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 access a wide range of generative AI capabilities directly from the terminal or as a skill for other agents (like Cursor or Claude Code).

How it works

The CLI acts as a bridge to the MiniMax AI Platform APIs, supporting both Global and China-based regions. It handles authentication via OAuth or API keys and provides specific commands for different modalities:

  • Text: Multi-turn chat, streaming, and JSON output.
  • Image: Text-to-image generation with batch and aspect ratio controls.
  • Video: Asynchronous video generation with progress tracking and support for reference images/videos.
  • Speech: Text-to-speech (TTS) with various voices and speed controls.
  • Vision: Image understanding and description.
  • Search: Web search capabilities powered by MiniMax.

Who it’s for

  • Developers who want to integrate AI capabilities into their terminal workflows or CI/CD pipelines.
  • AI Agent creators who want to add MiniMax's multimodal capabilities as a skill to their agents.
  • Power users who prefer command-line interactions over a web interface.

Highlights

  • Multimodal Support: Single tool for text, image, video, speech, and vision.
  • Agent-Ready: Specifically designed to be added as a skill to AI agents.
  • Dual Region Support: Seamlessly switches between Global and CN platforms.
  • Flexible Authentication: Supports both OAuth (RFC 8628) and API keys.
  • Developer-Friendly: Includes streaming playback for speech and JSON output for text/search results.

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
    SamurAIGPT/muapi-cli

    A command-line interface for muapi.ai that allows users and AI agents to generate images, videos, and audio using various generative AI models.

  • Project
    flatkey-ai/flatkey-cli

    A command-line interface for unified multimodal AI generation, allowing media teams and AI agents to generate images, videos, audio, and text through a single API key and credit balance.

  • 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
    higgsfield-ai/cli

    A command-line interface for the Higgsfield AI platform that enables the generation of images, videos, 3D assets, and audio using 40+ models, alongside tools for training custom characters and deploying AI websites.