scrollport

Text-to-video API

Generate video directly from a written prompt using live models with different production controls.

Create video from text with Scrollport

Use Scrollport

Scrollport identifies and validates the best-in-class API tools and provides them on a pay-as-you-go basis so you don't need to maintain a separate provider account, subscription or credits.

Give your agent the setup prompt to receive $1 in trial credit and start using the tools right away.

4 available tools

Video generation

$0.1960 per video second

Grok Imagine Video 1.5 Text-to-Video

Generate video from a text prompt with duration, resolution and aspect-ratio controls.

xAI

Video generation

$0.1120 per video second

MiniMax H3 Text-to-Video

Generate video from a text prompt with bounded duration, resolution and aspect-ratio controls.

MiniMax

Video generation

$0.0034 per 1k tokens

Seedance 1.5 Pro

Generate video from text prompts with duration, resolution and aspect-ratio controls.

ByteDance

Video generation

$0.0300 per 1k tokens

Seedance 2.5 Text-to-Video

Generate video from text prompts with duration, resolution and aspect-ratio controls.

ByteDance

Learn more about text-to-video generation

Describe one filmable shot with a clear subject, action, setting and camera intention. Your agent can turn that direction into a bounded first generation.

Write a shot, not a whole story

Specify what is visible during a short period: subject appearance, action, environment, framing, camera movement, lighting and mood. Split scene changes into separate shots.

How detailed should a text-to-video prompt be?

Include details that affect the visible result and omit instructions the camera cannot show. Prioritise subject consistency and physical action over long backstory or several competing style references.

Approve a short draft before extending

Review motion, anatomy, camera behaviour, unwanted objects and the ending frame. Refine the shot before requesting more duration or matching shots for a sequence.

Example prompt

This prompt keeps the generation to one observable shot.

Example prompt to give your agent

Use Scrollport's Text-to-video capability to create a [DURATION] [ASPECT RATIO] shot for [USE]. Show [SUBJECT] [ACTION] in [SETTING]. Frame it as [SHOT SIZE], move the camera [CAMERA MOVEMENT], and use [LIGHTING AND MOOD]. Preserve [IMPORTANT DETAILS], avoid [EXCLUSIONS], and show me the price before the paid run.