Seedance 2.0 API

Seedance 2.0 is ByteDance's second-generation video model. It generates up to 1080p, 15s video with native audio sync. The breakthrough is the @-reference system: upload video, audio, or image references, and the model extracts camera paths, motion patterns, rhythm, and style.EvoLink will enable Seedance 2.0 access as soon as the official API is live. Join Discord for launch updates, the final model ID once it's live, and day-one pricing/quota notes (or get one launch email).Key takeaway: You can integrate with EvoLink today using the same async workflow (submit → poll → fetch). See the API tab for request format. When Seedance 2.0 becomes available, you'll enable it by switching one model value — no code rewrite.

Seedance 2.0: Multimodal AI Video Generation

Generate cinematic video with synchronized audio using text, image, video, and audio references — all in one API call. Seedance 2.0 by ByteDance introduces the @-reference system for extracting motion, camera, and style from source media. Key upgrades from 1.5 Pro: video and audio reference inputs, up to 9 image + 3 video + 3 audio references per request, video-to-video editing mode, and 15-second max duration.

Seedance 2.0 API multimodal video generation showcase

What can you build with Seedance 2.0 API?

Seedance 2.0 Reference-Driven Video Production

With Seedance 2.0 API, upload a reference video and the model extracts camera movement, motion dynamics, and transition style via the @-reference system. Generate dozens of on-brand video variations from one hero clip — without reshooting. Supports up to 3 video references per request for combining camera from one source, motion from another, and style from a third.

Seedance 2.0 Audio-Synced Content with Reference Audio

Seedance 2.0 API lets you provide up to 3 audio tracks as references. Seedance 2.0 aligns cuts, motion energy, and scene transitions to beat and rhythm. The output includes native synchronized audio — dialogue lip-syncs in multiple languages, sound effects match on-screen action, and background music follows the mood of your audio reference.

Seedance 2.0 Multi-Reference Storyboard to Video

Seedance 2.0 lets you combine up to 9 reference images with text prompts to control composition, character, and environment across shots. Seedance 2.0 fills the gaps between keyframes with consistent identity, lighting, and style. Ideal for ad production, product demo sequences, and animated storyboards.

How Seedance 2.0 Compares — All models on one EvoLink API key

Seedance 2.0 leads with multimodal @-reference inputs, video-to-video editing, and the highest image reference count among major video generation models.

Seedance 2.0 API Multimodal @-Reference System

Seedance 2.0 is the only model supporting video, audio, and image references in a single request. Upload up to 9 images + 3 videos + 3 audio tracks to control camera, motion, rhythm, and style — capabilities unavailable in Sora 2, Kling 3.0, or Seedance 1.5 Pro.

Seedance 2.0 API Video-to-Video Editing

Seedance 2.0 API enables editing specific segments, characters, or actions in existing videos. Seedance 2.0 supports targeted V2V modifications — a feature not available in Sora 2 or Kling 3.0.

Seedance 2.0 API Competitive Pricing via EvoLink

Access Seedance 2.0 API through EvoLink's unified API with competitive per-second pricing. One API key gives you access to Seedance 2.0, Sora 2, Kling 3.0, Veo 3.1, and more — with automatic routing to the best provider.

Pricing & Specs (Quick Comparison)

A transparent benchmark across leading video APIs. Seedance 2.0 pricing will be published on launch.

Metric	Seedance 2.0	Sora 2	Kling 3.0	Veo 3.1
Price (USD / second, incl. audio)	Coming soon	$0.10 (720p)	$0.112 (1080p)	$0.40 (1080p)
Typical cost per video	Coming soon	$1.20 / 12s	$1.12 / 10s	$3.20 / 8s
Max duration	15s	12s	15s	8s
Max resolution	TBD	720p (Std) / 1080p (Pro)	1080p / 4K (tiered)	1080p / 4K (tiered)
Inputs supported	Text, Image, Video, Audio	Text, Image	Text, Image, Video, Audio	Text, Image
Reference controls (Video / Audio / Image)	✓ / ✓ / ✓	— / — / ✓	✓ / ✓ / ✓	— / — / ✓

Notes: Prices are estimates and may vary by tier/region/provider. "Typical cost per video" examples may use different durations/resolutions as shown. Last updated: 2026-02-21.

How to Integrate Seedance 2.0 API

Seamlessly integrate multimodal video generation into your app with EvoLink's unified API. Supports T2V, I2V, and V2V modes.

Step 1 — Get Your API Key

Sign up on EvoLink.ai and generate your secure API key from the dashboard. This key authenticates all your requests to the Seedance 2.0 endpoint.

Step 2 — Submit Generation Task

Send a POST request to /v1/videos/generations with your text prompt, image URLs, or video/audio references. Use the references parameter to pass video, audio, and image inputs for the @-reference system. The API processes this asynchronously and returns a task id for tracking.

Step 3 — Retrieve Video Result

Use the `task_id` to poll the status endpoint or configure a webhook. Once completed, you'll receive a secure URL to download your synchronized audio-video file in MP4+AAC format.

Seedance 2.0 API Capabilities

Technical specifications for multimodal video production

Multimodal

@-Reference System

Upload up to 9 images + 3 videos + 3 audio references per request. The model extracts camera paths, motion patterns, rhythm, and style from source media.

Quality

Up to 1080p High Definition

Outputs video at up to 1080p resolution (1920x1080 for 16:9), ensuring crisp details on all screens.

Flexibility

4-15s Duration

Supports variable video lengths from 4 to 15 seconds, with multi-shot consistency for longer narrative sequences.

Modes

Text, Image, Video & Audio Input

Supports T2V (text-to-video), I2V (image-to-video), and V2V (video-to-video) generation modes with combinable multimodal inputs.

Audio

Native Audio with Lip-Sync

Generates synchronized dialogue, sound effects, and background music. Lip-sync support for multiple languages.

Licensing

Commercial Rights

Commercial usage rights subject to BytePlus terms, enabled securely through the EvoLink platform.

Seedance 2.0 API Frequently Asked Questions

Everything you need to know about the product and billing.

Seedance 2.0 is ByteDance's second-generation video model. Compared to Seedance 1.5 Pro, it introduces the @-reference system for multimodal inputs (video, audio, and image references), video-to-video editing mode, 15-second max duration (was 12s), and up to 9 image + 3 video + 3 audio references per request. It is a major upgrade in both capabilities and flexibility.

Seedance 2.0 is billed per second with competitive pricing through EvoLink. Pricing varies by resolution (480p/720p/1080p) and whether audio is enabled. Check the pricing table above for exact per-second rates for each configuration.

Yes. EvoLink provides global access to Seedance 2.0 API with no regional restrictions. You can integrate from anywhere using a single API key.

The @-reference system is Seedance 2.0's breakthrough feature. It allows you to upload reference media (videos, audio tracks, images) and the model extracts specific attributes — camera paths from video, rhythm and beat from audio, composition and style from images. You can combine references from different sources in a single request to precisely control the output.

Seedance 2.0 supports text prompts combined with up to 9 reference images, 3 reference videos, and 3 reference audio tracks — all combinable in a single request. Generation modes include text-to-video (T2V), image-to-video (I2V), and video-to-video (V2V) editing.

Seedance 2.0 is the only model offering video and audio reference inputs, the @-reference system, and V2V editing — features not available in Sora 2 or Kling 3.0. It supports up to 9 image references (vs 1 for competitors). All three models are available through EvoLink's unified API. For a detailed side-by-side comparison, see our blog post.

Yes. Seedance 2.0 generates native synchronized audio including dialogue with lip-sync in multiple languages, sound effects matched to on-screen action, and background music. Audio generation can be toggled on/off per request, and audio references can be used to guide rhythm and mood.

Output videos are in MP4 format (H.264) with AAC audio. Supported resolutions: 480p, 720p, and 1080p. Duration: 4-15 seconds. Frame rate: 24fps. Aspect ratios: 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, and adaptive.

Yes. EvoLink's Seedance API provides a unified endpoint for Seedance 2.0, 1.5 Pro, and 1.0 Pro Fast. Use the model parameter to switch between versions.

All Seedance API Models

EvoLink provides unified API access to the full Seedance model family:

Seedance 2.0

Latest generation, cinematic quality

This page

Seedance 1.5 Pro

1080p with native audio

View details →

Seedance 1.0 Pro Fast

Fastest generation, lowest cost

View details →

All models share the same Seedance API endpoint. Switch models with one parameter.

Explore more video APIs on EvoLink—Sora 2|Kling 3.0|Veo 3.1

API Reference

Select endpoint

Authentication

All APIs require Bearer Token authentication.

Header

Authorization: 
Bearer YOUR_API_KEY

Get API Key

POST

/v1/videos/generations

Create Video

Seedance 2.0 (seedance-2.0) model supports multiple generation modes including text-to-video, image-to-video, and video-to-video editing with the @-reference system.

Asynchronous processing mode, use the returned task ID to .

Generated video links are valid for 24 hours, please save them promptly.

Request Parameters

modelstringRequiredDefault: seedance-2.0

Video generation model name.

Exampleseedance-2.0

promptstringRequired

Prompt describing what kind of video to generate. Use @-references to assign roles to uploaded files.

Notes

Limited to 2000 tokens
@Image1, @Image2... → images from image_urls (in order)
@Video1, @Video2... → videos from video_urls (in order)
@Audio1, @Audio2... → audios from audio_urls (in order)
Example: '@Image1 as first frame, replicate @Video1 camera movement, @Audio1 for BGM rhythm'

Example@Image1 as first frame, a cinematic drone shot over a coastal city at golden hour

image_urlsarrayOptional

Reference image URL list for image-to-video and multimodal generation.

Notes

Up to 9 images per request
Max size: 30MB per image
Formats: .jpeg, .png, .webp, .bmp, .tiff, .gif
Mixed input total limit: 12 files across all modalities
Realistic human face uploads are not supported and will be automatically rejected
URLs must be directly viewable by the server

Examplehttp://example.com/image1.jpg

video_urlsarrayOptional

Reference video URL list for video-to-video editing and @-reference system.

Notes

Up to 3 videos per request, total duration 2–15s
Max size: 50MB per video
Formats: .mp4, .mov
Pixel range: 409,600 (480p) – 927,408 (720p)
Using video references will increase cost
Realistic human face uploads are not supported and will be automatically rejected
URLs must be directly accessible by the server

Examplehttp://example.com/reference.mp4

audio_urlsarrayOptional

Reference audio URL list for audio-driven generation via @-reference system.

Notes

Up to 3 audio tracks per request, total duration ≤ 15s
Max size: 15MB per audio
Formats: .mp3, .wav
Aligns cuts, motion energy, and transitions to beat and rhythm
URLs must be directly accessible by the server

Examplehttp://example.com/reference.mp3

durationintegerOptionalDefault: 5

Specifies the duration of the generated video (in seconds).

Value	Description
4-15	Any integer value between 4 and 15 seconds

Notes

Billing is based on duration; longer durations result in higher costs

Example5

qualitystringOptionalDefault: 720p

Video resolution.

Value	Description
480p	Lower resolution, lower pricing
720p	Standard definition (default)
1080p	High definition, higher pricing

Example720p

aspect_ratiostringOptionalDefault: 16:9

Video aspect ratio.

Value	Description
16:9	Landscape video (default for text-to-video)
9:16	Portrait video
1:1	Square video
4:3	Standard video
3:4	Portrait standard
21:9	Ultra-wide video
adaptive	Adaptive ratio (default for image-to-video)

Example'16:9'

generate_audiobooleanOptionalDefault: true

Whether to generate audio. Enabling will increase cost.

Value	Description
true	Video includes synchronized audio (voice, sound effects, background music)
false	Video is silent

Notes

Place dialogue within double quotes in prompt to optimize audio generation

Exampletrue

callback_urlstringOptional

HTTPS callback address after task completion.

Notes

Triggered on completion, failure, or cancellation
Sent after billing confirmation
HTTPS only, no internal IPs
Max length: 2048 chars
Timeout: 10s, Max 3 retries

Examplehttps://your-domain.com/webhooks/video-task-completed

Request Example

{
  "model": "seedance-2.0",
  "prompt": "A cinematic drone shot over a coastal city at golden hour",
  "image_urls": ["http://example.com/ref1.jpg", "http://example.com/ref2.jpg"],
  "video_urls": ["http://example.com/reference.mp4"],
  "audio_urls": ["http://example.com/reference.mp3"],
  "duration": 10,
  "quality": "1080p",
  "aspect_ratio": "16:9",
  "generate_audio": true
}

Response Example

{
  "created": 1761313744,
  "id": "task-unified-1761313744-vux2jw0k",
  "model": "seedance-2.0",
  "object": "video.generation.task",
  "progress": 0,
  "status": "pending",
  "task_info": {
    "can_cancel": true,
    "estimated_time": 165,
    "video_duration": 8
  },
  "type": "video",
  "usage": {
    "billing_rule": "per_call",
    "credits_reserved": 8,
    "user_group": "default"
  }
}