Multi-model text-to-audio / audio-to-audio Gradio interface for Apple Silicon — Stable Audio Open, Stable Audio 3, AudioLDM2, ACE-Step
Radar
New projects people are discovering or following across Pinokio.
Auris-BadBaDaki is Offline audiobook reader for EPUB, PDF, and TXT with local OmniVoice TTS, character-aware voices, per-book narrator control, and synced text highlighting. Everything runs locally after setup. No API keys. No hosted TTS dependency.
Zero Breach — local, read-only scanner that checks a computer for indicators of the AdFection / Candiru ad-delivered spyware campaign. No network, no admin, no dependencies.
Text-to-Image model with 0.9B parameters. Download, explore files and run it on Hugging Face.
An all-in-one, 100% local AI creative studio, director, and multi-track editor. Generate with MiniMax H3, LTX-2.5/2.3, Wan, Flux, Qwen, and more; turn an idea or song into a planned production; then finish it on the timeline. Requires an NVIDIA GPU (6GB+ VRAM).
WatermarkRemover AI photo cleanup and WatermarkRemover AI video review share one local workspace. Mark a logo, caption, or timestamp, then check the mask before inpainting rebuilds that area. A short WatermarkRemover AI tutorial keeps each step clear for pictures and clips you created or are allowed to edit.
An AI radio station you run yourself. Picks the records, presents between them, and streams it. https://github.com/robert-dean/deadair
Make a complete drama song ad: a long-form ad sung as a drama, from script to song to finished video. Originally designed for the MaxFusion AI MCP, tool-agnostic: works with any image, audio and video generation tools, or by hand.
[NVIDIA ONLY] Advanced Web UI for CogVideo (text to video, image to video, video to video, extend video, etc) -- Generate videos with less than 10GB VRAM
VectorCraft: An open-source, vector art tool written by scratch in pure Rust
Text-to-Speech model with 40.2M parameters. Download, explore files and run it on Hugging Face.
Text-to-Speech for 16 Indian languages: Assamese, Bengali, Bodo, English (Indian accent), Hinglish, Gujarati, Hindi, Kannada, Malayalam, Manipuri, Marathi, Odia, Punjabi, Rajasthani, Tamil, and Telugu. SOTA models based on FastPitch and HiFi-GAN V1.
