llms.txt
# Muse Video
> Muse Video is an AI video generation model introduced by Meta Superintelligence Labs, designed to create high-quality videos with native audio from detailed prompts.
Muse Video focuses on prompt adherence, visual fidelity, temporal consistency, and native audio generation. It interprets creative direction for subjects, actions, camera movement, atmosphere, dialogue, ambience, and sound effects to produce coherent video sequences. The MuseVideo website provides a creation workspace where users can explore Muse Video information and generate videos or images with available AI models.
Official website: https://musevideo.io
## What Muse Video Offers
- Text-to-video: Describe a subject, action, setting, camera movement, lighting, mood, dialogue, ambience, or sound direction to create a video.
- Image-to-video: Upload a reference image and animate it with model-supported motion, framing, timing, and format controls.
- AI image generation and editing: Create or edit images with supported image models, aspect ratios, resolutions, and quality settings.
- Multiple AI models: Compare supported video and image models and select the model that fits the intended result.
- Creative workspace: Keep prompts and generated assets together for iteration and reuse.
- Flexible output settings: Choose model-dependent aspect ratio, duration, resolution, and audio options when available.
## Typical Uses
Muse Video can be used for cinematic scenes, short-form social videos, product concepts, advertisements, campaign drafts, visual storytelling, previsualization, motion studies, and animated visual experiments.
## How to Create a Video
1. Enter a detailed prompt describing the subject, scene, style, motion, camera direction, sound, and intended duration.
2. Optionally upload a reference image for an image-to-video workflow.
3. Select an available model and review its supported settings.
4. Generate the video, review motion and reference consistency, and export the preferred result.
## Muse Video Model Information
Meta Superintelligence Labs previewed Muse Video on July 7, 2026. Meta identified native audio, prompt adherence, visual fidelity, and temporal consistency as core areas of focus. The model is designed to generate video and sound from the same creative instruction. Final public specifications for duration, resolution, pricing, and availability may change as Meta continues developing the model.
## Key Pages
- [MuseVideo Home](https://musevideo.io/): Overview, examples, capabilities, workflow, use cases, and frequently asked questions.
- [AI Video Generator](https://musevideo.io/ai-video): Create videos from text prompts or reference images with supported AI video models.
- [AI Image Generator](https://musevideo.io/ai-image): Generate and edit images with supported AI image models.
- [AI Models](https://musevideo.io/ai-model): Explore the available video and image model catalog.
- [Pricing](https://musevideo.io/pricing): Compare current plans, credits, billing options, and included features.
- [Privacy Policy](https://musevideo.io/privacy-policy): Learn how MuseVideo handles data and third-party services.
- [Terms of Service](https://musevideo.io/terms-of-service): Review service rules, model-provider dependencies, and output considerations.
## Important Usage Notes
- Commercial-use rights depend on the selected model, provider terms, MuseVideo plan, source material, and applicable law.
- Users must have permission to upload or use people, brands, music, artwork, and other protected material.
- For current model settings, availability, credit costs, and limits, consult the generator and pricing pages rather than relying on fixed values in third-party summaries.
## Contact
- Support: support@musevideo.io
