You pay for video minutes, not for features.

A set of vertical 9:16 clips, ranked best-first, each already cut, reframed and captioned word-by-word. You pick which ones are worth posting — there is no editing step in between.

Longer than a page load and shorter than an editor. Transcription, ranking and rendering are real work on real hardware, so a job runs for minutes rather than seconds. The app shows you which stage it is on the whole time instead of a spinner.

No. Everything runs in the browser at app.ytshorts.ai. There is also a command-line version of the same pipeline for developers who would rather run it on their own machine with their own API keys.

Yes — it is the full product, not a locked demo. All five tools are available on Free. What you trade is a watermark on exports, 50 credits a month, source videos capped at 30 minutes, and up to 2 clips per Extract job.

One job costs credits based on how long its source video is — counted per 5 minutes, rounded up — and which tool you ran. Create Video has no source, so it is counted per 30 seconds of the video it makes. Higher plans get more credits each month and pay fewer credits for the exact same video. As a rough guide, a month of Extract Shorts covers about 30 min of video on Free, 4 hours on Starter, 11 hours on Pro and 26 hours on Max; the other tools stretch further.

Buy extra credits on the Buy credits page, on any plan, from $0.50 (or ₹50): 125 credits per $1. Your monthly credits are always used first, and bought credits stay usable for 90 days from purchase. Jobs cost the same credits as usual for your plan.

Rendered clips stay in your library for 7 days on Free, 14 days on Starter and 30 days on Pro and Max, then are deleted automatically. You can delete anything yourself at any time, and your uploaded voice clones are never swept.

Yes. Transcription auto-detects the language, and you can force a specific one if you would rather. Captions can also be translated into another language before they are burned in.

Add Voiceover and Add Captions both work from audio alone, so an audio-first show can still produce captioned, watchable shorts without a camera setup.