🟢 NVIDIA ONLY – All-in-One TTS App with Kokoro, KittenTTS, Higgs audio, Chatterbox, Fish-Speech, F5 & index-tts & indextts2, Supports Conversation Mode & eBook-to-Audiobook. All features work across all engines in a unified interface except vibe voice which is it's own app panel.
Radar
New projects people are discovering or following across Pinokio.
Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).
Swap the face in one image with the face from another image. Optionally enhance the swapped face. Upload two images and choose to enhance the result.
Hermes Agent with modern WebUI (nesquena/hermes-webui). Persistent memory, multi-provider AI (OpenAI, Anthropic, Gemini, DeepSeek, OpenRouter), scheduled cron jobs, skills, and sessions. Three-panel interface with chat, tasks, memory, and workspace browser. https://github.com/nesquena/hermes-webui
MiniMax H3 video studio with a local NVIDIA CUDA backend or a managed Runpod cloud GPU.
Fast AI Video Generation per GPU poor (Wan2.1, Hunyuan, LTV). Gradio UI su http://127.0.0.1:7860
The JARVIS project is an advanced, AI-powered virtual assistant and autonomous agent designed to simplify your digital life. By leveraging powerful language models, it automates workflows, answers queries, manages smart home devices, and navigates the web to assist with complex daily tasks.
Run voice AI locally with open-source models. Bring it to any device with one command.
User-friendly WebUI for LLMs, supported LLM runners include Ollama and OpenAI-compatible APIs https://github.com/open-webui/open-webui
Installe Ollama (si pas déjà) et ajoute DeepSeek-Coder au sein de Pinokio.
Bots are automated tools designed to streamline the process of submitting reports on Instagram accounts that may violate the platform’s Community Guidelines. They can assist with reporting issues such as spam, report reporter mass acc ban bot impersonation, fake profile account, or other policy violations. Depending on their functionality, tool
Turn any image into a video! (Web UI created by fffiloni: https://huggingface.co/spaces/fffiloni/MS-Image2Video)
Image-to-Image model. Download, explore files and run it on Hugging Face.
AI video generation browser for Wan2GP / WanGP (and ComfyUI output folders): library, full generation recipe per clip, settings diff and side-by-side, wipe and blink A/B comparison.
Apple Silicon TTS — curated MLX-first models for cloning, multilingual speech, narration, and expressive voices.
Text-to-Speech model. Download, explore files and run it on Hugging Face.
