Do I need an API key to use this skill?

An OpenAI API key is required for cloud-based TTS. For COEIROINK and VOICEVOX, you must have the respective engines running locally on your machine.

Does it support different speaking styles and tones?

Yes, when using the OpenAI provider, you can use natural language instructions to specify tone, such as 'warm', 'professional', or 'energetic'.

Which TTS providers are supported by this skill?

The skill supports OpenAI (gpt-4o-mini-tts) for high-quality cloud generation, as well as COEIROINK and VOICEVOX for local generation.

Can I generate multiple audio files at once?

Yes, the skill includes a batch-tts script that processes JSON input to generate multiple audio segments and can automatically merge them into a single file.

Multi-Provider Text-to-Speech

Name: Multi-Provider Text-to-Speech
Author: haboshi

byhaboshi

0•

Content Management

Converts text into high-quality speech using OpenAI, COEIROINK, or VOICEVOX with batch processing and audio merging capabilities.

This Claude Code skill empowers developers to generate natural-sounding voiceovers and audio files directly from terminal commands or dialogue scripts. By supporting both high-quality cloud services like OpenAI's gpt-4o-mini-tts and local engines like COEIROINK and VOICEVOX, it offers a versatile solution for creating character dialogue, narration, and localized Japanese audio. The skill features a robust batch processing system, allows for natural language style instructions, and includes utility scripts for merging multiple WAV files into a single output, making it ideal for automated content creation and application development.

Key Features

01Multi-provider support for OpenAI TTS, COEIROINK, and VOICEVOX

02Advanced style control using natural language instructions via OpenAI

03Batch audio generation from structured JSON dialogue scripts

04Automatic WAV concatenation and file merging utilities

05Speaker mapping for complex multi-character projects

060 GitHub stars

Use Cases

01Creating professional narrations for videos or podcasts using AI voices

02Generating character dialogue for games or visual novels from script files

03Automating localized Japanese audio asset production for web applications

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add haboshi/claude-code-skills tts

For use in Claude.ai and ChatGPT