Make video

The quickest way to make a video from a description: no template, node types or graph to wire. Picks a video model that renders the shape and length asked for (Veo 3.1 Lite unless a model is named or it cannot), prepares the render, and answers like estimate_run_cost: the price, whether the balance covers it, and a quoteId. It does NOT start the render: tell the person what it makes and the price, and once they accept, call run_pipeline with the returned pipelineId and quoteId (no inputs; the prompt is saved). Clients that show panels put the price in front of them with a Start render button. Use 9:16 for Shorts, Reels and TikTok. With maxPriceUsd, a video over it is refused with its price rather than shortened. For anything beyond one generated clip (clipping a long video, music, narration, editing a file) use a template, assemble_video or edit_asset instead. Needs the pipelines:write scope; the run needs pipelines:run.

post/api/v1/tools/make_video

Request

  • Base URL: https://www.trezalabs.com
  • URL: https://www.trezalabs.com/api/v1/tools/make_video
  • Auth: HTTP bearer

Request body

promptstring required

What the video shows, in the person's words or a fuller description of them.

durationSecnumber

Length in seconds. A model that renders fixed takes uses the next one up (at most 2s longer), and says so. Defaults to 4.

aspectRatio'16:9' | '9:16' | '1:1'

"9:16" vertical (Shorts, Reels, TikTok), "16:9" horizontal (the default), "1:1" square.

withAudioboolean

Generate sound with the video where the model can. Defaults to true.

maxPriceUsdnumber

The most the person will pay for this render, if they said.

modelstring

A video model id from get_node_type video-gen, only when the person asked for a specific model.

namestring

What to call the render.

Response

The tool's result.

object required

Changes

No recorded changes to this operation across all 1 revision of this API.