Seedance 2.0 Mini Video from Text

Seedance 2.0 Mini is an AI video generator that can request a 4–15-second clip from one written scene. It accepts text only; you cannot add a photo, video or sound clip.

Your AI

Use with your AI

For tasks with several steps, continue in the AI you already use.

CodexClaude CodeCursorWindsurfCline

View instructions

Use Toolmu's Seedance 2.0 Mini video generator for my request. I will describe one scene using text only. Do not ask me for photos, videos or sound clips; this tool works from text. Turn everyday requests such as [vertical video] and [about 5 seconds] into this tool's available choices. Ask me if an option is unsupported. Before any action that could charge me, tell me the current price and wait for my approval. Follow the task until it finishes or fails. If it finishes successfully, share the actual video link returned; do not say the video is ready before then or guarantee that the link will always work.

Task:
Make a [vertical video] about [5 seconds] long, showing [a paper sailboat gliding across a sunlit desk]. After it finishes, share the video link if one is returned.

Paste into your connected AI's conversation.

Connection guide

Up to 2.4 credits / call

The final charge is based on confirmed usage. Unused reserved credits return to your available balance.

ByteDance

Seedance 2.0 Mini Video from Text

Seedance 2.0 Mini is an AI video generator that can request a 4–15-second clip from one written scene. It accepts text only; you cannot add a photo, video or sound clip.

You receive

After generation succeeds, the result is a video URL. Your Agent can return that link so you can review the clip for a short promotion, social post or visual draft.

Start with your task

Make a [vertical video] about [5 seconds] long, showing [a paper sailboat gliding across a sunlit desk]. After it finishes, share the video link if one is returned.

What to know

This Mini task accepts text only, without image, video or audio references. Exact scene reproduction and completion time are not guaranteed; link access and lifetime are not assured.

Inputs & outputs

Inspect the current inputs, availability, and maximum charge before starting.

Input schema

Input schema
Field / Path	Type	Requirement	Meaning
Frame shape`ratio`	`string`	Optional	Choose a frame shape such as 9:16 for portrait or 16:9 for landscape. Specify the ratio when a particular layout matters. Options `16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive`
Scene content`content`	`array`	Required	Provide exactly one text prompt item for the scene you want to generate. Minimum items `1` Maximum items `1`
Text prompt item`content[]`	`object`	—	One object containing the text kind and your scene description. Required fields `type, text`
Scene description`content[].text`	`string`	—	Write 1–6,000 characters describing the subject, action and important visual details. Keep the request focused on one short scene. Minimum length `1` Maximum length `6000`
Content kind`content[].type`	`string`	—	Set the item kind to text. Fixed value `text`
Requested duration`duration`	`integer`	Optional	Choose a duration from 4 to 15 seconds. Specify the duration when the clip needs to fit a particular slot. Default `5` Minimum `4` Maximum `15`
Queue priority`priority`	`integer`	Optional	Choose a queue priority from 0 to 9. Higher values request an earlier queue position; this does not set a completion deadline. Minimum `0` Maximum `9`
AI watermark`watermark`	`boolean`	Optional	Use true to request an AI Generated watermark, or false to request no watermark. Default `false`
Resolution`resolution`	`string`	Optional	Choose 480p or 720p. Resolution participates in price selection, so check the current charge before starting. Default `720p` Options `480p, 720p`
Generated sound`generate_audio`	`boolean`	Optional	Use true to request synchronized generated sound, or false to request a silent clip. This is a sound setting, not an audio reference upload. Default `true`

View raw JSON

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "content"
  ],
  "properties": {
    "ratio": {
      "enum": [
        "16:9",
        "4:3",
        "1:1",
        "3:4",
        "9:16",
        "21:9",
        "adaptive"
      ],
      "type": "string",
      "description": "Aspect ratio. Omit for the upstream default (adaptive - picks the best fit from your prompt/inputs)."
    },
    "content": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "type",
          "text"
        ],
        "properties": {
          "text": {
            "type": "string",
            "maxLength": 6000,
            "minLength": 1
          },
          "type": {
            "const": "text"
          }
        },
        "additionalProperties": false
      },
      "maxItems": 1,
      "minItems": 1
    },
    "duration": {
      "type": "integer",
      "default": 5,
      "maximum": 15,
      "minimum": 4,
      "description": "Duration in seconds (4-15)."
    },
    "priority": {
      "type": "integer",
      "maximum": 9,
      "minimum": 0,
      "description": "Queue priority 0-9 (higher = front of the queue). Default 0."
    },
    "watermark": {
      "type": "boolean",
      "default": false,
      "description": "Add an \"AI Generated\" watermark. Default false."
    },
    "resolution": {
      "enum": [
        "480p",
        "720p"
      ],
      "type": "string",
      "default": "720p",
      "description": "Output resolution (also the price selector)."
    },
    "generate_audio": {
      "type": "boolean",
      "default": true,
      "description": "Generate synchronized audio (voice, sound effects, music). Default true. No price impact."
    }
  },
  "additionalProperties": false
}

Result schema

Result schema
Field / Path	Type	Meaning
Generated video link`videoUrl`	`string`	The link returned for the completed video. Keep the actual URL with your prompt when reviewing the result. Format `uri`

View raw JSON

{
  "type": "object",
  "required": [
    "videoUrl"
  ],
  "properties": {
    "videoUrl": {
      "type": "string",
      "format": "uri"
    }
  },
  "additionalProperties": false
}

Additional notes

Keep the scene focused

Put the main visible action first. Add a camera viewpoint and lighting that help explain it; avoid competing actions in a short clip. If you want sound, describe the desired sound as part of the text and choose the audio setting separately.

Keep a revision note

Save the prompt and requested settings beside the returned link. When the clip is available to view, compare the main action and framing before deciding which part of the prompt to revise.

Seedance 2.0 Mini Video from Text

Seedance 2.0 Mini Video from Text

You receive

Start with your task

What to know

Inputs & outputs

Input schema

Result schema

Keep the scene focused

Keep a revision note

Connect your AI assistant

Describe your scene

Check the video link