Seedance - Text to Video

Generate video directly from a text prompt using ByteDance's Seedance models, with native audio generation and aspect-ratio control. Optionally attach reference images, video clips and audio tracks to guide the result — a plain prompt with no references still generates a normal text-to-video clip.

Endpoint

POSThttps://api.1min.ai/api/features

Request Headers

Field	Value
API-KEY	<api-key>
Content-Type	application/json

Request Parameters

Field Name	Type	Example	Description	Required
type	string	TEXT_TO_VIDEO	Feature identifier	✔️
model	string	bytedance/seedance-2.5	AI model to use: bytedance/seedance-2.5, bytedance/seedance-2.0, bytedance/seedance-2.0-fast or bytedance/seedance-2.0-mini	✔️
conversationId	string	TEXT_TO_VIDEO	Conversation context	✔️
promptObject.prompt	string	A cat surfing on a neon wave, cinematic lighting	Text description of the video to generate. Max 5000 characters	✔️
promptObject.resolution	string	720p	Output resolution. Allowed values depend on the model (see the table below)	✔️
promptObject.duration	number	5	Video duration in seconds. Allowed range depends on the model (see the table below)	✔️
promptObject.imageUrls	string[]	["images/character.png"]	S3 object keys (not public URLs) returned by the Asset API — upload each file first, then pass the returned paths. Reference images guiding the subjects and style of the video. Up to the per-model cap (see the table below). Each image must be at least 300px wide — the provider rejects narrower images	❌
promptObject.videoUrls	string[]	["videos/walk_cycle.mp4"]	S3 object keys (not public URLs) returned by the Asset API — upload each file first, then pass the returned paths. Reference video clips	❌
promptObject.audioUrls	string[]	["audios/voice.mp3"]	S3 object keys (not public URLs) returned by the Asset API — upload each file first, then pass the returned paths. Reference audio tracks	❌
promptObject.ratio	string	16:9	Aspect ratio of the output video: 16:9, 4:3, 1:1, 3:4, 9:16 or 21:9, plus 9:21 on the bytedance/seedance-2.0 family. Omit the field to let the provider choose the ratio	❌
promptObject.generateAudio	boolean	true	Generate dialogue, ambience and sound effects alongside the video. Defaults to true	❌
promptObject.seed	number	12345	Random seed for reproducible generation. Integer from 0 to 4294967295, or -1 for random	❌
promptObject.watermark	boolean	false	Whether to add an AI-generated watermark to the output video	❌

Four variants are available, and the accepted resolution, duration, seed and reference counts differ between them:

Model	Resolutions	Duration (s)	Seed	Max ref. images / videos / audio	Combined ref. video/audio length
bytedance/seedance-2.5	480p, 720p	4-30	supported	30 / 10 / 10	≤ 30s
bytedance/seedance-2.0	480p, 720p, 1080p, 4K	4-15	supported	9 / 3 / 3	≤ 15s
bytedance/seedance-2.0-fast	480p, 720p	4-15	supported	9 / 3 / 3	≤ 15s
bytedance/seedance-2.0-mini	480p, 720p	4-15	supported	9 / 3 / 3	≤ 15s

Code Examples

Text to Video (no references)

cURL

curl --location 'https://api.1min.ai/api/features' \
--header 'API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"type": "TEXT_TO_VIDEO",
"model": "bytedance/seedance-2.5",
"conversationId": "TEXT_TO_VIDEO",
"promptObject": {
  "prompt": "A cat surfing on a neon wave, cinematic lighting",
  "resolution": "720p",
  "duration": 5,
  "generateAudio": true
}
}'

JavaScript

fetch('https://api.1min.ai/api/features', {
method: 'POST',
headers: {
  'Content-Type': 'application/json',
  'API-KEY': 'YOUR_API_KEY'
},
body: JSON.stringify({
  type: 'TEXT_TO_VIDEO',
  model: 'bytedance/seedance-2.5',
  conversationId: 'TEXT_TO_VIDEO',
  promptObject: {
    prompt: 'A cat surfing on a neon wave, cinematic lighting',
    resolution: '720p',
    duration: 5,
    generateAudio: true
  }
})
})

Python

import requests

url = "https://api.1min.ai/api/features"
headers = {
"Content-Type": "application/json",
"API-KEY": "YOUR_API_KEY"
}

data = {
"type": "TEXT_TO_VIDEO",
"model": "bytedance/seedance-2.5",
"conversationId": "TEXT_TO_VIDEO",
"promptObject": {
  "prompt": "A cat surfing on a neon wave, cinematic lighting",
  "resolution": "720p",
  "duration": 5,
  "generateAudio": True
}
}

response = requests.post(url, headers=headers, json=data)

Reference to Video

Attach reference images, video clips and/or audio tracks to guide the generation instead of relying on the prompt alone.

cURL

curl --location 'https://api.1min.ai/api/features' \
--header 'API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"type": "TEXT_TO_VIDEO",
"model": "bytedance/seedance-2.0",
"conversationId": "TEXT_TO_VIDEO",
"promptObject": {
  "prompt": "The character from the reference images walks through the same street",
  "resolution": "1080p",
  "duration": 10,
  "ratio": "16:9",
  "generateAudio": true,
  "seed": 12345,
  "imageUrls": ["images/character.png", "images/street.png"],
  "videoUrls": ["videos/walk_cycle.mp4"],
  "audioUrls": ["audios/voice.mp3"]
}
}'

JavaScript

fetch('https://api.1min.ai/api/features', {
method: 'POST',
headers: {
  'Content-Type': 'application/json',
  'API-KEY': 'YOUR_API_KEY'
},
body: JSON.stringify({
  type: 'TEXT_TO_VIDEO',
  model: 'bytedance/seedance-2.0',
  conversationId: 'TEXT_TO_VIDEO',
  promptObject: {
    prompt: 'The character from the reference images walks through the same street',
    resolution: '1080p',
    duration: 10,
    ratio: '16:9',
    generateAudio: true,
    seed: 12345,
    imageUrls: ['images/character.png', 'images/street.png'],
    videoUrls: ['videos/walk_cycle.mp4'],
    audioUrls: ['audios/voice.mp3']
  }
})
})

Python

import requests

url = "https://api.1min.ai/api/features"
headers = {
"Content-Type": "application/json",
"API-KEY": "YOUR_API_KEY"
}

data = {
"type": "TEXT_TO_VIDEO",
"model": "bytedance/seedance-2.0",
"conversationId": "TEXT_TO_VIDEO",
"promptObject": {
  "prompt": "The character from the reference images walks through the same street",
  "resolution": "1080p",
  "duration": 10,
  "ratio": "16:9",
  "generateAudio": True,
  "seed": 12345,
  "imageUrls": ["images/character.png", "images/street.png"],
  "videoUrls": ["videos/walk_cycle.mp4"],
  "audioUrls": ["audios/voice.mp3"]
}
}

response = requests.post(url, headers=headers, json=data)

Interactive Playground

API Playground

GETPOSTPUTDELETEhttps://api.1min.ai/api/features

AI Model *Seedance 2.5 (480p/720p, 4-30s)Seedance 2.0 (up to 4K, 4-15s)Seedance 2.0 Fast (480p/720p, 4-15s)Seedance 2.0 Mini (480p/720p, 4-15s)

Video Description *A cat surfing on a neon wave, cinematic lighting

Resolution *

1080p and 4K are only accepted by bytedance/seedance-2.0

480p720p1080p (bytedance/seedance-2.0 only)4K (bytedance/seedance-2.0 only)

Duration (seconds) *

bytedance/seedance-2.5 accepts 4-30s; every other variant accepts 4-15s

Aspect Ratio

Leave unset to let the provider choose the ratio. 9:21 is accepted by the bytedance/seedance-2.0 family only

16:9 (Widescreen)9:16 (Vertical)1:1 (Square)4:3 (Standard)3:4 (Vertical Standard)21:9 (Cinematic)9:21 (bytedance/seedance-2.0 family only)

Reference Image S3 Paths

Comma-separated Asset API paths. Up to the per-model cap. Each image must be at least 300px wide

Reference Video S3 Paths

Comma-separated Asset API paths

Reference Audio S3 Paths

Comma-separated Asset API paths

Generate Audio

Generate dialogue, ambience and sound effects alongside the video

Seed

Fixed seed for reproducible generation

Watermark

Add an AI-generated watermark to the output video

Generated cURL Command:

curl -X POST "https://api.1min.ai/api/features" \
  -H "API-KEY: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{
  "type": "TEXT_TO_VIDEO",
  "model": "bytedance/seedance-2.5",
  "conversationId": "TEXT_TO_VIDEO",
  "promptObject": {
    "prompt": "A cat surfing on a neon wave, cinematic lighting",
    "resolution": "720p",
    "duration": 5,
    "generateAudio": true
  }
}'

Response

{
"aiRecord": {
  "uuid": "b574969b-4992-4173-9e62-7ebd4782103e",
  "userId": "2f57c2a4-1fff-48e7-972f-3c1d6c59bced",
  "teamId": "eb48d89f-1bb7-4d82-9b25-481971a0e97a",
  "model": "bytedance/seedance-2.5",
  "type": "TEXT_TO_VIDEO",
  "metadata": {
    "credit": 12000000,
    "duration": 5,
    "resolution": "720p",
    "executionTime": 48.201
  },
  "rating": null,
  "feedback": null,
  "conversationId": null,
  "status": "SUCCESS",
  "createdAt": "2026-08-13T16:47:28.018Z",
  "aiRecordDetail": {
    "promptObject": {
      "prompt": "A cat surfing on a neon wave, cinematic lighting",
      "ratio": "16:9",
      "duration": 5,
      "resolution": "720p",
      "generateAudio": true
    },
    "resultObject": [
      "development/videos/2026_08_13_23_48_59_722_158922.mp4"
    ],
    "responseObject": {
      "task_id": "3f2aK9mR",
      "credits": 100,
      "processing_time": 48
    }
  },
  "additionalData": null,
  "temporaryUrl": "https://s3.us-east-1.amazonaws.com/asset.1min.ai/development/videos/2026_08_13_23_48_59_722_158922.mp4?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=..."
}
}