tts

Convert text to speech using OpenAI, COEIROINK, and VOICEVOX engines.

Updated Jan 28, 2026
One-click install
npx skills add https://github.com/haboshi/claude-code-skills --skill tts-haboshi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tts
Source: https://github.com/haboshi/claude-code-skills/tree/main/tts
Command: npx skills add https://github.com/haboshi/claude-code-skills --skill tts-haboshi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill transforms written text into spoken audio, enabling voiceovers, audio content creation, and accessibility features.

Core Features & Use Cases

  • Multi-Provider Support: Utilizes OpenAI (cloud, high-quality), COEIROINK, and VOICEVOX (local) for flexible TTS generation.
  • Customization: Supports various voices, styles, and speed adjustments for natural-sounding speech.
  • Use Case: Generate a professional-sounding voiceover for a YouTube video script, or create an audio version of a long article for listening on the go.

Quick Start

Use the tts skill to convert the text 'Hello, world!' into speech using the OpenAI nova voice.

Frequently Asked Questions about tts

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

FAQPage Schema
How do I convert text to speech using OpenAI or VOICEVOX?

This Skill transforms written text into spoken audio using OpenAI's cloud-based gpt-4o-mini-tts, VOICEVOX, and COEIROINK engines, enabling you to generate voiceovers by providing text input and selecting a preferred voice.

What do I need to generate AI voiceovers with gpt-4o-mini-tts?

Generating AI voiceovers with gpt-4o-mini-tts requires Node.js 18+ and specific API keys for OpenAI's cloud service, or local engine configurations if you choose to use VOICEVOX or COEIROINK.

Can I batch generate audio files and concatenate WAV files?

Yes, this Skill supports batch audio generation and WAV file concatenation, allowing you to process multiple text segments and merge the resulting WAV files into a single continuous audio track.

How do I customize voice style and speed for text-to-speech output?

You can customize text-to-speech output by providing natural language style instructions and speed adjustments, allowing you to direct the AI to use specific voices like OpenAI's nova for tailored speech.

Does this text-to-speech tool work with local TTS engines like COEIROINK?

Yes, it works with local TTS engines like COEIROINK and VOICEVOX. It offers multi-provider support, allowing you to choose between cloud-based OpenAI processing or local engine generation.