Fully offline, CUDA-accelerated local voice assistant pipeline for NVIDIA Jetson.
Scanned 9/10/2026
Install to Claude Code
Skills Directorynpx -y skills add luokai0/ai-agent-skills-by-luo-kai --skill oc-jetson-cuda-voice --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Oc Jetson Cuda Voice?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/luokai0-oc-jetson-cuda-voice)More formats (shields.io, HTML) on the badges page.
---
name: oc-jetson-cuda-voice
version: 1.0.0
description: Fully offline, CUDA-accelerated local voice assistant pipeline for NVIDIA Jetson.
author: luo-kai
tags: [jetson-cuda-voice, openclaw, community]
source: https://clawskills.sh/skills/jetson-cuda-voice
---
# Jetson Cuda Voice
## Overview
Fully offline, CUDA-accelerated local voice assistant pipeline for NVIDIA Jetson.
## Before Starting
1. What specific task do you need this skill for?
2. What inputs are available?
3. What is the expected output format?
## Usage
Install via: `npx clawhub install jetson-cuda-voice`
Documentation: https://clawskills.sh/skills/jetson-cuda-voice
## Core Functionality
Fully offline, CUDA-accelerated local voice assistant pipeline for NVIDIA Jetson.
## Best Practices
- Test in sandbox environment first
- Check latest version before production use
- Review source docs for advanced configuration
## Related Skills
- agent-installer
- clawhub-publisher
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
