Seedance 2.0

Generate 4-15 second videos with multimodal reference input using Seedance 2.0 through VicSee API. Text, image, video, and audio references. Native audio included. 100-830 credits.

Try it now: Use the Seedance 2.0 Generator to create videos with multimodal references.

Pricing

Text to Video / Image to Video

Duration480p Credits480p (Pro Yearly)480p (Pro Monthly)720p Credits720p (Pro Yearly)720p (Pro Monthly)
4s100$0.60$1.20220$1.32$2.64
5s120$0.72$1.44280$1.68$3.36
6s150$0.90$1.80330$1.98$3.96
7s170$1.02$2.04390$2.34$4.68
8s200$1.20$2.40440$2.64$5.28
9s220$1.32$2.64500$3.00$6.00
10s250$1.50$3.00550$3.30$6.60
11s270$1.62$3.24610$3.66$7.32
12s300$1.80$3.60660$3.96$7.92
13s320$1.92$3.84720$4.32$8.64
14s350$2.10$4.20770$4.62$9.24
15s370$2.22$4.44830$4.98$9.96

Reference to Video (with video references)

When using reference_video_urls, credits are calculated dynamically based on total video duration:

Total credits = per-second rate x (sum of input video durations + output duration)

ResolutionCredits per second
480p15/s
720p35/s

Example: 10s reference video + 8s output at 720p = (10 + 8) x 35 = 630 credits

Reference to Video requests using only image and/or audio references (no video references) use the standard pricing table above.

Note: Audio generation is included at no extra cost. Credits are deducted only on successful generation.

Credit range: 100-830 credits (standard pricing), variable for video references.

Endpoint

POST https://vicsee.com/api/v1/generate

See Authentication for API key setup.


Text to Video

Generate videos from text descriptions with native audio.

Request Parameters

ParameterTypeRequiredDescription
modelstringYesseedance-2-0-text-to-video
input.promptstringYesVideo description (max 2500 chars)
input.durationnumberNo4-15 seconds, any integer (default: 8)
input.resolutionstringNo480p, 720p (default: 720p)
input.aspect_ratiostringNo16:9, 9:16, 1:1, 4:3, 3:4, 21:9, adaptive (default: 16:9)
input.audiobooleanNoEnable native audio (default: true)
input.web_searchbooleanNoEnhance prompt with web search (default: false)

Example Request

curl -X POST https://vicsee.com/api/v1/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2-0-text-to-video",
    "input": {
      "prompt": "A martial arts master demonstrates fluid spear techniques in a sunlit courtyard",
      "duration": 8,
      "resolution": "720p",
      "aspect_ratio": "16:9",
      "audio": true
    }
  }'

Image to Video

Animate images into video using first frame and optional last frame control.

Request Parameters

ParameterTypeRequiredDescription
modelstringYesseedance-2-0-image-to-video
input.promptstringYesDescription of the animation
input.image_urlsstring[]YesArray of 1-2 images (first frame, optional last frame)
input.durationnumberNo4-15 seconds, any integer (default: 8)
input.resolutionstringNo480p, 720p (default: 720p)
input.aspect_ratiostringNo16:9, 9:16, 1:1, 4:3, 3:4, 21:9, adaptive (default: 16:9)
input.audiobooleanNoEnable native audio (default: true)

Example Request

curl -X POST https://vicsee.com/api/v1/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2-0-image-to-video",
    "input": {
      "prompt": "The woman turns and smiles warmly, the wind catching her hair",
      "image_urls": ["https://example.com/start-frame.jpg"],
      "duration": 6,
      "resolution": "720p",
      "audio": true
    }
  }'

Two images: Pass a second URL for last frame control. The model generates a smooth transition between the two frames.

"image_urls": [
  "https://example.com/start-frame.jpg",
  "https://example.com/end-frame.jpg"
]

Reference to Video

Generate videos using multimodal references: images, videos, and audio. This is Seedance 2.0's unique capability, allowing character consistency, motion reference, and audio-driven generation.

Request Parameters

ParameterTypeRequiredDescription
modelstringYesseedance-2-0-reference-to-video
input.promptstringNoText description to guide generation
input.reference_image_urlsstring[]NoUp to 7 reference images (character refs, scene refs)
input.reference_video_urlsstring[]NoUp to 3 reference videos (motion, style)
input.reference_audio_urlsstring[]NoUp to 3 reference audio files (voice, music, SFX)
input.durationnumberNo4-15 seconds, any integer (default: 8)
input.resolutionstringNo480p, 720p (default: 720p)
input.aspect_ratiostringNo16:9, 9:16, 1:1, 4:3, 3:4, 21:9, adaptive (default: 16:9)
input.audiobooleanNoEnable native audio (default: true)

At least one reference type must be provided. You can combine all three in a single request.

Reference Constraints

TypeMax CountMax SizeDuration LimitFormats
Images730MB eachjpeg, png, webp, bmp, tiff, gif
Videos350MB each2-15s each, total max 15smp4, mov
Audio310MB each2-15s each, total max 15smp3, wav

Example Request

curl -X POST https://vicsee.com/api/v1/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2-0-reference-to-video",
    "input": {
      "prompt": "The character walks through a garden, looking around with curiosity",
      "reference_image_urls": [
        "https://example.com/character-ref.jpg",
        "https://example.com/scene-ref.jpg"
      ],
      "reference_video_urls": [
        "https://example.com/motion-reference.mp4"
      ],
      "duration": 10,
      "resolution": "720p"
    }
  }'

Response

Success (200)

{
  "success": true,
  "data": {
    "id": "task_abc123xyz",
    "model": "seedance-2-0-text-to-video",
    "status": "pending",
    "creditsUsed": 440,
    "creditsRemaining": 560,
    "createdAt": "2026-04-04T12:00:00Z"
  }
}

Poll for completion using Tasks API.

Task Complete

{
  "taskId": "task_abc123xyz",
  "status": "completed",
  "output": {
    "url": "https://cdn.vicsee.com/outputs/video_xyz.mp4",
    "duration": 8,
    "format": "mp4",
    "hasAudio": true
  }
}