AudioChunker
Audiochunker — slice any audio into perfectly timed clips, instantly Audiochunker is a lightweight Pinokio ap...
Launcher updates
Free AI Agents, Forever
Included a feature called Router, which you can manually connect and plug in free models across many provider...
Phosphene 3.2.4 - Ideogram 4 now runs on M1 and M2 Macs
Phosphene 3.2.4 fixes Ideogram 4 for slower Apple GPUs. It now runs on M1 and M2 Macs, not just the fast ones...
UnderfitFeatured
Underfit is for musicians, sound designers, sample makers, and audio experimenters who want Stable Audio 3 to...
Store
Automatically clip videos and generate captions for LoRA training using advanced vision models like Gemma-3, Qwen3-VL, and Qwen2-VL.
✨ The agentic HTML editor — your local AI agent writes the HTML, you ship it. 🚀 75 Skills × 9 Surfaces (magazine · deck · poster · XHS / tweet · prototype · data report · Hyperframes) 🛡️ Sandboxed preview · 📤 1-click to WeChat / X / Zhihu / HTML / PNG 🔑 Zero API key — Claude Code / Cursor / Codex / Gemini / Copilot / OpenCode / Qwen / Aider.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
MuseTalk is a cutting-edge video-to-video (V2V) lip-sync solution engineered to deliver highly accurate and natural mouth movements synchronized to audio input. Precision LipSync: Realistic and seamless synchronization of speech audio to facial movements. Efficiently designed to run on 8–12 GB VRAM,
@manatheturipa
2 check-ins
LLM-powered dating simulator
RMBG-2-StudioFeatured
Enhanced background remove and replace app built around BRIA-RMBG-2.0 https://huggingface.co/briaai/RMBG-2.0
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Higgs Audio v3 TTS + AI text director, voice cloning, podcast & audiobook (multi-speaker). 100+ languages, offline, NVIDIA GPU.
@nerual_dreming4 check-ins
Contribute to jd-opensource/JoyAI-VL-Interaction development by creating an account on GitHub.
Demo of ESpeech TTS models
Stores all your tweets nicely claw-able for agents.
A multi-voice AI audiobook generator built on Qwen3-TTS — annotate scripts with an LLM, assign unique voices to each character, per-line style instructions for delivery, clone voices from reference audio, design new voices from text descriptions, train custom voices with LoRA fine-tuning, and export to MP3 or Audacity multi-track projects
Free voice gen, video gen & anti-copyright yt
Orpheus-TTS-FastAPIFeatured
Orpheus TTS is an open-source text-to-speech system built on the Llama-3b backbone. Orpheus demonstrates the emergent capabilities of using LLMs for speech synthesis https://github.com/canopyai/Orpheus-TTS
Next-Gen High-Resolution 3D Model Generation
This app lets you upload any picture and turns it into a 3D Gaussian‑splat model that can be viewed or downloaded as a PLY or .splat file. You can adjust settings like seed, steps, and detail level...
[NVIDIA Only] Wan2.2 video Studio (text/image-to-video, restyle, keyframe, talking-character S2V) + LoRA Gym + MOVA joint audio+video. From 12GB VRAM.
Codex-assisted local 2D animation spritesheet generator and scene compositing workspace.
P2PCLAW Agent Benchmark — connect any LLM agent (Claude, GPT, Gemini, Qwen, Kimi, DeepSeek…) and get scored on 10 dimensions + Tribunal IQ. Dashboard runs locally on :8787, leaderboard at p2pclaw.com/app/benchmark.
Python bindings for llama.cpp