Radar
New projects people are discovering or following across Pinokio.
Private local AI meeting assistant: record conversations, transcribe speech, identify speakers, search meeting history, and create structured notes without uploading recordings by default.
ThonburianTTS, a finetuned Thai TTS based on the E2-TTS and F5-TTS architectures, designed to improve pronunciation accuracy, alignment robustness, and zero-shot speaker adaptation for the Thai language
[NVIDIA Only] Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation https://github.com/fudan-generative-vision/hallo
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
Upload the picture of an image, and generate images with that image style. Instant generation with no LoRA required https://huggingface.co/spaces/InstantX/InstantStyle
High Court filing desk. Automates case intake, hearings, and cause lists on top of the existing Excel backend without changing it.
Titan Dynamics tastefully modified Mission Planner Ground Control Station for ArduPilot (c# .net)

ScraperAI is an open-source, AI-powered tool designed to simplify web scraping for users of all skill levels.
# SillyTavern Character Generator A pinokio script for https://github.com/Tremontaine/character-card-generator When used with KoboldCPP use http://localhost:5001/v1 Where 5001 is the port reported by KoboldCPP when starting Text API Key needs to be filled with anything. (If left empty will give a error so just add anything to it)
mimetic-a0: text-to-audio for music trained only on CC0 and synthetic audio. CLI + web UI (CUDA, Apple Silicon, CPU).
Decentralized geospatial intelligence dashboard aggregating 60+ real-time public feeds (aircraft, ships, satellites, seismic events, fires, signals) into a unified map UI.