scrollport

Seedance 2.5 Text-to-Video

Generate video with duration, resolution and native audio controls.

by ByteDanceReady to run$0.0150 per 1k tokens

Example

You ask your agent

“Make a 4-second video of a cobalt reusable bottle turning on a stone plinth as daylight moves across it.”

You get

Result
MP4 video file
Length
4 seconds
What your agent sends and gets back (JSON)

Your agent works out the exact inputs, such as IDs, dates and settings, from what you ask.

Request

{
  "tool_id": "bytedance.seedance-2-5-text",
  "input": {
    "prompt": "a cobalt reusable bottle rotates on a stone plinth as soft daylight moves across the scene",
    "duration": 4,
    "resolution": "480p",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}

Response

{
  "note": "video returned as an artifact",
  "video": {
    "audio": true,
    "content_type": "video/mp4",
    "duration_seconds": 4
  }
}

Use it with your agent

Copy the prompt and paste it into your agent, then tell it what you need.

Read https://scrollport.com/start. Use my existing Scrollport connection, or help me connect if needed. Help me use Seedance 2.5 Text-to-Video (tool ID: bytedance.seedance-2-5-text). Ask me for the details you need, then show me the result.

Provider access is included. If your agent isn't connected to Scrollport yet, it will help you set that up.

Other tools for this job

Compare all 11 →

Questions

Is Seedance 2.5 Text-to-Video by ByteDance free?

Scrollport has no free tier: it costs $0.0150 per 1k tokens, paid per use from a prepaid wallet with no subscription. Connecting your first agent adds $1 of trial credit, so you can try it before adding funds.

Do I need an API key from ByteDance?

No. Your agent runs it through your Scrollport connection (MCP, the Scrollport CLI or the HTTP API), and Scrollport handles access to ByteDance, so you don't sign up with ByteDance or manage an API key.

Details

About this tool

Create a 4–30 second Seedance 2.5 video at 480p or 720p using the prompt and references shown in the input schema. Native audio is included. Reserve the maximum output-token charge, then pay only for the generated output tokens after the video has been preserved as a Scrollport artifact. Failed requests are uncharged. The same job resumes after interruption. The model rejects reference images containing real human faces. Video references are excluded.

All inputs and outputs

Input

aspect_ratiostring · optional

Width-to-height ratio of the generated media.

enum: 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

durationinteger · optional

Length of the generated media.

minimum: 4 · maximum: 30

generate_audioboolean · optional

Whether to generate an audio track with the video.

promptstring · required

Instruction describing the requested generated output.

minLength: 1 · maxLength: 5000

resolutionstring · optional

Output resolution of the generated media.

enum: 480p, 720p

Output

notestring

Note about how the result was produced or limited.

videoobject

Generated video file.

Errors and limits
  • invalid_input: duration must be an integer from 4 to 30 secondsexample: {"prompt":"a cobalt reusable bottle rotates on a stone plinth as soft daylight moves across the scene","aspect_ratio":"16:9","resolution":"480p","duration":4,"generate_audio":true}