of the HuggingFace demo. Created by Claude Code, orchestrated by TheAwakenOne.

World Model - Image to Video (4-bit Quantized, ~20GB VRAM)