菜单
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.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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.
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.
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.
| name | sonos-announce |
| description | 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. |
| tier | FRIDAY |
| triggers | ["tell [name] to","announce","say on the sonos","send a message to the kitchen","send a message to the bedroom","let her know","let him know","message the speaker","play on sonos","say upstairs","say downstairs"] |
Send a spoken message to any Sonos speaker in the house using the Jarvis (Chatterbox) voice.
"Jarvis, tell [name] to check their phone." "Say on the kitchen speaker: dinner is ready." "Announce upstairs that I'm heading out." "Send a message to the bedroom."
Speakers are configured in .env:
| Variable | Description |
|---|---|
SONOS_DOWN_IP | Downstairs speaker IP (e.g. kitchen) |
SONOS_UP_IP | Upstairs speaker IP (e.g. bedroom) |
SONOS_DEFAULT | Default target: up, down, or all |
GAMEZ_IP | IP of the machine serving the audio file |
GAMEZ_PORT | Port for the audio HTTP server (default: 8765) |
CHATTERBOX_HOST | SSH alias for the machine running Chatterbox TTS |
CHATTERBOX_URL | Chatterbox endpoint (default: http://localhost:3340/tts) |
Location is inferred from natural language:
| User says | Target |
|---|---|
| "upstairs", "bedroom", "bathroom" | up |
| "downstairs", "kitchen", "living room" | down |
| "everywhere", "all speakers", "the whole house" | all |
| (no location) | $SONOS_DEFAULT (default: down) |
sonos-say <up|down|all> "message"
See SETUP.md for installation.
| User says | Jarvis announces |
|---|---|
| "Tell [name] to check their phone" | "Hey [name], [user] was wondering if you would check your phone." |
| "Let her know dinner is ready" | "Hey [name], [user] wanted to let you know that dinner is ready." |
| "Tell her I'll be there in 5" | "Hey [name], [user] will be there in about five minutes." |