菜单
Command-line interface for MiniMax AI — chat (MiniMax-M3, MiniMax-M2.7) and speech-2.x TTS via the MiniMax API.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/HKUDS/CLI-Anything --skill cli-anything-minimax命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
基于 SOC 职业分类
正在显示 SKILL.md
| name | cli-anything-minimax |
| description | Command-line interface for MiniMax AI — chat (MiniMax-M3, MiniMax-M2.7) and speech-2.x TTS via the MiniMax API. |
A CLI harness for MiniMax AI — providing chat completions and text-to-speech synthesis through the MiniMax API.
pip install git+https://github.com/HKUDS/CLI-Anything.git#subdirectory=minimax/agent-harness
Prerequisites:
# Show help
cli-anything-minimax --help
# Start interactive REPL
cli-anything-minimax
# Chat with MiniMax-M3
cli-anything-minimax chat --prompt "What is AI?"
# Alternate chat model
cli-anything-minimax chat --prompt "Quick answer" --model MiniMax-M2.7
# Stream chat response
cli-anything-minimax stream --prompt "Write a poem about code"
# Synthesize speech
cli-anything-minimax tts --text "Hello world" --output hello.mp3
# JSON output for agents
cli-anything-minimax --json chat --prompt "Hello"
--text (required) / --model / --voice / --output plus voice and audio
controls: --speed (0.5..2.0), (0..10), (-12..12),
(8k/16k/22.05k/24k/32k/44.1k), (32k/64k/128k/256k),
(mp3/pcm/flac), (1/2). See for defaults.
--vol--pitch--sample-rate--bitrate--format--channeltts --help| Command | Description |
|---|---|
chat | Chat with MiniMax LLM |
stream | Stream chat completion |
| Command | Description |
|---|---|
tts | Synthesize text to speech (hex-decoded MP3 via SSE) |
voices | List available voice IDs |
| Command | Description |
|---|---|
session status | Show session status |
session clear | Clear session history |
session history | Show command history |
| Command | Description |
|---|---|
config set | Set a configuration value |
config get | Get a configuration value (or show all) |
config delete | Delete a configuration value |
config path | Show the config file path |
| Command | Description |
|---|---|
test | Test API connectivity |
models | List chat models |
models --tts | List TTS models |
export MINIMAX_API_KEY="your-api-key"
# or
cli-anything-minimax config set api_key "your-api-key"
cli-anything-minimax chat --prompt "Explain quantum computing"
cli-anything-minimax stream --prompt "Write a Python quicksort"
cli-anything-minimax tts --text "Hello!" --output hello.mp3
cli-anything-minimax tts --text "Fast" --model speech-2.8-turbo --voice English_Insightful_Speaker --output fast.mp3
| Model ID | Description |
|---|---|
MiniMax-M3 | Next-generation flagship model (default) |
MiniMax-M2.7 | Peak Performance. Ultimate Value. |
| Model ID | Description |
|---|---|
speech-2.8-hd | High-definition TTS (default) |
speech-2.8-turbo | Fast TTS |
speech-2.6-hd | High-definition TTS |
speech-2.6-turbo | Fast TTS |
speech-02-hd | High-definition TTS |
speech-02-turbo | Fast TTS |
speech-01-hd | High-definition TTS |
speech-01-turbo | Fast TTS |
--json flag for parseable output1.0.0