Wanted

Free open-source Opus Clip alternative for ComfyUI — AI video clipping nodes that turn long-form videos / podcasts / interviews into ranked viral short clips for YouTube Shorts, TikTok, Instagram Reels. Server-side Whisper, virality ranking, dedupe, and face-tracked auto-crop via muapi.ai.

Contribute to manat0912/MagicQuillV2 development by creating an account on GitHub.

Universal SEO skill for Claude Code. 25 sub-skills + 18 sub-agents covering technical SEO, E-E-A-T, schema, GEO/AEO, backlinks, local SEO, maps intelligence, semantic clustering, e-commerce SEO, international SEO, Google APIs, and PDF/Excel reporting. Optional DataForSEO, Firecrawl, and Banana extensions.

Low-VRAM LoRA Training for Krea-2

Network-wide ads & trackers blocking DNS server

Desktop app with Compose Multiplatform to use Qwen3-TTS with an UI.

A Gradio WebUI for voice cloning powered by Qwen3-TTS. Provide reference audio via YouTube URL, microphone recording, or file upload — the app transcribes it with Whisper and clones the voice for TTS. Save/load voice profiles for reuse. Optimized for Apple Silicon (MPS).

Contribute to dotneet/image-to-3d development by creating an account on GitHub.

Self-hosted AI workspace.

NSFW expansion module for ComfyUI Photoreal Prompt Builder

Frame is an AI-powered, open-source vibe video editor, offering a Professional VIDEO cuting alternative for creators. With Cursor-like interaction, it automates editing, enhances videos, and delivers a seamless vibe video editing experience.

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

ComfyUI workflow Sora 2 alike

Beads - A memory upgrade for your coding agent

Visualize, collaborate, and evolve the software architecture with always actual and live diagrams from your code

Writingway is an AI-powered creative writing tool that helps authors brainstorm, refine prose, analyze story structure, and manage context dynamically. It features a chat-based workshop, customizable prompts, a project structure view, and a compendium for worldbuilding. Link to our Discord server: https://discord.gg/xkkGaRFXNX

Local voice recording for creating Piper datasets

MLX port of HeartMuLa music foundation models for Apple Silicon

Aesthetic, minimalist platform for learning Japanese inspired by Duolingo and Monkeytype, built with Next.js and sponsored by Vercel. Beginner-friendly with plenty of good first issues - all contributions are welcome!

:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)