skills.rest
DisruptionEngineer
DisruptionEngineerCOMMUNITY
Explore all skills by this author →
GitHub

voice-customizer

Train wake words and clone voices for Pi deployment via Discord.

Updated Aug 27, 2026
Search Tags:#deployment#tts#pi#discord-bot#voice-cloning#wake-word#watchtower
One-click install
npx skills add https://github.com/DisruptionEngineer/build-useful-skills --skill voice-customizer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: voice-customizer
Source: https://github.com/DisruptionEngineer/build-useful-skills/tree/main/voice-customizer
Command: npx skills add https://github.com/DisruptionEngineer/build-useful-skills --skill voice-customizer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manage wake words and TTS voice profiles for the Jarvis kitchen Pi via Discord. Train openWakeWord models, clone voices from YouTube references, switch active wake word or voice, and deploy configuration changes to the Pi voice assistant.

Core Features & Use Cases

  • Wake word training via openWakeWord Docker on WatchTower.
  • Voice cloning from YouTube audio using XTTS v2.
  • Listing available wake words and voices, switching the active wake word or voice, and deploying updates to the Pi.
  • Handling approvals through Discord to prevent accidental deployments.

Quick Start

Use the Discord commands to train a wake word or clone a voice, then approve deployment to the Pi.

Frequently Asked Questions about voice-customizer

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

FAQPage Schema
How do I train a custom wake word for a Raspberry Pi voice assistant?▼

Wake word training is automated via openWakeWord Docker on WatchTower, allowing you to train new models and deploy them to a Pi-based voice assistant. You initiate training through Discord commands and approve the deployment through a pending-approval workflow.

Can I clone a voice from YouTube audio for a TTS deployment?▼

Yes, voice cloning from YouTube audio is performed using XTTS v2 to create TTS voice profiles. The Skill validates the input audio, clones the voice, and configures it for deployment to the Pi-based kitchen assistant.

How do I switch active TTS voices and wake words on a Raspberry Pi?▼

You can list available wake words and TTS voices, then switch the active profile by issuing Discord commands. The Skill updates local and remote configs and performs safe restarts to apply the new voice or wake word.

Do I need Discord to approve wake word deployments to the Pi?▼

Yes, Discord is required to handle the pending-approval workflow and prevent accidental deployments. The Skill uses Discord commands to manage, approve, and trigger configuration updates for both WatchTower and the Pi.

What is the best way to deploy openWakeWord models to a Pi-based assistant?▼

The best way to deploy openWakeWord models is through an automated pipeline that updates WatchTower and the Pi config simultaneously. The Skill validates inputs, manages approvals via Discord, and ensures safe restarts of the voice assistant.

Related Skills

Explore More Software Engineering Skills→
VivekSinghRathore7VivekSinghRathore7

configure

Automates Discord channel setup by saving bot tokens and reviewing access policies.

Community
Intermediate
want2betwant2bet

pi-deployment

Deploy Bob The Skull to Raspberry Pi with Python files and configuration.

Community
Advanced
PsiACEPsiACE
6

discord

Send Discord messages, manage channels, and respond to events.

Community
Intermediate
JosiahSiegelJosiahSiegel
51

fal-audio

Transcribe audio, translate speech, synthesize voices, and clone voices.

Community
Advanced