Raise the back of your tongue to touch the soft palate (velum). Stop the air, then release.

Americans pronounce capacity as kuh-PA-suh-tee (/kəˈpæsəɾi/). In "capacity", the "t" between vowels sounds like a quick "d" — the tongue briefly taps the ridge behind the upper teeth. This is called the Flap T, a small move that separates 'classroom' from 'native'. It comes out as kuh·PA·suh·tee. Stress falls on the second syllable — keep everything else short and quick. You'll hear it in sentences like "The system is operating at maximum capacity".
Record yourself saying "capacity" and play it back. The mic stays on your device — nothing's uploaded.
4 syllables, 8 sounds. Tap a syllable to jump to its row, then explore each sound's mouth shape and how it's made.
The textbook way isn't wrong — it's just not how anyone actually says it.
In "capacity", the "t" between vowels sounds like a quick "d" — the tongue briefly taps the ridge behind the upper teeth. /t/ or /d/ becomes a quick tap [ɾ] — sounds like a soft D. The tongue briefly taps the ridge behind the upper teeth.
Stress falls on the second syllable, not the others. Stretch PA — keep everything else short and quick.
Don't pronounce the first syllable too fully. The unstressed syllable reduces to a schwa — the lazy "uh" sound — in casual speech.