Skip to content

About

音色库没有?一句话描述现造一个 | No matching voice? Describe one in a sentence · 📮 wow.vip@foxmail.com · 🎬 https://v.douyin.com/07EjIDGVErY/

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 

Repository files navigation

🎬 voice-design

音色库没有?一句话描述现造一个

No matching voice? Describe one in a sentence

📮 商务合作 / Business:wow.vip@foxmail.com 🎬 抖音 / Douyin:v.douyin.com/07EjIDGVErY


🇨🇳 中文

当官方音色库找不到合适的声音、需要独特音色身份时,用自然语言描述声音特征来设计并试听自定义音色。输入年龄、性别、情感色彩、语速等描述与试听文本,先改写提示词并确认语种,再产出试听样本和可复用的 voice_id 供 TTS 集成使用。适合在检索现有音色后仍不合适时,做声音方向的对比与收敛。该功能属实验性质,品质通常低于内置音色库,建议优先复用已有音色。

✨ 能做什么

  • 输入声音特征描述与试听文本 → 输出试听样本与可复用 voice_id
  • 改写提示词,收敛年龄、质感、语速与情绪等声音方向
  • 生成前先确认语种与发音目标
  • 产出试听样本、音色选择建议与 TTS 集成标识
  • 适合检索现有音色库后仍找不到合适声音的场景
  • 实验性质,品质通常低于内置音色库,建议优先复用现有音色

📦 包含的技能

🚀 安装

git clone https://github.com/yzsp-studio/voice-design.git
cp -r voice-design/* "$DSH_HOME/skills/"

技能是纯文本说明(SKILL.md + references/),零依赖、零 API key,用你当前 agent 的会话额度。


🇬🇧 English

Designs and previews a custom voice from text when the standard voice library has nothing suitable and a distinct voice identity is required. Input is a natural-language description of the desired traits — age, gender, emotional color, pace — plus a preview text. The prompt is refined, language is confirmed, and the output is preview audio plus a reusable voice_id for TTS integration. This is an experimental feature whose quality is usually below the built-in voice library, so searching existing voices first is recommended.

✨ What it does

  • Turns a natural-language trait description plus preview text into a custom voice
  • Rewrites the prompt to converge age, texture, pace, and emotional character
  • Confirms language and pronunciation goals before generating
  • Returns preview samples, selection guidance, and a reusable voice_id for TTS
  • Best used when searching the existing library found nothing suitable
  • Experimental: quality is often below built-in voices, so reuse comes first

📦 Skills included

🚀 Install

git clone https://github.com/yzsp-studio/voice-design.git
cp -r voice-design/* "$DSH_HOME/skills/"

Skills are plain-text instructions (SKILL.md + references/). Zero dependencies, no API keys — they run on your agent's existing session quota.


📮 联系 / Contact

🎬 抖音 / Douyin https://v.douyin.com/07EjIDGVErY/
📮 商务合作 / Business wow.vip@foxmail.com
🐙 GitHub https://github.com/yzsp-ai
💖 打赏 / Support afdian.com/a/yzsp-ai

📄 License

MIT · © 2026 yzsp-ai

About

音色库没有?一句话描述现造一个 | No matching voice? Describe one in a sentence · 📮 wow.vip@foxmail.com · 🎬 https://v.douyin.com/07EjIDGVErY/

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors