AI Video APIAI Video API

Seedance 2.0

View API docs

Seedance 2.0 creates and edits cinematic video from natural-language prompts with text, image, video, and audio references. Reference media can preserve subject identity, composition, and motion while the model rewrites lighting, style, environments, weather, camera feel, or specific scene elements with stable motion and polished visual quality.

Built on ByteDance Seed's unified multimodal architecture and delivered through a ready-to-use REST API, it is designed for fast production workflows, reliable performance, no cold starts, and affordable scaling.

Seedance 2.0

Seedance 2.0 multi-modal video generation. Supports text, image, video, and audio references with configurable duration (4-15s), resolution (480p/720p/1080p), and aspect ratio. · seedance

ParametersLive request

Seedance model to run. Fast supports 480p and 720p only.

Optional webhook URL for task completion or failure notifications.

Text description. Chinese or English, recommended under 500 characters.

Generation mode. first_and_last_frames uses 1-2 images and ignores video/audio URLs.

Reference image URLs. One per line, or JSON array. Up to 9 in omni_reference, 1-2 in first_and_last_frames.

Reference video URLs. One per line. Up to 3 videos, total duration max 15s. Ignored in first_and_last_frames mode.

Reference audio URLs. One per line. Up to 3 audio files, total duration max 15s. Must be combined with image or video.

Video duration in seconds: 4-15.

Output aspect ratio. adaptive lets the model choose based on prompt or reference media.

Output resolution. Seedance 2.0 Fast supports 480p and 720p only.

Generate synchronized audio.

Add watermark to the generated video.

Random seed. Use -1 for a random seed.

Return the last frame image for chaining consecutive videos.

Enable web search for real-time information.

Pricing
210credits
5s
Per second42 credits/s
Modeldoubao-seedance-2.0
Resolution720p
ResultPreview output

Configure parameters and click Run to test the API.

Code Example
curl -X POST https://aivideoapi.ai/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "doubao-seedance-2.0",
  "input": {
    "prompt": "A drone shot flying over mountains at sunset, cinematic lighting",
    "generation_type": "omni_reference",
    "duration": 5,
    "aspect_ratio": "adaptive",
    "resolution": "720p",
    "generate_audio": true,
    "watermark": false,
    "seed": -1,
    "return_last_frame": false,
    "web_search": false
  }
}'

Model capabilities

Reference-driven video generation for production workflows.

Seedance 2.0 is built for short-form generation where prompts and uploaded references work together: first frames, end frames, style images, motion clips, and rhythm references can all guide the final output.

Reference-guided creation

Use product shots, character images, first and last frames, or style references to control visual direction.

Motion and camera transfer

Attach short reference clips so the model can follow movement, composition, rhythm, and transition intent.

Audio-aware generation

Provide music or sound references, or enable synchronized audio generation for richer short-form output.

Multi-shot storytelling

Create short cinematic sequences with stronger scene flow, subject consistency, and production-ready pacing.

API workflow

One endpoint, async delivery, clean task status.

01

Submit a generation task

Send prompt, references, duration, aspect ratio, resolution, and callback URL to the video generation endpoint.

02

Track async progress

Use the returned task ID to poll status, or let the callback deliver completion and failure events.

03

Receive hosted output

Completed tasks return mirrored video URLs and metadata through the same response shape used by other models.

POST /v1/videos/generations
curl -X POST https://api.aivideoapi.ai/v1/videos/generations \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedance-2.0",
    "callback_url": "https://your-app.com/webhooks/video",
    "input": {
      "prompt": "A cinematic product reveal with smooth camera movement",
      "image_urls": ["https://example.com/product.png"],
      "duration": 5,
      "aspect_ratio": "16:9",
      "resolution": "720p",
      "generate_audio": true
    }
  }'

Model options

Standard quality or faster iteration.

Use `doubao-seedance-2.0` for the full resolution range. Use `doubao-seedance-2.0-fast` when you want lower-cost drafts and rapid batch testing.

Seedance 2.0

Best for production output, 1080p clips, and final creative runs.

Resolution
No video ref
With video ref
480p
20 credits/s
12 credits/s
720p
42 credits/s
25 credits/s
1080p
102 credits/s
62 credits/s

Seedance 2.0 Fast

Optimized for faster, lower-cost exploration at 480p and 720p.

Resolution
No video ref
With video ref
480p
16 credits/s
10 credits/s
720p
33 credits/s
20 credits/s

What teams build

From reference assets to finished clips.

The same API supports lightweight text-to-video prompts and reference-heavy creative pipelines for apps, ad tools, and automated content systems.

Product reveal videos
Short social ads
Character-driven clips
Music and beat-matched edits
Storyboard to video drafts
Reference video remixes
Ready for integration

Start with Seedance 2.0 in the same API you use for other video models.

Create an API key, submit a task, and route generated outputs into your product without building provider-specific plumbing.

Try playground
API-key authenticationCallback supportJSON request body