跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

happy-audio-gen

Plugin 已验证
90

Universal AI TTS / voice generation across OpenAI TTS, ElevenLabs, Bailian Qwen-TTS, MiniMax, SiliconFlow CosyVoice, and PlayHT. Auto-chunks long Chinese text for Qwen-TTS.

AI 摘要

This skill aggregates numerous AI text-to-speech services including OpenAI TTS, ElevenLabs, and Bailian Qwen-TTS. It offers specialized functionality for processing long Chinese text by automatically chunking it for services like Qwen-TTS.

Scope

  • info:Single responsibility principleThe extension bundles multiple AI TTS providers for voice generation, which is a coherent domain. However, the breadth of providers might lead to a large toolset, bordering on aggregation of loosely related workflows.

Invocation

  • warning:Scoped toolsThe extension likely exposes a single interface for voice generation that then dispatches to different providers, rather than having distinctly scoped tools for each provider's nuances.

Documentation

  • warning:Install / Setup InstructionsWhile dependencies are mentioned, the SKILL.md does not provide explicit install commands for the skill itself or configuration instructions for providers.

安装

请先添加 Marketplace

/plugin marketplace add iamzhihuix/happy-claude-skills
/plugin install happy-audio-gen@happy-claude-skills
22 days ago
285 stars
MIT
更新于 6 days ago
查看源代码