CommunityCoding & Developmentgithub.com

lgwanai/sound-skill

A Codex/Claude Skill engineering project for local sound production workflows. It focuses on five capabilities: timbre design, voice cloning, ASR transcription, video timbre extraction, and global timbre management. Defaults to running locally on Apple Silicon Mac, using local directories and local oMLX HTTP services for model files to avoid uploading audio to the cloud.

What is sound-skill?

The lgwanai/sound-skill is a specialized AI agent skill designed for local sound production workflows, compatible with platforms like Codex and Claude. It offers five core capabilities: timbre design, voice cloning, automatic speech recognition (ASR) transcription, video timbre extraction, and global timbre management. By default, this skill runs entirely on Apple Silicon Mac hardware, leveraging local model directories and a local oMLX HTTP service to process audio. This local-first approach ensures all audio data remains on the user's machine, providing enhanced privacy and faster processing by avoiding any cloud uploads. Developers can use this skill to integrate robust, privacy-focused sound manipulation and analysis into their AI agent workflows, making it ideal for offline or sensitive audio projects.

Works with✓Claude Code✓Codex CLI~Cursor
npx skills add lgwanai/sound-skill

Installed? Explore more Coding & Development skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

What does sound-skill do?

A Codex/Claude Skill engineering project for local sound production workflows. The project focuses on five capabilities: timbre design, voice cloning, ASR transcription, video timbre extraction, and global timbre management. It defaults to running locally on Apple Silicon Mac, using local directories and a local oMLX HTTP service for model files to avoid uploading audio to the cloud.

Related Skills