Dream in motion.
Generate the rest.

AI video generation, one API away.

DreamAPI is the developer platform for AI video generation. Turn text, images, video and audio references into production-ready 4K clips — with native sound, in a single API call.

Capabilities

More than video.
A complete audiovisual engine.

One multimodal model that understands motion, sound and reference material together — so your result feels directed, not generated.

Multimodal inputs

Feed text, images, video and audio in the same request. The model fuses them into one coherent scene instead of treating them as separate steps.

Native audio co-generation

Dialogue, ambience and synchronized sound effects are generated alongside the video — no separate audio pipeline required.

Director-grade camera control

Describe shot scale, camera movement and scene rhythm in plain language. Wide tracking, close portrait, rear follow — one prompt sets the performance.

High-motion stability

Fast bodies, changing poses and moving cameras stay consistent — subjects hold their identity through an active scene.

Reference & preservation

Animate an existing image while keeping composition, identity and texture — or transfer motion from a reference clip to your own characters.

Speed tiers for every stage

From full-quality 4K finals to fast 480p previews, pick the model tier that matches your iteration loop and your budget.

The experience

Scene, rhythm, sound.

Motion and audio are generated together in a unified architecture, so pacing, atmosphere and on-screen events stay in sync.

Tap the video to hear generated audioTap for sound
01

Motion stability

Maintain coherent subjects and believable movement through an active scene.

02

Audio-visual sync

Align atmosphere, sound cues and on-screen events into one result.

03

Natural ambience

Use sound to strengthen pacing, emotion and perceived realism.

Direction

Set the performance.
Shape the light.
Move the camera.

Communicate shot scale, camera behavior and scene rhythm in a single generation — no separate tools or keyframes.

Director promptThree-panel cinematic sequence: side tracking shot, close portrait, rear follow shot in the rain.
Tap for sound
Wide / trackingMedium / portraitRear / follow
02
Text to videoCamera control
Reference control

Bring more than a prompt.

Guide performance with references, or animate an existing image while preserving the details that matter.

Tap for sound
01
Multimodal referencePerformance transfer
Reference control

From motion sketch to finished characters.

Combine motion structure, character appearance and visual style in one generation.

MotionCharactersStyle
InputOriginal cat, flowers and butterfly illustration
Output
Tap for sound
Preservation + editing

Keep the artwork. Add the motion.

Animate illustrations while preserving subject, composition and the original visual language.

CompositionIdentityTexture
Models

One flagship. Three speeds.

Seedance 2.0 on DreamAPI comes in three tiers — the same architecture, tuned for different stages of production.

seedance-2.0

The full-quality flagship. Standard speed, highest fidelity — built for professional content creation at 1080p and native 4K.

4K supportHighest quality

seedance-2.0-fast

Accelerated generation for rapid iteration. Good quality at a fraction of the credits — ideal for previews and A/B testing.

480p720p

seedance-2.0-mini

The budget tier. Fast, affordable generations for drafts, thumbnails and high-volume social pipelines.

480p720p
Use cases

From an idea to something people watch.

Production-ready video for every pipeline — ads, previs, social and entertainment.

Tap for sound
AD

Advertising

Build product films and campaign concepts without a traditional shoot.

Tap for sound
FILM

Previsualization

Turn storyboards and references into moving creative direction.

Tap for sound
SOCIAL

Short-form content

Create high-impact vertical sequences for rapid iteration.

Tap for sound
IP

Entertainment

Develop characters, worlds and narrative moments with control.

Developer API

One request.
Every input.

Submit a generation job through DreamAPI, poll its status, then retrieve the finished video. Async by design — built for production workloads.

01

Submit a task

Send prompt plus any references — image, video, audio — in one JSON request.

02

Poll the status

Check progress with the task ID while rendering runs in the background.

03

Retrieve the video

Download the finished clip with synchronized audio included.

View API documentation
generate
const response = await fetch('https://api.newportai.com/api/async/seedance_2.0', {
  method: 'POST',
  headers: {
    'Authorization': `Bearer ${process.env.DREAMAPI_KEY}`,
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'seedance-2.0',
    prompt: 'A girl dancing in a park on a sunny day with trees and benches in the background',
    resolution: '720p',
    ratio: 'adaptive',
    duration: 8,
    seed: -1,
    generateAudio: false
  })
});
const { data: { taskId } } = await response.json();
curl -X POST 'https://api.newportai.com/api/async/seedance_2.0' \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer {{key}}' \
  -d '{
    "model": "seedance-2.0",
    "prompt": "A girl dancing in a park on a sunny day with trees and benches in the background",
    "resolution": "720p",
    "ratio": "adaptive",
    "duration": 8,
    "seed": -1,
    "generateAudio": false
  }'
HttpClient client = HttpClient.newHttpClient();
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.newportai.com/api/async/seedance_2.0"))
    .header("Content-Type", "application/json")
    .header("Authorization", "Bearer {{key}}")
    .POST(HttpRequest.BodyPublishers.ofString("{\"model\":\"seedance-2.0\",\"prompt\":\"A girl dancing in a park on a sunny day with trees and benches in the background\",\"resolution\":\"720p\",\"ratio\":\"adaptive\",\"duration\":8,\"seed\":-1,\"generateAudio\":false}"))
    .build();
HttpResponse<String> res = client.send(request, HttpResponse.BodyHandlers.ofString());
import requests

response = requests.post(
    "https://api.newportai.com/api/async/seedance_2.0",
    headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer {{key}}"
    },
    json={
        "model": "seedance-2.0",
        "prompt": "A girl dancing in a park on a sunny day with trees and benches in the background",
        "resolution": "720p",
        "ratio": "adaptive",
        "duration": 8,
        "seed": -1,
        "generateAudio": False
    }
)
print(response.json())
Pricing plans

Top up credits.
Pay as you generate.

One credit pool for every model on DreamAPI — video, image, avatar and editing. Buy a pack, then spend credits at the per-model rates below.

Credit packs are purchased on the DreamAPI pricing page.

Pricing

Choose the right generation mode.

Pricing uses DreamAPI credits and varies by model version and output resolution. Pay only for what you generate.

Seedance 2.0 — credits per second

Limited-time offerEnds Oct 6, 2026

Pricing Formula

Text to VideoCredits = Base Credits × Duration (seconds)
Image to VideoCredits = Base Credits × Duration (seconds)
Reference To VideoCredits = Output Video Credits × Duration (seconds) + Reference Video Credits × Total Reference Video Duration (seconds)
ModelResolutionT2V / I2V OutputR2V OutputR2V Reference
seedance-2.0480p303010
seedance-2.0720p676723
seedance-2.01080p16516555
seedance-2.04K340340114
seedance-2.0-fast480p2518251897
seedance-2.0-fast720p534053401813
seedance-2.0-mini480p15615652
seedance-2.0-mini720p33133313114

Model comparison

Model versionSpeedQualityUse case
seedance-2.0StandardHighProfessional content creation
seedance-2.0-fastFastGoodQuick iterations, previews
seedance-2.0-miniFastGoodBudget-friendly, quick previews

All plans start with free generations. No card required to try.

FAQ

Before your
first request.

What is Seedance 2.0 on DreamAPI?+

Seedance 2.0 is a multimodal AI video generation model that accepts text, image, video and audio references — available through the DreamAPI developer platform.

What makes it different from standard text-to-video?+

It can combine several reference types to guide character, performance, environment, timing and sound in a single generation.

Can Seedance 2.0 generate audio?+

Yes. Seedance 2.0 supports audio-video joint generation, so dialogue, ambience and sound effects sync with the visuals natively.

How much does the API cost?+

Rates vary by model version and output resolution, billed in DreamAPI credits. See the pricing table above for current rates.

How do I get started?+

Create a DreamAPI account to receive an API key, then submit your first generation with a few lines of code. Free generations are included for new accounts.

Creativity without limits.
Explore what's possible.

Turn every kind of inspiration into a story worth watching.