// AI NEWS · AI VIDEO

Meta Previews Muse Video, Its First In-House AI Video Model, With Native Audio — but Ships It as a Preview, Not a Product

Alongside Muse Image, Meta Superintelligence Labs showed Muse Video: text-to-video with a soundtrack generated from the same prompt. It ranks near the top of the text-to-video leaderboard, but it's 'coming soon,' not live.

KompozyTurn one idea into a week of content — across every platform, published for you.
Get Started →

2026-07-08 · by Moe Ameen

What happened

On July 7, 2026, Meta previewed Muse Video, its first in-house AI video generation model, alongside the launch of Muse Image. Both are the first media-generation models from Meta Superintelligence Labs (MSL), the group led by Alexandr Wang. Muse Video is built on the same pretraining base as Muse Image, and its headline capability is native audio — it generates the soundtrack together with the picture from a single text prompt, rather than producing a silent clip you score afterward.

The rollout split the two models. Muse Image shipped to real users the same day, across Meta AI, WhatsApp, and Instagram. Muse Video did not: Meta showed sample generations to demonstrate where its video quality stands and said the model is "coming soon to creators and Meta AI," without committing to a release date. At preview, Meta reported Muse Video ranking around #3 on the Arena human-preference leaderboard for text-to-video, behind the leading entries from OpenAI and Google.

Meta was candid about the gaps. It flagged two areas it is still refining: audio-video synchronization, and physically accurate fast motion — the weak spots most current text-to-video models share. It published no resolution, clip length, or pricing; those details are expected when the model opens to creators. Treat every figure here as a preview-window snapshot and confirm it against Meta's own announcement before relying on it.

Why it matters for creators

  • Native audio is the notable part: one prompt yields a clip that already has sound, collapsing a step most video generators leave to a separate scoring pass.
  • It's a preview, not a tool. You can't log in and generate today — Meta showed samples and said access is 'coming soon,' so there's nothing to add to a workflow yet.
  • Even when it lands, it makes one clip inside Meta. No captioning for other feeds, no reframing per platform, no clipping long video, no carousels, blogs, or scheduling.
  • Ranking near the top of the text-to-video leaderboard signals Meta is now a serious video-model player — creators should expect it inside Instagram and Meta AI, not as a standalone editor.
  • The honest read: Muse Video is raw generation capability, months of product work away from being a content operation — the gap between 'a clip with sound' and 'a week of on-brand posts' is exactly where a creator's real work lives.

How to act on this with Kompozy

The catch with acting on this news is that there's nothing to act on inside Meta yet — Muse Video is a preview, "coming soon," with no login. That makes the smart move two-fold. First, the story itself is publishable content this week: with Kompozy you turn "Meta just previewed an AI video model with built-in audio" into an explainer Blog Article, a comparison Carousel against the models that beat it, native Text Posts for X and LinkedIn, and a short — the whole set drafted in your voice via the Persona Brief and scheduled across all nine platforms plus blog and email from one queue, while the topic is fresh and search interest is spiking.

Second, don't wait on Meta to have a video engine. The thing Muse Video will eventually be — a way to make video from a prompt — Kompozy already ships in a form Meta can't match: HeyGen-driven Persona Shorts, Persona Frames, and Marketing Shorts built on a face-locked AI Influencer persona you own, so your channel has a consistent presenter every week, plus Clipped Shorts, Listicle and Naturalistic Video, and auto-captioned reframing per platform. When Muse Video does open, the workflow is ready: generate a clip in Meta AI, bring it into Kompozy, auto-caption and reframe it, fan it into carousels, quote graphics, text, and a newsletter, and publish everywhere. Meta previews a model; Kompozy is the content engine that turns any video — theirs or its own — into posts across every platform, today.

Quick takeaways

  • Muse Video previewed July 7, 2026 — Meta's first in-house AI video model, from Meta Superintelligence Labs, built on the same base as Muse Image.
  • Headline feature: native audio — the soundtrack is generated with the picture from one text prompt.
  • It's a preview, not a public product: 'coming soon to creators and Meta AI,' with no release date, resolution, length, or pricing published.
  • At preview it ranked around #3 on the Arena text-to-video leaderboard; Meta flagged gaps in audio-video sync and fast motion.
  • You can't use it yet — so publish the story now with Kompozy, and use Kompozy's persona video for the video output Meta only previewed.

Frequently asked questions

What is Meta Muse Video?

Muse Video is Meta's first in-house AI video generation model, previewed July 7, 2026 by Meta Superintelligence Labs alongside Muse Image. It generates short video from a text prompt with native audio — the soundtrack is produced together with the picture. It was shown as an early preview, not released as a public product.

Can I use Muse Video now?

Not yet. Meta previewed it on July 7, 2026 to demonstrate its video quality and said access is 'coming soon to creators and Meta AI,' without a firm date. Muse Image launched to users the same day, but Muse Video did not.

Does Muse Video generate audio?

Yes — native audio is its headline feature. Muse Video generates a soundtrack alongside the picture from a single prompt, instead of producing a silent clip. Meta has said audio-video synchronization is one of the areas it is still refining.

What can creators do about Muse Video today?

Because it isn't live, the move is to publish the news while it's fresh and to use a video engine that already works. Kompozy turns the announcement into a blog, carousel, and posts across nine platforms, and generates persona/avatar video, clipped shorts, and listicle video now — so you're not waiting on Meta for video output.

Related news

← All AI news · Get started →