Global radar

Qwen3-ASR is an open-source series of ASR models developed by the Qwen team at Alibaba Cloud, supporting stable multilingual speech/music/song recognition, language detection and timestamp prediction.

Open-source alternative to OpusClip - AI-powered YouTube Shorts generator.
100% free and unlimited.

Buzz transcribes and translates audio offline on your personal computer. Powered by OpenAI's Whisper.

Natively is an open-source, privacy-first AI meeting assistant and the best alternative to Cluely. It supports both local models and cloud AI providers , delivering real-time assistance during meetings, interviews, and conversations while remaining invisible in screen shares and recordings.

🔥 Clone and recreate any website as a modern React app in seconds

Generador de Imagenes

Audio driven talkinghead generation based on LivePortrait.

Contribute to LoneWolfVPS/magicresume-pinokio development by creating an account on GitHub.

a cross-platform image super-resolution tool

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Tiny, Fast, and Deployable anywhere — automate the mundane, unleash your creativity

SkyReels V1: The first and most advanced open-source human-centric video foundation model

Multi-modal Generative Media Skills for AI Agents (Claude Code, Cursor, Gemini CLI). High-quality image, video, and audio generation powered by muapi.ai.

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

FastAPI powered API for Fooocus

SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement

[ICCV 2023 Oral] Text-to-Image Diffusion Models are Zero-Shot Video Generators

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

A Gradio-based web UI for voice cloning and voice design, powered by Qwen3-TTS & VibeVoice. Can use Whisper or VibeVoice-ASR for automatic transcription. Improved from the FrankyB origial version