メニュー
Install and configure Jarvis Voice — a real-time Discord voice assistant for OpenClaw. Speak in a Discord voice channel and your OpenClaw agent responds by voice.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Manage the Kanban task board — create, start, list, and trash tasks from Discord or voice. Wraps the kanban CLI to give Jarvis full board access without opening a browser.
Route Jarvis audio responses to a Sonos speaker. Mic stays on Discord/phone — only the output is redirected. Supports per-message routing and a persistent speaker mode that stays active until turned off.
Launch a safe Claude Code subagent development session for a repo. Use when the user wants to start building a feature, write code, or kick off a coding task. Opens an isolated branch with safety guardrails — agents commit freely but cannot push, open PRs, or touch main.
Send a Jarvis-voiced TTS announcement to a Sonos speaker in the house. Uses Chatterbox for voice generation. Use when the user wants to send a spoken message to someone in another room via a Sonos speaker.
Interactive Jarvis Voice installer. Walks through the complete setup from clone to first voice response, including tier selection and skill installation. Use when someone says install Jarvis, set up Jarvis voice, install Jarvis voice, or wants to get the voice bot running.
Interactive voiceprint enrollment for Jarvis Voice. Guides the user through enrolling their voice so only they can command Jarvis. Use when someone says enroll my voice, set up voiceprint, train Jarvis to recognize me, or voice enrollment.
| name | jarvis-voice |
| description | Install and configure Jarvis Voice — a real-time Discord voice assistant for OpenClaw. Speak in a Discord voice channel and your OpenClaw agent responds by voice. |
This skill installs Jarvis Voice — a Discord bot that bridges voice channels to your OpenClaw gateway agent.
Speak in a Discord voice channel. The bot transcribes your speech, sends it to your OpenClaw gateway (the same agent handling your text channels, with all its tools), and speaks the response back in the channel.
apt install ffmpeg)bash skill/install.sh
The installer checks dependencies, scaffolds your .env, installs npm packages, and creates the systemd user service.
systemctl --user start jarvis-voiceKey flags in .env:
| Flag | Default | Effect |
|---|---|---|
WAKE_WORD_ENABLED | false | Require "Jarvis" before each command |
VOICE_ACK_ENABLED | false | Say "On it" before thinking (adds ~1s latency) |
STT_PROVIDER | faster-whisper | faster-whisper / deepgram / mlx-whisper / whisper |
TTS_PROVIDER | edge | edge (free) / openai (paid) / piper (local) |
STREAMING_TTS_ENABLED | true | Sentence-by-sentence TTS for faster first word |
See .env.example for all flags with descriptions.
The bot exposes a webhook server (default port 3335) for pushing alerts and content to voice. See README.md for full docs.