mcpField
T
tts-skill

tts-skill

github.com/noteditCreative & media34098 installsUpdated 34w ago
Repository

About tts-skill

MiniMax TTS Skill wraps the MiniMax TTS API in a Python module for developers working with speech generation. Alongside text-to-speech, it can list voices, clone a voice from audio, and design a voice from a text description.

Key features

  1. 01Convert text into audio files
  2. 02List available voices
  3. 03Clone a voice from audio
  4. 04Design a voice from a description
  5. 05Play audio files

Use cases

  1. 01Create speech files from text
  2. 02Find a suitable preset voice
  3. 03Create a custom voice from a sample
  4. 04Preview a voice described in text

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/notedit/happy-skills --skill tts-skill

After installing, type/tts-skillin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

assets/
minimax_tts.py
rules/
list-voices.md
setup.md
text-to-audio.md
voice-clone.md
voice-design.md

Details

From the project README

MiniMax TTS Skill

这个 Skill 提供 MiniMax TTS API 的完整封装，支持文本转语音、声音克隆和声音设计功能。

快速开始

1. 环境配置

确保已设置环境变量：

export MINIMAX_API_KEY="your-api-key"

详细配置说明见 setup.md

2. 使用 Python 模块
import sys
import os

# 获取 skill 目录路径
skill_dir = os.path.dirname(os.path.abspath(__file__))
sys.path.insert(0, os.path.join(skill_dir, "assets"))

from minimax_tts import text_to_audio, list_voices, voice_clone, voice_design, play_audio

功能概览

功能函数说明
文本转语音text_to_audio()将文本转换为语音文件
列出声音list_voices()获取可用的声音列表
声音克隆voice_clone()基于音频文件克隆声音
声音设计voice_design()根据文字描述生成声音
播放音频play_audio()播放音频文件

详细文档

快速示例

文本转语音
text_to_audio(
    text="你好，欢迎使用 MiniMax TTS 服务！",
    voice_id="female-shaonv",
    output_path="./hello.mp3"
)
列出可用声音
voices = list_voices(voice_type="system")
for voice in voices:
    print(f"{voice['voice_id']}: {voice['name']}")
声音克隆
voice_clone(
    voice_id="my-custom-voice",
    audio_file="./sample.mp3",
    voice_name="我的声音"
)
声音设计
voice_design(
    prompt="一个温柔的年轻女性声音，带有轻微的南方口音",
    preview_text="你好，这是我的声音"
)

支持的模型

模型说明
speech-02-hd高清版本，音质最佳
speech-02-turbo快速版本，延迟低
speech-01-hd旧版高清
speech-01-turbo旧版快速
speech-2.6-hd2.6 版高清
speech-2.6-turbo2.6 版快速

常用声音 ID

系统预设声音
  • female-shaonv - 少女音
  • female-yujie - 御姐音
  • female-chengshu - 成熟女声
  • male-qingnian - 青年男声
  • male-chengshu - 成熟男声

更多声音请使用 list_voices() 查询。

Comments

Markdown supported