jarvis-vocal for Openclaw

A neural text-to-speech skill that brings an authentic, movie-accurate J.A.R.V.I.S. voice to your AI agents and Android devices.

kishen35
v1.0.0
Apr 12, 2026
0
877
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install jarvis-vocal

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install jarvis-vocal using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is jarvis-vocal?

jarvis-vocal is a high-fidelity text-to-speech (TTS) solution designed for developers using Openclaw Skills to create immersive AI experiences. By leveraging the Piper TTS neural engine and a model specifically trained on cinematic dialogue, this skill produces a naturally British, sophisticated voice without the need for additional audio post-processing filters. It serves as a bridge between your local development environment and remote Android nodes, providing a seamless way to hear your AI agent respond in real-time using high-quality local synthesis.

jarvis-vocal Use Cases

  • Adding a professional, cinematic voice interface to local AI coding agents.
  • Broadcasting AI responses to Android mobile devices via Openclaw Skills nodes.
  • Generating high-quality narration for technical documentation or system alerts.
  • Integrating voice feedback into automated workflows for smart home or lab environments.

How jarvis-vocal Works

  1. The user provides a text string to the jarvis-speak or jarvis-tts command interface.
  2. The Piper TTS engine loads the locally stored ONNX voice model trained on movie-accurate lines.
  3. The text is processed into a high-quality WAV audio file or stream locally on the machine.
  4. If configured with Openclaw Skills nodes, the audio is pushed via ADB over a network like Tailscale to a connected Android device.
  5. The recipient device plays the audio locally, providing immediate vocal feedback from the AI.

jarvis-vocal Setup

To begin using this voice synthesis tool within Openclaw Skills, follow these steps:

Prerequisites

pipx install piper-tts
sudo apt install ffmpeg

Model Installation

Download the required assets to the specified directory:

mkdir -p ~/.local/share/piper/voices/en_GB
cd ~/.local/share/piper/voices/en_GB
hf download jgkawell/jarvis en/en_GB/jarvis/high/jarvis-high.onnx --local-dir .
hf download jgkawell/jarvis en/en_GB/jarvis/high/jarvis-high.onnx.json --local-dir .

jarvis-vocal Data Schema & Taxonomy

The skill manages audio assets and configuration parameters as follows:

Component Type Path / Detail
Voice Models ONNX ~/.local/share/piper/voices/en_GB/
Output Files WAV Local directory or /sdcard/Download/ on Android
Config Scripts jarvis-speak configuration defaults (speed, volume)
Meta Data JSON Sidecar files for ONNX model parameters

jarvis-vocal Advanced Features

  • Multi-quality model support: Choose between high-fidelity (114MB) or performance-optimized medium (63MB) models.
  • Real-time streaming: Direct audio pipe via ADB for ultra-low latency response in Openclaw Skills setups.
  • Remote execution: Integrated support for Tailscale networking to reach Android nodes anywhere.
  • Custom length-scaling: Adjustable speech rates to match the personality of your AI agent.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*