Your AI video workspace
Create the shot your story needs
Video Generation Studio plans and creates short AI videos from a written shot, an opening image, exact first and last frames, creative references, or footage you want to edit or continue. Each shot arrives as its own MP4 clip of 2 to 30 seconds in 16:9, 9:16, 1:1, 4:3, or 3:4, made on a video model that fits your input. Video Generation Studio works in Claude Code, Codex, Cursor, and other agents that run Skills.
Install Video Generation Studio and tell me when I need to sign in: https://beatra.ai/skills/video-generation-studio/install.md
For agents:Install guideMarkdown version
Send it to WorkBuddy, Codex, Claude Code, or another agent to install. Sign in once the first time you use it.GitHub ↗Docs ↗Use it on your phone: WeChat mini program
Short video with a clear job
Direction before creation
Clarify the action, camera, pacing, duration, and destination before creating the clip.
Use the right starting point
Begin with words, one opening image, exact boundary frames, creative references, or existing footage.
Revise with purpose
Review the delivered motion and choose one focused edit, extension, or new render.
How it is made
Decide what happens before creating
Start with the purpose of the clip, then settle the subject, action, camera, pacing, length, and frame.
Give one shot one clear job · Choose one readable action and camera move · Fit the clip to its destination
Words, images, references, or footage
Create a new shot, animate an opening image, move between boundary frames, follow creative references, change footage, or continue one clip.
Create from a written shot · Animate an image or connect two frames · Guide, edit, or continue video
Match the clip to an eligible video model
The available choice depends on the starting media, duration, frame, quality, and requested controls. A named model remains your choice when it fits the clip.
Match the model to the requested input · Keep a named compatible choice · Confirm model and input compatibility before creation
Watch the clip before choosing the next step
Check action, subject stability, camera, continuity, and destination fit. When audio was requested or returned, check that too, then change only what matters.
Compare the result with the direction · Report visible drift honestly · Choose one focused next step
For ads, product stories, social clips, and cinematic ideas
Product videos
Turn product stories, packshots, and creative references into short demonstration or reveal clips.
AI ad video
Create concise campaign shots around one message, action, and placement.
Social clips
Design short vertical or feed-ready ideas with purposeful pacing and framing.
Transitions and reveals
Define exact first and last images and direct the movement between them.
Video edits
Change a focused visual detail or style in existing footage and review what stayed recognizable.
B-roll and continuations
Create a new supporting shot or add footage directly before or after one existing clip.
Inputs and outputs
Input · Text — A written shot: subject, action, camera, and pacing
Input · Image — Opening image, first and last frames, or reference images (optional)
- Formats
- JPG, PNG
Input · Video — Footage to edit or continue (optional)
- Formats
- MP4, MOV
Output · Video — One clip per shot, on a video model that fits the input
- Formats
- MP4
- Specifications
- 2–30 s; aspect ratios 16:9, 9:16, 1:1, 4:3, 3:4
| Input or output | Type | Formats | Specifications |
|---|---|---|---|
| Input | Text — A written shot: subject, action, camera, and pacing | — | — |
| Input | Image — Opening image, first and last frames, or reference images (optional) | JPG, PNG | — |
| Input | Video — Footage to edit or continue (optional) | MP4, MOV | — |
| Output | Video — One clip per shot, on a video model that fits the input | MP4 | 2–30 s; aspect ratios 16:9, 9:16, 1:1, 4:3, 3:4 |
Specifications last checked · Sources: Model catalog · Documentation · Terms of Service
Questions
What can I make with Video Generation Studio?
You can create short product, ad, social, b-roll, transition, reveal, and cinematic concept clips from text, images, references, or existing footage.
Can I start from my own image?
Yes. Use one image as the opening frame, or provide exact first and last images for a directed transition.
Can it edit or continue existing footage?
Yes. It can change one part of a clip or add new footage directly before or after it.
Which video model does it use?
It matches the requested inputs and settings to a currently eligible model. If you name a compatible model, that choice is kept.
Can it make a longer sequence?
Yes. A longer idea is made shot by shot as a series of clips, ready for captions, narration, transitions, and timeline assembly.
Related Skills
