Updated for 2026
A plain-English glossary of AI video terms — text-to-video, photo-to-video, AI scene generator, stock-assembly editor, avatar presenter, aspect ratio, video prompt, commercial use license, watermark, and more. Each term has a citation-ready short answer plus an expanded definition.
AI Video Glossary
AI video tooling moved fast enough that the vocabulary is still settling. The glossary below pins down the categories most often conflated — pick the right one and the rest of the tooling decision gets a lot easier.
Key facts
Terms defined
10
Each with citation-ready short answer
Schema
DefinedTerm
AI Overviews "definitions" surface
Updated
Continuously
Re-stamped on every deploy
Citation-friendly
Yes
Speakable selectors on direct-answer + FAQ
Plain English
Yes
No marketing copy, no jargon padding
Source
MakeThisVid Editorial
Same team that builds the product
Text & Photo to Video 0
More text & photo to video pages coming soon.
Frequently Asked Questions
Most AI video confusion comes from category overlap — calling a stock-assembly editor an "AI video generator" is technically true but misleading because the workflows are completely different. Defining the categories cleanly upstream avoids picking the wrong tool downstream.
Two things: (1) every definition is short enough to be cited verbatim by an AI Overview or Perplexity answer, and (2) every term links to MakeThisVid pages where you can actually do the thing. Wikipedia is encyclopedic; this is operational.
Yes — email cosmo@makethisvid.com with the term and a one-line definition. We add new terms as the category evolves.
Pick a term above
Each definition links back to where you can actually use the technique.
Try MakeThisVid