Short video script
Under Reels, Shorts and VK Clips. A hook for the first three seconds, a storyboard for seconds, lines and text on the screen, plus a reason to watch to the end.
A short video lives or dies in the first three seconds: it decides whether it will be watched or skipped, and no subsequent value will correct this. The tool assembles a script where the hook is separated from the rest, the storyboard is scheduled down to the second, and in the middle there is a reason to watch to the end.
AI answers are free, but limited by the overall site limit. If the limit is reached, come back later: repeated clicks will not speed up the response.
Three seconds decide the fate of the entire video
In vertical video, the decision is made almost instantly, and it is made before the viewer knows what the video is about. Therefore, a high-quality middle does not save a weak beginning: they simply do not reach the middle. The hook is written separately and first, and not attached to the finished script.
A hook is not a greeting or an introduction. “Hey, I’ll tell you today” wastes three of the most expensive seconds on information that the viewer doesn’t need. The promise of a specific result, an unusual shot, a question about its situation, or a immediately shown result works.
The second blade point is the middle. The viewer stayed after the hook, received what was promised and leaves. Therefore, the script has a separate reason to watch it: what is announced at the beginning, but shown at the end.
The storyboard is counted in seconds at a rate of approximately 2.5 words per second. Text that does not fit into the timing will have to be hastily cut during editing, and usually the most valuable is cut.
What the tool intentionally doesn't do
Does not insert numbers, deadlines, benchmarks and names of companies that did not exist in your input. If the output requires a number that you did not provide, in the answer will be marked “to clarify” rather than a plausible number. This limitation is worth in the system prompt and works against the main property of language models: It’s difficult to complete what’s missing.
The request text is sent to the AI provider, and the response is returned to the browser. The site does not save these texts in the database. To limit expenses separately the number of requests and the anonymized connection identifier are taken into account. If the free limit is reached, the tool will offer to come back later.