tts

Generate spoken audio with lip-sync animation and emotional tones via Python.

18|Updated Feb 9, 2026
One-click install
npx skills add https://github.com/sawarae/utsutsu-code --skill tts-sawarae
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tts
Source: https://github.com/sawarae/utsutsu-code/tree/main/.claude/skills/tts
Command: npx skills add https://github.com/sawarae/utsutsu-code --skill tts-sawarae

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python3, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows your mascot to speak messages with accompanying lip-sync animation and emotional expressions, making interactions more engaging.

Core Features & Use Cases

  • Text-to-Speech with Emotion: Convert text messages into spoken audio with specific emotional tones.
  • Lip-Sync Animation: Synchronize the mascot's mouth movements with the spoken audio.
  • Use Case: Have your mascot greet users with a "Gentle" emotion, celebrate a successful build with "Joy", or express "Trouble" when an error occurs.

Quick Start

Have the mascot say "Hello there!" with a gentle emotion.

Frequently Asked Questions about tts

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

FAQPage Schema
How do I add lip-sync animation to a mascot using text-to-speech?

Lip-sync animation for a mascot is enabled by running a Python script that converts text messages into spoken audio while synchronizing the mascot's mouth movements with the generated speech.

Can I assign different emotional expressions to text-to-speech messages?

Emotional expressions for text-to-speech can be selected dynamically based on conversation context or specified explicitly through arguments to match tones like Joy, Gentle, or Trouble.

Do I need Python to run text-to-speech with lip-sync for my mascot?

Python is a required dependency to execute the text-to-speech script that drives the mascot's lip-sync animation and emotional expression.

What happens if no text-to-speech engine is available on my system?

Text-to-speech functionality falls back to standard macOS notifications if the system detects that no dedicated TTS engine is available to play the audio.

Are there character limits for the spoken text messages?

Text-to-speech messages are subject to message length and character set restrictions to ensure proper lip-sync animation and audio playback synchronization.