jarvis-voice

Name: jarvis-voice
Availability: InStock
Author: laoye2020

Generate spoken responses with a metallic AI voice using sherpa-onnx and ffmpeg.

Updated Aug 23, 2026

Search Tags:#voice #audio #persona #tts #sherpa-onnx #jarvis

Ready to run

npx skills add https://github.com/laoye2020/openclaw-workspace-clean --skill jarvis-voice

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: jarvis-voice
Source: https://github.com/laoye2020/openclaw-workspace-clean/tree/main/skills/jarvis-voice
Command: npx skills add https://github.com/laoye2020/openclaw-workspace-clean --skill jarvis-voice

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a unique, metallic AI voice persona for spoken responses, enhancing user engagement and offering a distinct auditory experience.

Core Features & Use Cases

TTS Output: Utilizes local speech synthesis (sherpa-onnx) for privacy and offline use.
Metallic Voice: Applies audio processing (ffmpeg) for a robotic, JARVIS-like sound.
Visual Styling: Supports custom styling for transcripts (purple italics) when integrated with a compatible UI.
Use Case: An AI assistant responding to user queries with a consistent, recognizable robotic voice, making interactions more immersive.

Quick Start

Use the jarvis skill to speak the phrase "Hello, I am your AI assistant."

Frequently Asked Questions about jarvis-voice

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate a robotic metallic AI voice for text to speech?▼

To generate a metallic AI voice, this Skill synthesizes speech locally using sherpa-onnx and processes the audio with ffmpeg to create a distinct, JARVIS-like robotic sound for spoken responses.

Can I use local TTS for offline voice assistant responses?▼

Yes, you can use local TTS for offline voice assistant responses. It utilizes sherpa-onnx for speech synthesis, ensuring privacy and offline functionality without relying on external cloud APIs.

Do I need ffmpeg and aplay to process TTS audio playback?▼

Yes, you need ffmpeg and aplay. FFmpeg applies the metallic audio processing effect, while aplay handles the final audio playback, and sherpa-onnx manages the underlying text-to-speech synthesis.

What is a metallic voice persona in AI text to speech?▼

A metallic voice persona is an auditory identity for AI assistants. It processes standard TTS output with audio filters to produce a consistent, robotic sound that enhances user engagement and immersion.

How to display styled visual transcripts for voice assistant replies?▼

To display styled visual transcripts, this Skill supports custom UI styling such as purple italics. This visually enhances the text representation of the spoken TTS output during assistant communication.