Media creation

Generate images, video, speech, music and sound effects through ready-to-run APIs from live model providers.

Create media content with 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.

Capabilities and tools

Text to speech

$0.1400 per 1k chars

Eleven v3

Generate multi-speaker dialogue audio from scripted text with voice and delivery controls.

ElevenLabs

Image editing

$0.0070 per megapixel

FLUX.2 Flash Edit

Edit one or more images from a text instruction with configurable output size and format.

Black Forest Labs

Image generation

$0.0420 per megapixel

FLUX.2 Pro

Generate images from text prompts with configurable aspect ratio, resolution and output format.

Black Forest Labs

Image generation

$0.0042 per megapixel

FLUX.1 schnell

Generate images from text prompts with configurable size, inference steps and output count.

Black Forest Labs

Image generation

$0.0280 per image

Grok Imagine Image

Generate or edit images from text prompts with aspect-ratio and output-format controls.

xAI

Image generation

$0.0049 per image

MiniMax Image-01

Generate images from text prompts with configurable aspect ratio and output count.

MiniMax

Video generation

$0.1960 per video second

Grok Imagine Video 1.5 Image-to-Video

Generate video from an input image and text prompt with duration and resolution controls.

xAI

Video generation

$0.0300 per 1k tokens

Seedance 2.5 Image-to-Video

Generate video from an input image and text prompt with duration and resolution controls.

ByteDance

Music generation

$0.0280 per minute

CassetteAI Music Generator

Generate music from text prompts with duration and instrumental controls.

CassetteAI

Music generation

$0.2100 per minute

Eleven Music v2

Generate music from text prompts with duration and composition controls.

ElevenLabs

Sound effect generation

$0.1680 per minute

Eleven Text to Sound v2

Generate sound effects from text prompts with duration and prompt-influence controls.

ElevenLabs

Text to speech

$0.0700 per 1k chars

Eleven Flash v2.5

Generate speech audio from text with a selected voice and output format.

ElevenLabs

Video generation

$0.1960 per video second

Grok Imagine Video 1.5 Reference-to-Video

Generate video from one to seven reference images and a tagged text prompt with duration and aspect-ratio controls.

xAI

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 Reference-to-Video

Generate video from referenced images, optional audio and a tagged text prompt with duration and resolution 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 AI media creation

Brief your agent around the outcome you want, then let it plan the work and select the right Scrollport capabilities and tools.

How should I brief my agent?

Start with the result you want rather than a model or API. Tell the agent who the content is for, where it will appear, what it should achieve and which source material it must use.

  • Provide brand references, source files, approved claims and anything that must appear.
  • State the desired format, dimensions or aspect ratio, duration and language.
  • Describe the tone and include a short list of things the output must avoid.
How should I structure a media workflow?

Ask the agent to turn a broad request into a short production plan before it generates anything. Approve the concept first, create a low-cost draft next, and produce the final assets only after the direction is settled.

  • Separate the script, visuals, voice and sound when each part needs independent review.
  • Reuse one approved creative brief so separate assets feel like the same campaign.
  • Ask for reusable source assets when you expect to create several formats or variants.
When should I ask for another version?

Give the agent specific feedback about what is not working, such as pacing, composition, tone or fidelity to the source material. Change one important variable at a time so the next result tests a clear improvement.

  • Keep the parts that already work and name them explicitly.
  • Describe the audience reaction you want instead of asking only for something better.
  • Use a short or lower-cost draft when testing a substantially different direction.
Example prompt

This example lets your agent plan a multi-stage media job and choose the appropriate Scrollport tools.

Example prompt to give your agent

Use Scrollport to help me create [MEDIA ASSET] for [AUDIENCE AND CHANNEL]. The goal is [OBJECTIVE]. Use the attached [SOURCE MATERIAL] and follow these requirements: [MUST INCLUDE]. Avoid: [MUST NOT INCLUDE]. First propose a short production plan and ask me for anything essential that is missing. Then choose the most suitable Scrollport capability and tool for each stage. Show me the price before every paid run and create one low-cost draft before the final version. Return the finished [FORMAT] plus any reusable source assets.