MiniMax-AI/cli

Generate text, images, video, speech, and music by MiniMax.

What it solves

This project provides a command-line interface (CLI) for the MiniMax AI Platform, allowing users and AI agents to interact with a wide range of generative AI capabilities—including text, image, video, speech, and vision—directly from a terminal or integrated into agentic workflows.

How it works

The CLI acts as a bridge between the user's terminal and the MiniMax API. It supports dual-region authentication (Global and CN) via OAuth or API keys. Once authenticated, users can execute specific commands to trigger different AI modalities:

  • Text: Handles multi-turn chat, streaming, and JSON output.
  • Image: Generates images from text prompts with controls for aspect ratio and batching.
  • Video: Manages asynchronous video generation (including the MiniMax-H3 model) with progress tracking and download capabilities.
  • Vision: Performs image understanding and description.
  • Speech: Provides text-to-speech (TTS) synthesis with various voices and speech-to-text (ASR) transcription into formats like JSON, SRT, and VTT.
  • Search: Executes web searches powered by MiniMax.

Who it’s for

  • Developers: Those who want to integrate MiniMax AI capabilities into scripts, CI/CD pipelines, or terminal-based workflows.
  • AI Agent Creators: Developers building agents (e.g., using Claude Code, Cursor) who need a standardized way to add AI skills to their agents.
  • Power Users: Individuals who prefer the terminal over a web interface for generating media and text.

Highlights

  • Multimodal Capabilities: Single tool for text, image, video, audio, and vision.
  • Agent Integration: Dedicated mmx agent setup command to configure MiniMax for popular AI agents like Claude Code and Codex.
  • Dual-Region Support: Seamless switching between Global and CN platforms.
  • Flexible Authentication: Supports both OAuth (RFC 8628) and API keys.
  • Comprehensive Speech Tools: Includes both synthesis and transcription with multiple output formats.

Related

  • Project
    vercel-labs/ai-cli

    A tiny, agent-native CLI for generating text, images, video, and audio using the Vercel AI SDK and AI Gateway for unified model access.

  • Project
    MiniMax-AI/minimax-code

    A terminal-based AI coding assistant that turns prompts into working software by editing code, running shell commands, and verifying tests.

  • Project
    MiniMax-AI/MiniMax-MCP

    An official Model Context Protocol (MCP) server that enables AI clients like Claude and Cursor to generate speech, clone voices, and create images and videos using MiniMax APIs.

  • Project
    flatkey-ai/flatkey-cli

    A unified command-line interface for generating images, videos, audio, and text via a single credit balance, designed for media teams and AI agent automation.

  • Project
    lessweb/deepcode-cli

    Deep Code CLI is a terminal AI coding assistant tuned for DeepSeek models. Install via npm, configure with a JSON file, and use slash commands or custom “skills” to get code suggestions, run multimodal queries, integrate external services (MCP), and control permissions. It shares settings with a VS Code extension and is MIT‑licensed.