skills.rest
HKUDS
HKUDSOFFICIAL
Explore all skills by this author →
WebsiteGitHub

cli-anything-minimax

Provides chat completions and text-to-speech synthesis through the MiniMax API.

48.8k|4.5k|Updated Mar 8, 2026
Search Tags:#api#CLI#text-to-speech#chat#tts#AI Agent#MiniMax
One-click install
npx skills add https://github.com/HKUDS/CLI-Anything --skill cli-anything-minimax
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cli-anything-minimax
Source: https://github.com/HKUDS/CLI-Anything/tree/main/minimax/agent-harness/cli_anything/minimax/skills
Command: npx skills add https://github.com/HKUDS/CLI-Anything --skill cli-anything-minimax

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI agents and developers need a scriptable, JSON-friendly way to call MiniMax chat models (MiniMax-M3, MiniMax-M2.7) and speech-2.x TTS models without writing custom API integration code.

Core Features & Use Cases

  • Chat & Streaming: Send prompts to MiniMax-M3 or MiniMax-M2.7 with one-shot or streaming responses, plus session history management.
  • Text-to-Speech: Synthesize speech with control over voice, speed, volume, pitch, sample rate, bitrate, format (mp3/pcm/flac), and channel.
  • Agent-Friendly Output: A --json flag, return codes, and stderr error reporting make the CLI parseable by AI agents.
  • Use Case: An agent generates a spoken audio briefing by chatting with MiniMax-M3 for the script, then running tts to produce an MP3 file.

Quick Start

Set your MiniMax API key with config set api_key or the MINIMAX_API_KEY environment variable, then ask the agent to run a chat prompt or synthesize text to an MP3 file.

Frequently Asked Questions about cli-anything-minimax

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I use the MiniMax API from the command line?▼

Install the CLI with pip from the GitHub repository, set your MiniMax API key via the MINIMAX_API_KEY environment variable or `config set api_key`, then run `cli-anything-minimax chat --prompt "your question"` to get a response.

How do I convert text to speech with MiniMax TTS models?▼

Run `cli-anything-minimax tts --text "Hello" --output hello.mp3` to synthesize speech. You can choose models like speech-2.8-hd or speech-2.8-turbo and adjust voice, speed, pitch, sample rate, bitrate, and format (mp3, pcm, or flac).

What chat models does MiniMax support in this CLI?▼

The CLI supports MiniMax-M3 as the default flagship model and MiniMax-M2.7 as an alternative. Use the `--model` flag on the chat command or run `cli-anything-minimax models` to list available options.

Can AI agents parse the CLI output programmatically?▼

Yes, pass the `--json` flag before any command to get structured JSON output. The CLI returns exit code 0 on success and non-zero on failure, with error messages written to stderr for agent error handling.

Why does the MiniMax CLI fail with authentication errors?▼

Authentication fails when no API key is configured. Set the MINIMAX_API_KEY environment variable or run `cli-anything-minimax config set api_key "your-key"` with a key from platform.minimax.io, then verify with the `test` command.

Related Skills

Explore More Software Engineering Skills→
jymchngjymchng

config-injection

Inject configuration from environment variables or config files during application initialization.

Community
Intermediate
refly-airefly-ai
199

fal-audio

Generate MP3 or WAV audio from text using Fal.ai models.

Official
Intermediate
deepgramdeepgram
23

openai-whisper-api

Convert audio files to text using the OpenAI Whisper API.

Official
Intermediate
cascade-protocolcascade-protocol
14

agentbox-inference

Generate chat completions via an OpenAI-compatible API with USDC micropayments.

Official
Intermediate