OpenParable
Skip to content
← Back to skills

CLI Anything Minimax

Apps & Automation
cli-anything-minimax

CLI Anything Minimax is an Agent Skill for apps & automation published in the HKUDS/CLI-Anything repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Command-line interface for MiniMax AI — chat (MiniMax-M3) and TTS (speech-2.8-hd) via the MiniMax API.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/HKUDS/CLI-Anything/blob/HEAD/skills/cli-anything-minimax/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/cli-anything-minimax, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

cli-anything-minimax

A CLI harness for MiniMax AI — providing chat completions and text-to-speech synthesis through the MiniMax API.

Installation

pip install git+https://github.com/HKUDS/CLI-Anything.git#subdirectory=minimax/agent-harness

Prerequisites:

Usage

Basic Commands

# Show help
cli-anything-minimax --help

# Start interactive REPL
cli-anything-minimax

# Chat with MiniMax-M3
cli-anything-minimax chat --prompt "What is AI?"

# High-speed model
cli-anything-minimax chat --prompt "Quick answer" --model MiniMax-M2.7-highspeed

# 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"

TTS options

--text (required) / --model / --voice / --output plus voice and audio controls: --speed (0.5..2.0), --vol (0..10), --pitch (-12..12), --sample-rate (8k/16k/22.05k/24k/32k/44.1k), --bitrate (32k/64k/128k/256k), --format (mp3/pcm/flac), --channel (1/2). See tts --help for defaults.

Command Groups

Chat

CommandDescription
chatChat with MiniMax LLM
streamStream chat completion

TTS

CommandDescription
ttsSynthesize text to speech (hex-decoded MP3 via SSE)
voicesList available voice IDs

Session

CommandDescription
session statusShow session status
session clearClear session history
session historyShow command history

Config

CommandDescription
config setSet a configuration value
config getGet a configuration value (or show all)
config deleteDelete a configuration value
config pathShow the config file path

Utility

CommandDescription
testTest API connectivity
modelsList chat models
models --ttsList TTS models

Examples

Configure API Key

export MINIMAX_API_KEY="your-api-key"
# or
cli-anything-minimax config set api_key "your-api-key"

Chat

cli-anything-minimax chat --prompt "Explain quantum computing"
cli-anything-minimax stream --prompt "Write a Python quicksort"

TTS

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

Chat Models

Model IDDescription
MiniMax-M3Next-generation flagship model (default)
MiniMax-M2.7Peak Performance. Ultimate Value.
MiniMax-M2.7-highspeedSame performance, faster and more agile

TTS Models

Model IDDescription
speech-2.8-hdHigh-definition TTS (default)
speech-2.8-turboFast TTS

For AI Agents

  1. Always use --json flag for parseable output
  2. Check return codes — 0 for success, non-zero for errors
  3. Parse stderr for error messages on failure
  4. Use absolute paths for TTS output files

Version

1.0.0