Generate karaoke videos, by downloading audio and lyrics, separating instrumentals, synchronising lyrics using transcription models, rendering CDG and uploading videos to YouTube / Dropbox / Google Drive
Radar
New projects people are discovering or following across Pinokio.
Generate complete textured 3D assets (GLB) from sparse, unposed multi-view images. Joint 3D reconstruction + generation built on TRELLIS.2 and VGGT, with a Gradio web UI. Native Windows install using prebuilt CUDA wheels.
Automated image captioning for ComfyUI using Joy Caption Alpha Two
Diffusion-based TTS with zero-shot voice cloning (1B / 3.5B). Upload a voice reference, auto-transcribe, and generate matching speech for video pickups and ADR.
One-click installer for Roblox Cube 3D: text-to-shape 3D generation with a Gradio web UI.
Pre-mastering & audio enhancement for AI-generated music. 12-stage processing chain with platform presets (Suno, Udio), before/after spectrogram, and broadcast-ready LUFS normalization.
Clean AI-generation artifacts from Suno tracks, then master for release. Free, offline, runs entirely on your machine.
Simple tabs for images and video: create, edit, image-to-video, text-to-video.
The most powerful local music generation model that outperforms most commercial alternatives.
A local-first agentic HTML editor that turns markdown, data, and notes into designed HTML artifacts.
[NVIDIA ONLY] High-Quality and Efficient 3D Mesh Generation from a Single Image (Minimum requirements 12GB VRAM / 24GB RAM)
Image-to-3D generation with Microsoft TRELLIS.2, running natively on Apple Silicon via PyTorch MPS. Gradio GUI with a 3D viewer, Metal-accelerated PBR texture baking, and GLB/OBJ export. No NVIDIA GPU required. Requires macOS on Apple Silicon (M1 or later), 24GB+ unified memory recommended. https://github.com/SUP3RMASS1VE/trellis-mac-GUI
Prompt-first symbolic-music studio powered by live TypeSafe Jev decisions. Describe music in words, listen to an editable composition, keep shaping the same piece. Requires a TYPESAFE_API_KEY for live mode; a no-credit fixture mode is built in.
Local text-to-speech WebUI on Apple Silicon, powered by Qwen3-TTS and mlx-audio
God's Eye View — live global camera map. Fork with world camera packs (~5,200 cameras, 20 countries), map labels, and production hosting.
An all-in-one, 100% local AI video, image, music & 3D studio. Its Director mode turns a single prompt into a full music video or short film — LLM-planned, shot by shot. Includes native Hunyuan3D generation alongside WanGP models. Requires an NVIDIA GPU (6GB+ VRAM).
Open-source gym & body-weight tracker, now in the App Store (iPhone + Apple Watch) and as an Android APK. Plan routines, log workouts, see which muscles are trained, import from Strong/Hevy/FitNotes. Self-host it or use it on the phone alone.
