Skip to content
Get packs

MiniMax AI CLI

Lets an agent chat with MiniMax models and generate speech audio via the MiniMax API

Source Download skill
Repository
HKUDS/CLI-Anything
Stars
58,084
Licence
Apache-2.0
Files
1 file

What it does

This skill teaches an agent to drive a command-line tool that connects to MiniMax AI, a hosted AI service. Once installed, the agent can send chat prompts to MiniMax models, stream responses, and convert text into MP3, FLAC or PCM speech audio with selectable voices. It also manages a local config file and session history, and can test API connectivity.

Great for

  • Developers who already have a MiniMax API key and want to script chat or text-to-speech from the terminal
  • Creators who need quick voiceovers generated from text files through an agent
  • Teams evaluating MiniMax models alongside other LLM providers

Skip it if

  • People without a MiniMax account or API key, since every call requires one and billing applies to the provider's account
  • Sensitive or confidential text, because prompts and text are sent to a third-party cloud service
  • Offline work, since the tool needs internet access to reach the MiniMax API

Try asking

  • “Chat with MiniMax-M3 about a technical question and return the answer as JSON”
  • “Turn this paragraph into an MP3 voiceover using a English voice and fast model”
  • “Stream a Python quicksort explanation from MiniMax-M2.7”
  • “List the available TTS voices and models before generating audio”
Step-by-step guide: how to use MiniMax AI CLIInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the Apache-2.0 licence and an attribution note.

    cli-anything-minimax.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip cli-anything-minimax.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip cli-anything-minimax.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Set the API key with the MINIMAX_API_KEY environment variable rather than storing it in the config file or chat history
  • Use the --json flag so the agent can parse output reliably, and use absolute paths for TTS output files
  • Run tts --help to check voice, speed, pitch and format defaults before generating audio

What's inside

  • SKILL.md

Redistributed unmodified from HKUDS/CLI-Anything under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.