HappyHorse 1.0 is now liveTry it now
EvoLink.AIEvoLink.AI

Seedance 2.0 API

Seedance 2.0 is ByteDance's second-generation video model for multimodal video generation, now with full real human video support. Available globally through EvoLink with per-second billing.
Model Type:
Text to VideoImage to VideoReference to Video
Fast Text to VideoFast Image to Video✓Fast Reference to Video

Price: $0.045 - 0.402(~ 3.029 - 27.3375 credits) per second of video

With video input: billed on (input+output) duration at reduced rate. Min billable input = output duration.

Highest stability with guaranteed 99.9% uptime. Recommended for production environments.

Use the same API endpoint for all versions. Only the model parameter differs.

Need inspiration? Browse Seedance 2.0 prompts
970 (suggested: 2,000)

Up to 9 images (jpg/png/webp, ≤30MB each, 300-6000px, aspect ratio 0.4-2.5). Use prompt to assign roles (e.g., "image 1 as first frame"). Total request body ≤ 64MB.

Click to upload or drag and drop

Supported formats: JPG, JPEG, PNG, WEBP
Maximum file size: 30MB; Maximum files: 9

Up to 3 videos (mp4/mov, ≤50MB each, 480p/720p, 2-15s per clip, total ≤15s, 24-60 FPS). Aspect ratio 0.4-2.5, 300-6000px per side, frame pixels 409,600-927,408. Video input duration is billed.

Click to upload or drag and drop

Supported formats: MP4, MOV
Maximum file size: 50MB; Maximum files: 3

Up to 3 tracks (mp3/wav, ≤15MB each, 2-15s per clip, total ≤15s). ⚠️ Cannot be used alone — at least 1 image or video is required.

Click to upload or drag and drop

Supported formats: MP3, WAV
Maximum file size: 15MB; Duration: max 16s

5s
4s15s

Generate synchronized audio. No extra charge.

0:00 / 0:00
Audio

History

Max 20 items

0 running · 0 completed

Your generation history will appear here

Billing Rules

  • •Without video input: billed per second of output video only.
  • •With video input: input video duration is also billed — both input and output seconds are charged at a reduced per-second rate (see pricing table).
  • •Minimum billable input duration = output duration (e.g., 3s input + 10s output → billed as 10s + 10s = 20s).
  • •Output duration range: 4–15 seconds.
  • •Audio generation: included at no extra charge.
  • •Supports: up to 9 images, 3 videos (≤15s total), 3 audio tracks (≤15s total).

Pricing

Seedance 2.0 Fast Reference to Video
Video Generation (Fast)
Quality:480p
Video Input:No
Price:
$0.075/ second
(5.08478 Credits)
Seedance 2.0 Fast Reference to Video
Video Generation (Fast)
Quality:720p
Video Input:No
Price:
$0.161/ second
(10.935 Credits)
Seedance 2.0 Fast Reference to VideoComing soon
Video Generation (Fast)
Quality:1080p
Video Input:No
Price:
$0.402/ second
(27.3375 Credits)
Seedance 2.0 Fast Reference to Video
Video Generation (Fast)
Quality:480p
Video Input:Yes (input+output)
Price:
$0.045/ second
(3.029 Credits)
Seedance 2.0 Fast Reference to Video
Video Generation (Fast)
Quality:720p
Video Input:Yes (input+output)
Price:
$0.096/ second
(6.50633 Credits)
Seedance 2.0 Fast Reference to VideoComing soon
Video Generation (Fast)
Quality:1080p
Video Input:Yes (input+output)
Price:
$0.240/ second
(16.29315 Credits)

If it's down, we automatically use the next cheapest available—ensuring 99.9% uptime at the best possible price.

ByteDance Seedance 2.0 API and AI Video Generator

Use the Seedance 2.0 API to run ByteDance Seedance as an AI video generator for text, image, video, and audio inputs — including real human video generation with lifelike faces, expressions, and full-body motion. This Seedance video generator adds the @-reference system, synchronized audio, video-to-video editing, and up to 15-second generation, while the Pricing tab helps you compare current Seedance price options.

ByteDance Seedance 2.0 AI video generator and API 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.

Seedance 2.0 Real Human Video Generation

Seedance 2.0 now fully supports real human video generation through EvoLink's API. Upload a portrait photo and generate video with lifelike facial expressions, natural micro-expressions, full-body motion including dance and athletics, and multi-language lip-synced dialogue. Ideal for face-led ads, spokesperson content, influencer-style creative, and realistic portrait storytelling.

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 Real Human Video Support

Seedance 2.0 on EvoLink fully supports real human video generation — upload a portrait photo and produce video with lifelike expressions, full-body motion, and multi-language lip-sync. This is a capability that remains limited or restricted on competing platforms like Kling 3.0 and Sora 2.

Seedance 2.0 API Competitive Pricing via EvoLink

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

Seedance 2.0 vs Kling 3.0 vs Sora 2

FeatureSeedance 2.0Kling 3.0Sora 2
EvoLink priceFrom $0.092/s$0.079/s$0.08/s
Current route quality480p / 720p / 1080p720p / 1080p720p
Native audioYesAI sound effectsYes (synchronized)
Reference controlText + image + video + audioText + imageText + image
Video length4-15s3-15s4 / 8 / 12s
Real human videoFull supportLimitedLimited
Best forPremium multimodal control, directed production, real human videoGeneral-purpose video, per-second billingOpenAI ecosystem, longer clips

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.

1

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.

2

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.

3

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 Output

The current EvoLink Seedance 2.0 route exposes 480p, 720p, and 1080p quality options, depending on mode and pricing.

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.

Human

Real Human Video Generation

Generate realistic videos of real people from reference photos. Supports lifelike facial expressions, micro-expressions, full-body motion, and multi-language lip-synced dialogue.

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 through EvoLink. On the current public route, text-to-video pricing is exposed at 480p, 720p, and 1080p, and audio generation is included at no extra charge. Check the pricing table above for the exact current per-second rates.
Yes. EvoLink provides Seedance 2.0 API access to developers worldwide. You can integrate using a single API key. For details on supported regions and any access considerations, see the Seedance 2.0 API access guide.
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.
On the current EvoLink route, output videos are in MP4 format (H.264) with AAC audio. Supported quality options are 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.
Yes. Seedance 2.0 on EvoLink fully supports real human video generation. Upload a portrait photo as a reference and generate video with lifelike facial expressions, natural micro-expressions, full-body motion (dance, athletics, gestures), and multi-language lip-synced dialogue. This makes it one of the strongest AI models for face-led ads, spokesperson content, and realistic portrait storytelling.
Seedance 2.0 is one of the stronger options for complex human motion such as dance and athletics. Combined with its @-reference system and native audio lip-sync, it supports a broader real human video workflow than Kling 3.0 or Sora 2, which have more limited support for real person reference inputs.

All Seedance API Models

EvoLink provides unified API access to the full Seedance model family: All models share the same Seedance API endpoint. Switch models with one parameter.

Explore Seedance familyView Seedance 1.5 ProView Seedance 1.0 Pro Fast
POST
/v1/videos/generations

Create Fast Reference-to-Video

Fast multimodal reference-to-video generation using Seedance 2.0.

Now supports AIGC-generated realistic human materials.

Asynchronous processing — use the returned task ID to query status. Video links are valid for 24 hours.

Request Parameters

modelstringRequiredDefault: seedance-2.0-fast-reference-to-video

Fixed value: seedance-2.0-fast-reference-to-video

Exampleseedance-2.0-fast-reference-to-video
promptstringOptional

Text prompt describing the video. Use natural language to assign roles to references.

Notes
  • Example: 'Use video 1 camera movement, image 1 as style reference, audio 1 as background music'
  • Chinese: ≤ 500 characters, English: ≤ 1000 words
ExampleUse the camera movement from video 1, with image 1 as style reference
image_urlsarrayOptional

Reference image URLs (0-9 images).

Notes
  • Formats: .jpeg, .png, .webp
  • Aspect ratio (width/height): 0.4 ~ 2.5
  • Width/height pixels: 300 ~ 6000 px
  • Max 30MB per image
  • Total request body ≤ 64MB, do not use Base64
  • Cannot provide only audio_urls — at least 1 image or 1 video is required
Example["https://example.com/ref1.jpg", "https://example.com/ref2.jpg"]
video_urlsarrayOptional

Reference video URLs (0-3 videos).

Notes
  • Formats: .mp4, .mov
  • Resolution: 480p or 720p
  • Duration: 2-15s per video, max 3 videos, total ≤ 15s
  • Aspect ratio (width/height): 0.4 ~ 2.5
  • Width/height pixels: 300 ~ 6000 px
  • Frame pixels (width × height): 409,600 ~ 927,408 (e.g., 640×640 ~ 834×1112)
  • Max 50MB per video, 24-60 FPS
  • Video input duration is counted in billing
Example["https://example.com/reference.mp4"]
audio_urlsarrayOptional

Reference audio URLs (0-3 clips).

Notes
  • Formats: .wav, .mp3
  • Duration: 2-15s per clip, max 3 clips, total ≤ 15s
  • Max 15MB per clip
  • Cannot be used alone — at least 1 image or 1 video must be included
Example["https://example.com/bgm.mp3"]
durationintegerOptionalDefault: 5

Output video duration in seconds.

ValueDescription
4-15Any integer between 4 and 15
Notes
  • Duration directly affects billing
Example10
qualitystringOptionalDefault: 720p

Video resolution.

ValueDescription
480pLower resolution
720pStandard (default)
Notes
  • 1080p resolution coming soon
Example720p
aspect_ratiostringOptionalDefault: 16:9

Video aspect ratio. 'adaptive' auto-selects based on input (video > image > prompt).

ValueDescription
16:9Landscape (1280×720 / 864×496)
9:16Portrait (720×1280 / 496×864)
1:1Square (960×960 / 640×640)
4:3Standard (1112×834 / 752×560)
3:4Portrait standard (834×1112 / 560×752)
21:9Ultrawide (1470×630 / 992×432)
adaptiveAuto-detect from input
Example16:9
generate_audiobooleanOptionalDefault: true

Whether to generate synchronized audio. No extra charge.

Exampletrue
callback_urlstringOptional

HTTPS callback URL for task completion notification.

Examplehttps://your-domain.com/webhooks/video-done

Request Example (Multimodal Reference)

{
  "model": "seedance-2.0-fast-reference-to-video",
  "prompt": "Use video 1 camera movement, audio 1 as background music. Product showcase ad.",
  "image_urls": ["https://example.com/ref1.jpg", "https://example.com/ref2.jpg"],
  "video_urls": ["https://example.com/reference.mp4"],
  "audio_urls": ["https://example.com/bgm.mp3"],
  "duration": 10,
  "quality": "720p",
  "aspect_ratio": "16:9"
}

Request Example (Video Extension)

{
  "model": "seedance-2.0-fast-reference-to-video",
  "prompt": "Continue the scene, camera enters the room through the window",
  "video_urls": [
    "https://example.com/part1.mp4",
    "https://example.com/part2.mp4"
  ],
  "duration": 8,
  "generate_audio": true
}

Response Example

{
  "created": 1761313744,
  "id": "task-unified-1761313744-abc123",
  "model": "seedance-2.0-fast-reference-to-video",
  "object": "video.generation.task",
  "progress": 0,
  "status": "pending",
  "type": "video"
}
Seedance 2.0 API | Pricing, Access & ByteDance AI Video | EvoLink