skills.rest
poco-ai
poco-aiOFFICIAL
Explore all skills by this author →
GitHub

minimax-multimodal-toolkit

Orchestrate speech, image, and video generation via MiniMax APIs and CLI scripts.

1.3k|126|Updated Jan 8, 2026
Search Tags:#workflow#api#multimodal#ffmpeg#image-generation#tts#video-generation
One-click install
npx skills add https://github.com/poco-ai/poco-claw --skill minimax-multimodal-toolkit-poco-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: minimax-multimodal-toolkit
Source: https://github.com/poco-ai/poco-claw/tree/main/backend/assets/skills/minimax-multimodal-toolkit
Command: npx skills add https://github.com/poco-ai/poco-claw --skill minimax-multimodal-toolkit-poco-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires ffmpeg, curl, jq, xxd, base64, file, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

MiniMax multimodal toolkit orchestrates generation of speech, images, and video by unifying TTS, image/video generation, and media tooling under a single command-line workflow, enabling developers to automate complex multimedia tasks and integrate AI-driven media into apps and pipelines.

Core Features & Use Cases

  • Centralized control over TTS (voice synthesis, cloning, design), image generation (text-to-image, image-to-image with a character reference), and video generation (text-to-video, image-to-video, start-end frame, long-form multi-scene) plus media tooling (convert, trim, concat, extract).
  • Bundled with script-based orchestration, environment checks, quota awareness, and template-driven video prompts for rapid iteration.
  • Use cases include building autonomous content generation pipelines, creating branded media assets, and automating multimedia QA and archival workflows for apps and services.

Quick Start

Place all generated outputs in minimax-output and run the appropriate scripts from your working directory to begin generating content.

Frequently Asked Questions about minimax-multimodal-toolkit

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

FAQPage Schema
How do I automate text-to-speech and image generation in a single workflow?▼

Automate text-to-speech and image generation in a single workflow by running bundled CLI scripts that orchestrate MiniMax APIs for voice synthesis and visual creation, placing all outputs in a designated directory.

What do I need to generate video from text using MiniMax APIs?▼

To generate video from text using MiniMax APIs, you need valid API keys, endpoint access, and local dependencies including curl, ffmpeg, jq, and base64 to execute the orchestration scripts reliably.

Can I use ffmpeg to trim and concatenate generated long-form video outputs?▼

Yes, you can use ffmpeg to trim and concatenate generated long-form video outputs, as the toolkit includes media tooling for converting, trimming, concatenating, and extracting media within your pipeline.

What is the best way to manage multimedia generation pipelines for autonomous content creation?▼

The best way to manage multimedia generation pipelines is using a centralized command-line toolkit that applies template-driven video prompts, quota awareness, and environment checks for rapid iteration and automated content creation.

Does this multimodal toolkit support image-to-image generation with a character reference?▼

Yes, the multimodal toolkit supports image-to-image generation with a character reference, alongside text-to-image, text-to-video, and start-end frame video generation for comprehensive media asset creation.

Related Skills

Explore More Software Engineering Skills→
JuanMS20JuanMS20

github-auth

Configure GitHub authentication for Hermes Agent using git, gh CLI, or SSH credentials.

Community
Intermediate
curiositechcuriositech
181

video-processing-editing

Automate video editing tasks with FFmpeg, including cutting, trimming, and batch processing.

Official
Advanced
HappyHackingSpaceHappyHackingSpace
4

funurl

Parse, modify, encode, decode, and deduplicate URLs from the command line.

Official
Intermediate
thompson0012thompson0012
28

media

Generate images, videos, transcripts, and speech via harness CLI media commands.

Community
Advanced