skills.rest
tdimino
tdiminoCOMMUNITY
Explore all skills by this author →
Website𝕏@IdaeanDaktylGitHub

speak-response

Vocalize AI-generated text responses using a local Qwen3-TTS engine.

41|3|Updated Jan 2, 2026
Search Tags:#text-to-speech#tts#voice cloning#qwen3-tts#local inference#voice design
One-click install
npx skills add https://github.com/tdimino/claude-code-minoan --skill speak-response
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: speak-response
Source: https://github.com/tdimino/claude-code-minoan/tree/main/skills/design-media/speak-response
Command: npx skills add https://github.com/tdimino/claude-code-minoan --skill speak-response

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill allows Claude to speak its responses aloud using your local machine's processing power, eliminating the need for external text-to-speech services and offering advanced voice customization.

Core Features & Use Cases

  • Local Text-to-Speech: Utilizes Qwen3-TTS for on-device speech generation.
  • Customizable Voices: Choose from preset speakers, clone your own voice, or design entirely new ones using natural language descriptions.
  • Emotion Control: Fine-tune the delivery with mood presets and detailed instructions.
  • Use Case: Have Claude read out your code review feedback in a professional tone, or narrate a story in a deep, dramatic voice.

Quick Start

Ask Claude to speak the last response using the default Oracle voice.

Frequently Asked Questions about speak-response

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

FAQPage Schema
How do I run text-to-speech locally for AI responses without external services?▼

You can vocalize AI text responses locally by utilizing the Qwen3-TTS engine on-device, which eliminates external text-to-speech service dependencies and keeps all voice synthesis private on your machine.

How does voice cloning work with local TTS inference?▼

Local TTS voice cloning works by processing audio input through the Qwen3-TTS engine on your machine, allowing you to replicate voice characteristics entirely on-device for private, customized speech generation.

Can I design a custom TTS voice using natural language descriptions?▼

You can design custom TTS voices from natural language descriptions by instructing the Qwen3-TTS engine to interpret text prompts and generate entirely new, customized voice profiles on-device.

Does local TTS inference support emotion-controlled voice synthesis?▼

Emotion-controlled voice synthesis is supported through mood presets and detailed instructions, allowing you to fine-tune the delivery of preset speakers and adjust the emotional output of your local TTS inference.

Is on-device text-to-speech optimized for Apple Silicon?▼

On-device text-to-speech is optimized for Apple Silicon using bfloat16 precision, which specifically reduces memory usage and accelerates local inference speeds on Apple Silicon hardware.

Related Skills

Explore More Design & Creative Skills→
jaminitachijaminitachi
1

tts

Converts Markdown documents to speech audio using the TTS pipeline.

Community
Advanced
DotNetAgeDotNetAge
32

sag

Convert text to speech with ElevenLabs voices via the sag CLI.

Community
Intermediate
malue-aimalue-ai
36

kokoro-tts

Generate local text-to-speech audio with Kokoro TTS engine.

Official
Intermediate
EmZodEmZod
8

speak-tts

Generate speech from text with on-device TTS and voice cloning on Apple Silicon.

Community
Advanced