// AI TOOLS · MINIMAX HUB

MiniMax Hub

MiniMax's all-in-one AI video generator — image, video, voiceover, music, and editing in one agent-driven, human-in-the-loop workspace.

Last verified · 2026-09-25 · by Moe Ameen

What MiniMax Hub is

MiniMax Hub is an all-in-one AI video generator from MiniMax, the Shanghai AI company behind the Hailuo video line and the Talkie app. It was unveiled on June 15, 2026 at the Shanghai International Film Festival. Where most AI video tools do one job and export a file you carry into the next app, Hub consolidates the whole production pipeline — image creation, video generation, voiceover, music, and video editing — into a single connected workspace so assets flow from step to step without export-and-reimport.

The way you drive it is agent-first. You give Hub a goal in plain language, or drop in a PDF proposal, a reference video, or an asset pack, and an AI agent interprets the brief, breaks it into tasks, selects the right model for each, executes, and checks the result. MiniMax built it around human oversight rather than automation: Xu Lüyang, from MiniMax's product operations team, said the agent "shouldn't be a black box, one-click generator" and instead pauses "at every critical decision point for your confirmation." The stated principle is that creative direction and aesthetic judgment stay with the human while the AI carries the execution. Hub also includes "Skill" and "Memory" functions so it can learn your workflows and aesthetic preferences over time.

Under the hood it draws on MiniMax's Hailuo platform and a family of multimodal foundation models spanning text, audio, image, video, and music. Reporting describes it as a desktop app for macOS and Windows with a node-based canvas — a flow diagram whose nodes are the script, image, video, and audio steps and whose connections show how one output feeds the next — orchestrated by a director agent that routes work to specialized sub-agents running in parallel. The app is free to download; generations draw on Hailuo credits under MiniMax's usage-based pricing, with a free tier for experimentation.

The honest boundary: Hub is a creation studio, not a distribution engine. It takes you from brief to a finished piece and stops at export. It writes no per-platform caption, sizes nothing for a specific feed, builds no carousel, blog, or newsletter, keeps no recurring on-brand persona across a content week, and posts to nothing. Interface, pricing, and platform specifics are launch-window details for a fast-moving product — confirm the current feature set and credit costs on MiniMax's own site before quoting them. Note: MiniMax has since rebranded the app as "MiniMax Design" (hub.minimax.io now redirects to design.minimax.io) — this page covers the product as introduced under the Hub name.

What you can make with it

  • A finished short-form video from a plain-language brief, a PDF proposal, a reference video, or an asset pack, assembled across script, image, video, and audio in one workspace
  • Multi-shot pieces where image generation, video generation, voiceover, and music are produced and connected without leaving the app
  • AI voiceover and a synced music track generated alongside the visuals rather than sourced separately
  • Edited cuts inside the same canvas, with the AI pausing at each decision point for your confirmation
  • Repeatable, personalized outputs as its "Skill" and "Memory" functions learn your workflow and aesthetic

How Kompozy turns MiniMax Hub output into content

Hub is best understood as the front half of a pipeline: it consolidates *making* one polished piece — script, image, video, voice, music, edit — into a single supervised workspace, and it ends when you export. The friction it leaves behind is the same one every studio tool leaves: you now have one finished video and a full day of manual work turning it into posts. Kompozy is built for that back half. The clean split is that Hub gives you a supervised film; Kompozy turns that film into a supervised *content week* and ships it.

Start with the fact that Hub is agent-driven toward longer, multi-shot pieces — which makes clipping the natural first move. Drop a Hub export into [Kompozy](/) and its [Clipped Shorts](/glossary/clipped-short) pulls the strongest vertical cuts out of the long piece, then it burns in captions styled to your brand, reframes each cut to 9:16, 1:1, and 16:9, and layers hook text through brand-exact [HyperFrames](/glossary/hyperframes) so the muted first second actually reads on the feed. From that one Hub video Kompozy then fans a whole unit: a [Carousel Post](/glossary/hyperframes) breaking the story down slide by slide, [Quote Graphics](/glossary/output-buckets), native [Text Posts](/glossary/output-buckets), a [Blog Article](/glossary/content-repurposing), and an Email Newsletter — every one held to a single [Persona Brief](/glossary/persona-brief) and banned-word filter so the volume still sounds like you. It also generates what Hub can't: HeyGen avatar-driven [Persona Shorts](/glossary/persona-shorts) and [Persona Frames](/glossary/persona-frames) for a recurring on-camera identity across posts. Then [Autopilot](/glossary/autopilot) schedules and publishes the set across the eight social platforms plus blog and email from one queue, each piece passing a per-post review pipeline first. Make it in Hub; clip, multiply, and distribute it in Kompozy.

  1. Produce your piece in Hub — brief the agent, confirm each decision, and export the finished video.
  2. Bring the export into Kompozy and let Clipped Shorts pull vertical cuts from the long-form piece.
  3. Let Kompozy add branded captions, reframe each cut per platform, and layer hook text or overlays via HyperFrames.
  4. Fan the same idea into a carousel, quote card, native text posts, a blog draft, and a newsletter — all in your voice through the Persona Brief.
  5. Review each piece behind the per-post gate, then schedule and publish across TikTok, Reels, Shorts, X, LinkedIn, and more with Autopilot.

Frequently asked questions

What is MiniMax Hub?

MiniMax Hub is an all-in-one AI video generator that MiniMax launched on June 15, 2026 at the Shanghai International Film Festival. It unites image creation, video generation, voiceover, music, and editing in one agent-driven workspace, where an AI agent interprets your brief, breaks it into tasks, and executes — pausing at each creative decision point for your confirmation rather than one-click generating.

Is MiniMax Hub free?

Reporting describes Hub as a free-to-download desktop app for macOS and Windows, with generations metered against Hailuo credits under MiniMax's usage-based pricing and a free tier for experimentation. Because it is a new, fast-moving product, confirm the current pricing and credit costs on MiniMax's own site.

How is Hub different from Hailuo?

Hailuo is MiniMax's AI video generator — it produces a clip from a prompt or image. Hub is the workspace layer above it: it uses MiniMax's Hailuo platform and multimodal models but consolidates image, video, voice, music, and editing into one connected, agent-driven pipeline, so you build a finished multi-shot piece instead of a single clip.

Can MiniMax Hub publish videos to social media?

No. Hub takes you from brief to a finished video and stops at export. It does not caption in your brand voice, size per platform, build carousels or newsletters, keep a recurring persona, or schedule and publish. To turn a Hub video into finished posts across the eight social platforms plus blog and email, use a content engine like Kompozy.

Related tools

  • Hailuo AI Video Generator — MiniMax's AI video generator, known for physically believable motion and strong instruction following from text or a single image.
  • MiniMax H3 Video Model — MiniMax's open-weights, multimodal video model — 2K clips with native stereo audio, conditioned on up to 9 image, 3 video, and 3 audio references, priced to undercut the proprietary leaders.
  • CapCut — ByteDance's all-in-one editor, now an AI creation suite — generate video, images, and audio in the timeline with Seedance, Seedream, and Seedmusic.
  • HeyGen — AI avatar video platform that turns a text script into a talking-head video — in 175+ languages.

← All AI tools · Get started →