9:16 films your page's own mobile layout in a real phone viewport — so the footage is what a viewer would see if they tapped through.
Letterboxing and tiny text tell the audience this was made for somewhere else.
If the captions are not the script, most viewers get nothing at all.
The platform decides what works, so you need variants — and manual editing cannot supply them.
The ratio chooses the device: 9:16 captures your real mobile layout in a phone viewport, stacked cards and mobile nav included.
The tiktok_punchy edit style cuts hard throughout, punches in on the problem or the win, and swipes on the closing beat.
Rewrite the opening scene and re-render. Five openings on the same body costs five re-renders (200 credits), not five productions.
No. Choosing 9:16 re-captures your page in a phone viewport, so you get your actual mobile layout rather than the middle slice of a desktop screenshot. That is the main reason these read as native.
Yes, generated from the narration and synced to the voice track word by word. If they ever drift after you edit the script, re-timing them against the existing voice is free, once per render.
No — the audio is your narration plus an optional music bed. Trending sounds have to be added in the platform's own editor, and that is the one step worth doing there.
Paste a URL, watch the AI build it. If it's not the fastest video you've ever produced, it cost you nothing.
Start free →