MiniMax Multimedia Generation Toolkit
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_6f64fcbc/minimax-multimedia-generate.
About this skill
Problem
When turning copy into TTS, audiobooks, music BGM, images, or short video, manually stitching MiniMax API calls with ffmpeg repeats the same output paths, segment splits, and media cleanup. This skill packages those operations into bash scripts that run against MINIMAX_API_KEY and MINIMAX_API_HOST.
How it works
- Voice: single text calls are used by default; multi-character or long text writes
segments.json, then generates per-segment audio and merges with crossfade. - Music: background music for video or podcasts defaults to instrumental; explicit song creation asks for pure music or lyrics.
- Images: text-to-image is the default, while a character reference photo switches to image-to-image; aspect ratios follow avatar, wallpaper, or poster context.
- Video: supports text-to-video, image-to-video, subject reference, and long-video chains; output goes to
minimax-output/. - Media tools: uses
ffmpegfor conversion, concatenation, trimming, and extraction.
Boundaries
It covers only MiniMax-supported capabilities and user plan quotas. Video is often 768P and counted in 6-second units, so confirm quota before generating. No Python is required, but curl, jq, xxd, ffmpeg, and valid API configuration are needed.
Use Cases
- Produce podcast narration and character dialogue from a script, split into `segments.json`, then merge one audio file.
- Create 768P 6-second text-to-video or image-to-video clips for a product promo and export them to a target directory.
- Generate same-character cover images from a reference portrait and select poster or phone-wallpaper aspect ratios.
- Run FFmpeg-based scripts to transcode, concatenate, trim, and extract multi-segment audio or video.
Best For
- Audiobook or podcast editors who need narrator and character dialogue separated and merged into one audio track.
- Content operators or video creators who need instrumental BGM, cover images, and short video clips.
- Automation or frontend engineers who need MiniMax API calls via bash, curl, and ffmpeg instead of Python.
- Product demonstrators who need character-reference images that keep the same person across aspect ratios.
Related Skills
A ComfyUI image-generation skill that uses a five-step dialog to collect prompts, prefill templates, confirm parameters, submit API jobs, and return results.
A design-system guidance skill for Impeccable that produces token-based rules, component states, accessibility criteria, and QA checklists.
Director-level video lapian that diagnoses material precision, then produces frame evidence, director analysis, a style bible, and a showcase video.
Plan and brief Amazon MAIN, Listing, and A+ image sets from verified product facts, then return plan and image QA status.