OpenClaw

mm-easy-voice

Simple text-to-speech skill using MiniMax Voice API. Converts text to audio with customizable voice selection. Use for generating speech audio from text.

blue-coconut0 来源安装数☆ 0 仓库 Stars

查看来源 ↗安装与使用 SKILL.md ↗

安装与使用

请根据来源仓库和你的 AI 工具说明安装此技能。先阅读技能文件和依赖要求，再添加到工作流。

SkillHub CLI

skillhub install blue-coconut/mm-easy-voice

打开来源仓库，查看说明和兼容环境后，按来源提供的命令或步骤安装。

将来源链接提供给你的 Agent，让它先读取说明、核对依赖，并向你说明将执行的安装步骤。

查看来源 ↗使用指南

技能说明

MiniMax Easy Voice

Simple text-to-speech skill powered by MiniMax Voice API. Converts any text into natural-sounding audio with customizable voice selection.

Usage

[Step 1] Preparation

IMPORTANT: Before using this skill, always verify the environment:

python check_environment.py

If API key is not set:

export MINIMAX_VOICE_API_KEY="your-api-key-here"

Requirements:

Python 3.8+
MINIMAX_VOICE_API_KEY environment variable (required)
FFmpeg (optional, for audio merging/conversion)

[Step 2] Generate speech audio from text

Convert any text to speech in one command:

# Default voice (male-qn-qingse)
python mmvoice.py tts "Hello, this is a test." -o test.mp3

# Chinese text
python mmvoice.py tts "你好，这是一个测试。" -o test_cn.mp3

# Specify a different voice by "-v voice_id"
python mmvoice.py tts "Hello world" -v female-shaonv -o hello.mp3

# Specify output path
python mmvoice.py tts "Your text" -o /path/to/output.mp3

Required parameters:

text: The text you want to convert to speech
-o OUTPUT: Output audio file path (required)

Optional parameters:

-v VOICE_ID: Voice to use (default: male-qn-qingse)

Usage Details

Text length limits:

Up to 10,000 characters per request
For longer text, split into multiple requests and merge later

Pause insertion: Use <#x#> where x = pause duration in seconds

Example: "Hello<#1.5#>world" = 1.5 second pause between words
Range: 0.01 to 99.99 seconds

Emotion matching: speech-2.8 models automatically match emotions to your text content

Voice Selection

Choose the right voice for your content by consulting the voice catalog:

# List all available voices
python mmvoice.py list-voices

Voice catalog: reference/voice_catalog.md

Contains:

All available system voices (male, female)
Voice characteristics and recommended use cases
How to select the right voice for your content

Advanced Op...

来源信息

Source: github
Repository: openclaw/skills
Path: skills/blue-coconut/mm-easy-voice
Version: —
Commit: 2bb051c0b96d53619d3863fe6ce0f9f30041adde
分类来源: rules
状态: active
可见性: public

这些信息来自收录时的来源分析，可能滞后；使用前请核对最新来源文件。

来源内容

SKILL.md

# MiniMax Easy Voice

Simple text-to-speech skill powered by MiniMax Voice API. Converts any text into natural-sounding audio with customizable voice selection.


## Usage
### [Step 1] Preparation

**IMPORTANT:** Before using this skill, always verify the environment:

```bash
python check_environment.py
```

**If API key is not set:**
```bash
export MINIMAX_VOICE_API_KEY="your-api-key-here"
```

**Requirements:**
- Python 3.8+
- MINIMAX_VOICE_API_KEY environment variable (required)
- FFmpeg (optional, for audio merging/conversion)


### [Step 2] Generate speech audio from text

Convert any text to speech in one command:

```bash
# Default voice (male-qn-qingse)
python mmvoice.py tts "Hello, this is a test." -o test.mp3

# Chinese text
python mmvoice.py tts "你好，这是一个测试。" -o test_cn.mp3

# Specify a different voice by "-v voice_id"
python mmvoice.py tts "Hello world" -v female-shaonv -o hello.mp3

# Specify output path
python mmvoice.py tts "Your text" -o /path/to/output.mp3
```

**Required parameters:**
- `text`: The text you want to convert to speech
- `-o OUTPUT`: Output audio file path (required)

**Optional parameters:**
- `-v VOICE_ID`: Voice to use (default: male-qn-qingse)


### Usage Details

**Text length limits:**
- Up to 10,000 characters per request
- For longer text, split into multiple requests and merge later

**Pause insertion:** Use `<#x#>` where x = pause duration in seconds
- Example: `"Hello<#1.5#>world"` = 1.5 second pause between words
- Range: 0.01 to 99.99 seconds

**Emotion matching:** speech-2.8 models automatically match emotions to your text content



## Voice Selection

Choose the right voice for your content by consulting the voice catalog:

```bash
# List all available voices
python mmvoice.py list-voices
```

**Voice catalog:** `reference/voice_catalog.md`

Contains:
- All available system voices (male, female)
- Voice characteristics and recommended use cases
- How to select the right voice for your content


## Advanced Op...

搜索