Radar
New projects people are discovering or following across Pinokio.
Uncensored Deepfakes for images and videos without training and an easy-to-use GUI.
Welcome to Kokoro, a high-quality text-to-speech synthesis program powered by deep learning. This tool converts any text into high-fidelity speech in just a few seconds. Simply input text, select a voice, adjust the speed, and enjoy the generated audio.
A Modular AI Image Generation Web-User-Interface, with an emphasis on making powertools easily accessible, high performance, and extensibility. Supports Stable Diffusion, Flux, etc. AI image models, with plans to support AI video, audio, and more in the future.
Expressive TTS with voice cloning, prompt-driven speech synthesis built on LTX-2.3 by Resemble AI
[NVIDIA ONLY] Generate Video Progressively. FramePack is a next-frame (next-frame-section) prediction neural network structure that generates videos progressively. https://github.com/lllyasviel/FramePack
OpenAI-compatible Speech-to-Text and Text-to-Speech server. Powered by Faster-Whisper, Kokoro, and Piper.
Qwen3.8-27B on 16-32 GB Nvidia GPUs one-click install for Windows / Linux
MatAnyone AI is a tool for editing videos by separating objects from their backgrounds. It is an AI to remove the background from videos effectively. Stable Video Matting with Consistent Memory Propagation: https://github.com/pq-yang/MatAnyone.git
Local AI YouTube video generator: script, scenes, voiceover, thumbnail and MP4 export.
Remove backgrounds from videos and images with precision AI matting. Runs locally on 12GB VRAM — Windows, Linux, and macOS.

Open-source, accurate and easy-to-use video clipping tool by Alibaba ModelScope.
Generate synchronized audio from video and/or text inputs https://github.com/hkchengrex/MMAudio
Separate Maestro DEV build with Storyteller planning chat, saved multi-turn stories, and exact Storyteller-to-Director Short Film handoff. Includes the existing local AI video, image, music, Studio, and Director workflows. Requires an NVIDIA GPU (6GB+ VRAM).