Native audio
Meta highlights sound generated as part of the video model.
GPT Image 2 is live — sharper edits, cleaner text, up to 4K
Meta Muse Video
A summary of what Meta has said about Muse Video so far, plus the video models you can generate with in the studio today.
AI Model 3 credits
Prompt0/2000
Avoid copyrighted characters, logos, music and sensitive or explicit content — it may be blocked.
Resolution
Aspect Ratio
Batch generation1
Estimated cost: 3 credits
Your creation appears here
Pick a model, describe the shot, and hit Generate.
Why Muse Video
Why creators choose Muse Video
A summary of what Meta has published about Muse Video, and where to generate video today.
Arena ranking
Meta cites a No. 3 text-to-video ranking on Arena as of July 5, 2026.
Shared foundation
Built on the same pretraining base as Muse Image.
Preview status
Meta lists it as coming soon, with no release date given.
Meta Muse Video guide
What Meta has said about Muse Video
Meta Muse Video is the video generation model from Meta Superintelligence Labs, previewed on July 7, 2026 alongside Muse Image. This page summarizes what Meta has published so far, and explains how it relates to the Muse Video generator in the GPTImagine 2 studio.
What Meta announced
Meta describes Muse Video as an early preview built on the same pretraining base as Muse Image. Its announcement highlights visual fidelity with native audio support, and says the model is competitive on prompt adherence, visual fidelity, and temporal consistency. Meta reported it ranking third in human-preference Elo for text to video on the Arena leaderboard as of July 5, 2026.
Meta has not published resolutions, clip lengths, aspect ratios, or supported inputs, and says Muse Video is coming soon to creators and Meta AI, with no release date.
Native audio
Sound is part of the model rather than an add-on.
Same base as Muse Image
Built on a shared pretraining base.
Early preview
Availability and specifications are still to come from Meta.
Known gaps Meta points to
Meta says it is still investing in audio-video synchronization and physically accurate fast motion, and that its Content Seal watermarking is planned to extend to video. When you test any video model, including this one, pay particular attention to lip and sound timing and to quick movement.
How this page relates to the studio
GPTImagine 2 is an independent product and is not affiliated with Meta. The Muse Video generator in the studio is a separate video tool for text to video, image to video, and reference to video. Specifications for it are listed on its own page rather than inferred from Meta’s announcement. For other models, see the individual pages for Seedance, Veo, Wan, Kling, and MiniMax.
How to use Muse Video
How to use Muse Video in three steps
Start with Meta’s post for the official claims and stated limits.
00:0000:1500:30
Who uses Muse Video
Who uses Muse Video for video work
Filmmakers
Tracking where AI video with native audio is heading.
Marketers
Planning for new generation tools.
Product teams
Evaluating video models for brand content.
AI enthusiasts
Following new model releases.
More models
Muse Video and every other model in one studio
Switch engines without switching tools — GPT Image 2 plus the strongest public image and video models, side by side in the GPTImagine 2 studio.
Multi-reference editingCharacter consistencyText rendering1K–4K outputConversational editsStyle transferVideo generationBatch runs
Muse VideoNewFlagship multimodal video with native audio
Seedance 2.5HotMulti-reference Seedance with native audioSeedance 2.0Previous-gen Seedance up to 4KSeedance 2.0 FastFastFastest Seedance tier for drafts
MiniMax H3Fast text/image to video up to 2KMiniMax H3 MaxHotReference-driven video consistency
Veo 3.1Google’s cinematic drafting engine
Wan 3.0Flexible duration and adaptive framing
Kling 3.0Dramatic motion from a single prompt
GPT Image 2.5NewSharp text and precise edits to 4KGPT Image 2Versatile image generation to 4KNano Banana 2.1NewFast drafts and precise edits to 4KNano Banana ProHotHigh-fidelity image output to 4KNano Banana 2Fast drafts and conversational editsNano Banana 2 LiteFastLightweight tier for quick, low-cost draftsFAQ
Muse Video FAQ
What is Meta Muse Video?
Muse Video is the video generation model from Meta Superintelligence Labs, previewed on July 7, 2026 alongside Muse Image. Meta describes it as built on the same pretraining base as Muse Image, with native audio support.
Is Meta Muse Video available yet?
Meta says it is coming soon to creators and Meta AI, and has not given a release date. It has also not published resolutions, clip lengths, or supported inputs.
How does Meta say Muse Video performs?
Meta reports it ranking third for text to video in human-preference Elo on the Arena leaderboard as of July 5, 2026, and says it is still improving audio-video synchronization and physically accurate fast motion.
Is GPTImagine 2 affiliated with Meta?
No. GPTImagine 2 is an independent product. The Muse Video generator in the studio is a separate tool, and its specifications are listed on its own page.