Super fast Multilingual TTS supporting 54 voices across 8 languages.
Radar
New projects people are discovering or following across Pinokio.
Text-to-Speech model. Download, explore files and run it on Hugging Face.
Feature Extraction model with 8B parameters. Download, explore files and run it on Hugging Face.
11 Claude skills for day trading: scan thousands of charts, track breaking news, time every entry and exit, and replay every outcome before you risk a dollar.
Claude AI skill for cinematic Higgsfield AI prompts — 32 sub-skills covering Seedance 2.5 (omni-reference, video edit + extend) and 2.0, the Hell Grind feature-film pipeline, an acting system, Cinema Studio 2.5/3.0/3.5, MCSLA, Soul ID consistency, Kling 3.0 Motion Control, the DISCIPLINE framework, and 18 templates.
Forge for stable-diffusion-webui-amdgpu (formerly stable-diffusion-webui-directml)
An all-in-one, 100% local AI video, image & music studio. Its Director mode turns a single prompt into a full music video or short film — LLM-planned, shot by shot. Built on the WanGP pipeline (Wan 2.1/2.2, LTX-2.3, Qwen, Hunyuan Video, Flux). Requires an NVIDIA GPU (6GB+ VRAM).
Download from YouTube or upload any track and effortlessly split it into four separate stems — vocals, drums, bass, and other — with StemXtract. Create clean instrumentals, isolate individual stems, mix custom combinations, or craft unique mashups by blending tracks. Features smart tempo/beat matching, simple effects, and easy mixing controls.
A multi-voice AI audiobook generator built on Qwen3-TTS — annotate scripts with an LLM, assign unique voices to each character, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, train custom voices with LoRA fine-tuning, and export to MP3 or Audacity multi-track projects
Drop images, auto-caption with local Qwen3-VL, edit all fields, publish Works & Projects to tera-sat.com.
Local-first AI video generation desktop app — prompt to finished video on your own GPU
Pixel-Aligned 3D Generation from Images (SIGGRAPH 2026). Generate high-fidelity 3D GLB assets with PBR textures from a single image, powered by the TRELLIS.2 backbone. Native Windows install using prebuilt CUDA wheels (Python 3.12 / torch 2.8 / CUDA 12.8).
