Minimax Tts Gyh

MiniMax TTS 文字转语音模型，支持 speech-02/speech-01 系列，生成高质量语音。使用 MINIMAX_API_KEY 环境变量。

Security Scan

The skill is a straightforward MiniMax TTS client and mostly behaves as described, but the package metadata fails to declare the required MINIMAX_API_KEY (and there is a small owner/slug mismatch), which is an incoherence you should resolve before trusting the skill.

Purpose & Capability

The script and SKILL.md both require a MINIMAX_API_KEY and call a MiniMax API host (https://api.minimaxi.com), which is coherent with a TTS client. However the registry/metadata lists no required environment variables or primary credential — an explicit omission that contradicts the code and instructions. _meta.json_ ownerId ('gyh') does not match the registry owner ID, which may indicate packaging/copy issues.

Instruction Scope

Runtime instructions and the included script stay inside the TTS use case: they require Python+requests, call the MiniMax API endpoints, poll async tasks, download returned audio, and write an output file. The SKILL.md does not instruct reading unrelated files or exfiltrating data beyond the TTS API.

Install Mechanism

No install spec is provided (instruction-only plus a bundled script). There are no remote downloads or archive extracts in the install metadata. The only runtime dependency is the Python requests package, which the README suggests installing with pip.

Credentials

The code requires the MINIMAX_API_KEY environment variable, but the skill metadata claims no required env vars or primary credential. Requesting an API key is expected for this purpose, but the metadata omission is misleading and could cause accidental missing prompts or credential misuse. No other unrelated credentials are requested.

Persistence & Privilege

The skill does not request persistent or elevated platform privileges (always:false). It only writes audio output files to the path the user supplies; it does not modify other skills or system-wide configuration.

What to consider before installing

This appears to be a normal client for a MiniMax TTS API, but before installing: 1) do not provide sensitive or broad credentials — the script only needs a service-specific MINIMAX_API_KEY, so use a limited-scope key or test key; 2) confirm the API host (https://api.minimaxi.com) is the official vendor and acceptable for your data; 3) ask the publisher to fix the metadata to declare MINIMAX_API_KEY as a required credential and to resolve the owner/slug mismatch; 4) inspect the script (already included) and, if possible, run it in a sandbox or with non-production credentials; 5) be aware the script will write files to the specified output path and will follow a download_url returned by the API (so a compromised API could cause the client to fetch from other hosts). If the metadata is corrected and the API host verified, the skill becomes coherent and lower risk.

MiniMax TTS 文字转语音

使用 MiniMax TTS API 将文本转换为语音。

支持的模型

模型	说明
speech-02-hd	高清语音，情感丰富
speech-02-turbo	高速语音
speech-01-hd	标准高清
speech-01-turbo	标准高速

前置要求

• Python 3
• pip3 install requests
• 设置环境变量 MINIMAX_API_KEY

使用方法

# 基本语音生成
python3 {baseDir}/scripts/tts.py --text "你好，欢迎使用MiniMax语音合成" --output hello.mp3

# 指定模型和声音
python3 {baseDir}/scripts/tts.py \
  --model speech-02-hd \
  --text "今天天气真不错" \
  --voice_id female_healthy \
  --output weather.mp3

# 英文语音
python3 {baseDir}/scripts/tts.py \
  --model speech-02-hd \
  --text "Hello, this is a test of MiniMax text to speech" \
  --voice_id male_tianmei \
  --output hello.mp3

参数说明

参数	说明	默认值
--model	模型名称	speech-02-hd
--text	要转换的文本	-
--voice_id	声音 ID	female_tianmei
--speed	语速 (0.5-2.0)	1.0
--pitch	音调调整	0
--volume	音量 (0.5-2.0)	1.0
--emotion	情感风格	neutral
--language	语言	auto
--output	输出文件路径	output.mp3