Can the skill merge separate audio segments into one file?

Yes, it includes a built-in concatenation feature that automatically joins individual speech parts into a single combined WAV file.

Which TTS providers are supported by this skill?

This skill supports OpenAI (gpt-4o-mini-tts), COEIROINK, and VOICEVOX, offering both high-quality cloud-based and local processing options.

Does it support scripts with multiple characters?

Yes, you can use a speaker map or structured JSON input to assign different voices and styles to individual segments of your script.

Can I customize the tone and style of the voice?

Yes, when using the OpenAI provider, you can provide natural language instructions such as 'speak warmly' or 'professional narrator' to precisely control the speech style.

Do I need an API key to use this skill?

An OpenAI API key is required for cloud-based TTS. However, local providers like COEIROINK and VOICEVOX can be used without an API key if the engines are running on your machine.

AI Text-to-Speech Multi-Provider

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

byhaboshi

0•

内容管理

Converts text into high-quality audio using OpenAI, COEIROINK, or VOICEVOX with support for batch processing and natural style instructions.

The TTS skill empowers Claude to generate professional-grade voiceovers and audio files directly from text inputs. By integrating with high-quality cloud providers like OpenAI and specialized local engines like COEIROINK and VOICEVOX, it offers a flexible, multi-provider architecture for creating dialogue, narrations, and batch audio segments. It features advanced capabilities like automated WAV file concatenation, speaker mapping for multi-character scripts, and natural language style instructions to control tone, emotion, and pace, making it an essential tool for content creators and developers looking to add vocal interfaces to their projects.

主要功能

01Customizable speaker mapping to link character names to specific voice IDs

02Natural language style instructions for precise tone and emotion control

03Automated WAV concatenation to merge multiple audio parts into a single file

04Multi-provider support for OpenAI, COEIROINK, and VOICEVOX engines

05Batch processing for generating complex multi-segment dialogue scripts

060 GitHub stars

使用场景

01Generating multi-character dialogue for game development or educational content

02Producing high-quality localized Japanese voiceovers using specialized local engines

03Creating automated narrations for documentation, tutorials, or blog posts

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

Download Skill