Skip to content
Agentmart
Submit a tool

语音合成

GPT-SoVITS 高质量语音合成(声音克隆 + 情绪表达),Edge-TTS 自动回退

Skill by yuxinbeiyi

IndexedMIT★ 15
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/yuxinbeiyi-232310

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

GPT-SoVITS 高质量语音合成(声音克隆 + 情绪表达),Edge-TTS 自动回退

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/skill

What's inside

Skill name
语音合成
Description
GPT-SoVITS 高质量语音合成(声音克隆 + 情绪表达),Edge-TTS 自动回退
License
MIT
Instructions
29 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Agent Skills spec issues

  • name: only lowercase letters, digits and single hyphens allowed

Files (9)

  • SKILL.md
  • config.json · ref_wavs/
  • config.json.bak · ref_wavs/
  • 收音机.wav · ref_wavs/
  • 槲寄生.wav · ref_wavs/
  • 温.wav · ref_wavs/
  • 牙仙.wav · ref_wavs/
  • 露西.wav · ref_wavs/
  • tools.py

SKILL.md (first lines)

# 语音合成

激活此技能后,莲心可以使用 GPT-SoVITS 进行高质量语音合成(含声音克隆),
并在 GPT-SoVITS 不可用时自动回退到 Edge-TTS(标准云端发音)。

## 能力说明

- **声音克隆**:通过参考音频定义莲心的专属声线,让每次语音回复都有统一的"人设声音"
- **情绪选择**:支持 casual(日常温柔)、tsundere(傲娇)、romantic(深情)、long(长句)、angry(生气)五种情绪音色
- **自动语音朗读**:每次回复都会自动通过语音朗读,无需调用工具
- **无缝回退**:GPT-SoVITS 不可用时自动使用 Edge-TTS,语音功能不受影响

## 工具使用场景

| 场景 | 调用 |
|------|------|
| 用户问"有哪些语音风格" | `list_voice_styles()` |
| 用户说"把语音风格设为深情" | `set_voice_mood(mood="romantic")` |

## 使用规则

- 语音朗读由系统自动完成,你不需要主动调用任何语音合成工具
- 用户问"有哪些语音风格"时,调用 `list_voice_styles`
- 用户说"切换语音风格"时,调用 `set_voice_mood`
- 用户说"用语音说句话"等请求时,正常回复即可,系统会自动朗读

**语言要求**:全程使用中文回复用户,不要使用日文或其他语言。

From yuxinbeiyi/Lianxin-AI, MIT.

More from yuxinbeiyi/Lianxin-AI

Signals

Stars
15
Forks
0
Open issues
0
Last commit (this folder)
Oct 15, 2026 (14 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from yuxinbeiyi

Cite this page

语音合成 skill. Agent Mart. https://agentmart.dev/skills/yuxinbeiyi-232310 (last updated 2026-10-24)