Voice Design

Community

win4r

voice_design

Choose or design a new speaking voice when the user asks for a new, different, custom, invented, or generated voice.

Overview

Publisher	win4r
Repository	`MuseAI-Skills`
Skill name	`voice_design`
Stars	382
Forks	116
Bundled files	Instructions only
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by win4r on GitHub. Read the source before you install it.

Installation

Install the Voice Design AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/win4r/MuseAI-Skills/tree/main/opt/hatch/skills/voice-design
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/win4r/MuseAI-Skills.git /tmp/MuseAI-Skills
mkdir -p .claude/skills
cp -r /tmp/MuseAI-Skills/opt/hatch/skills/voice-design .claude/skills/voice_design

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Voice Design in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Voice Design on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Voice Design is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Voice design

Help the user choose a new voice. By default, one result is selected immediately. An explicit request for two or three options returns existing voices without selecting one. Never present a picker or create a widget.

Start naturally

Let the user's request lead. If they only say they want a new or custom voice without giving any direction, ask one short question: do they want to describe the voice, or should you pick one for them? Then wait for the answer. Do not start voice design in the background before they answer.

If the user explicitly asks to create multiple new voices, explain that this flow creates one new voice at a time and ask which one to start with. Do not silently replace requested new designs with existing library voices.

Ask at most once. If the user gives any usable direction, says “surprise me,” or asks you to choose, proceed without another question or confirmation.

Choose the path

Call muse.voice_options exactly once with the complete request.

Treat allow_create_new_voices as permission, not your choice of outcome. Set it to true when the user permits creating a custom voice, including requests to create, design, invent, or generate one, or hands you the open choice with “pick one for me” or “surprise me.” The runtime still chooses an existing system or saved voice when it is the best fit.
Set it to false when the user restricts the choice to existing system or saved voices.
Set candidate_count to an explicitly requested two or three, and use three for “a few.” Otherwise use one. Counts above one return existing voices only and do not select, save, or switch, so set both creation fields to false.
For candidate_count one, set require_new_voice to true only when the user explicitly requires a newly created voice. Preserve true when their current reply answers your immediately preceding clarification about a request to create, design, invent, generate, or make a custom or brand-new voice. For example, “surprise me” after “make a brand-new voice” still requires a new design. Set it to false for an open request to pick a different voice, where the runtime may choose a strong library match.
Put the user's complete voice request in request, including preferences established by the immediately preceding exchange.

Preserve every explicit attribute in the immediate request. The runtime supplies the current voice, available library, and bounded persona and avatar context to the selector. Do not copy private or unrelated facts into the tool request.

The rewrite service expands a custom request into the detailed acoustic prompt, conversational instructions, name, and preview text required by the voice model. Do not write those implementation fields yourself and do not call muse.design_voice.

Report the result

Custom design runs in one managed background worker. Briefly say it is being created, then continue normally. Do not poll, retry automatically, or start a second design while it is running.

Follow the tool's authoritative result:

For options, name the returned voices and ask the user to choose. Do not claim anything was selected, saved, or switched.
In text, say which single voice you picked and invite the user to start a call to hear it.
During a call, confirm the new voice only after live_switch_completed is true, then invite the caller to change it again if they want.
If a call ended or changed before activation, say the preference was saved but that call did not switch.
If the result includes a soft-refusal message, say it naturally once before describing the safe alternative.

Refer to voices only by display name. Never expose voice, saved-voice, profile, call, or worker identifiers. Do not create chat preview UI; voice previews stay in Voice Settings.

Frequently asked questions

What does the Voice Design AI skill do?

Choose or design a new speaking voice when the user asks for a new, different, custom, invented, or generated voice.

Why use Voice Design on TypingMind?

Because you install it once and use it with any model. Voice Design is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Voice Design in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/win4r/MuseAI-Skills/tree/main/opt/hatch/skills/voice-design. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Voice Design?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Voice Design?

As many as you like. As long as a model supports skills, you can use Voice Design with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Voice Design AI skill free?

It is published on GitHub by win4r. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Mono Color

NousResearch

OrganizationPopular

Generate one- or two-ink editorial print poster images.

Pretext

Build creative browser demos with DOM-free text layout.

Sketch

Throwaway HTML mockups: 2-3 design variants to compare.

Tldraw Offline

Drive and script tldraw offline canvases with an agent.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Voice design

Start naturally

Choose the path

Report the result

Frequently asked questions

Related AI Skills

Set up your own AI workspace now