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.
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.
One multimodal model that understands motion, sound and reference material together — so your result feels directed, not generated.
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.
Dialogue, ambience and synchronized sound effects are generated alongside the video — no separate audio pipeline required.
Describe shot scale, camera movement and scene rhythm in plain language. Wide tracking, close portrait, rear follow — one prompt sets the performance.
Fast bodies, changing poses and moving cameras stay consistent — subjects hold their identity through an active scene.
Animate an existing image while keeping composition, identity and texture — or transfer motion from a reference clip to your own characters.
From full-quality 4K finals to fast 480p previews, pick the model tier that matches your iteration loop and your budget.
Motion and audio are generated together in a unified architecture, so pacing, atmosphere and on-screen events stay in sync.
Maintain coherent subjects and believable movement through an active scene.
Align atmosphere, sound cues and on-screen events into one result.
Use sound to strengthen pacing, emotion and perceived realism.
Communicate shot scale, camera behavior and scene rhythm in a single generation — no separate tools or keyframes.
Guide performance with references, or animate an existing image while preserving the details that matter.
Combine motion structure, character appearance and visual style in one generation.

Animate illustrations while preserving subject, composition and the original visual language.
Seedance 2.0 on DreamAPI comes in three tiers — the same architecture, tuned for different stages of production.
The full-quality flagship. Standard speed, highest fidelity — built for professional content creation at 1080p and native 4K.
Accelerated generation for rapid iteration. Good quality at a fraction of the credits — ideal for previews and A/B testing.
The budget tier. Fast, affordable generations for drafts, thumbnails and high-volume social pipelines.
Production-ready video for every pipeline — ads, previs, social and entertainment.
Build product films and campaign concepts without a traditional shoot.
Turn storyboards and references into moving creative direction.
Create high-impact vertical sequences for rapid iteration.
Develop characters, worlds and narrative moments with control.
Submit a generation job through DreamAPI, poll its status, then retrieve the finished video. Async by design — built for production workloads.
Send prompt plus any references — image, video, audio — in one JSON request.
Check progress with the task ID while rendering runs in the background.
Download the finished clip with synchronized audio included.
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())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 uses DreamAPI credits and varies by model version and output resolution. Pay only for what you generate.
All plans start with free generations. No card required to try.
Seedance 2.0 is a multimodal AI video generation model that accepts text, image, video and audio references — available through the DreamAPI developer platform.
It can combine several reference types to guide character, performance, environment, timing and sound in a single generation.
Yes. Seedance 2.0 supports audio-video joint generation, so dialogue, ambience and sound effects sync with the visuals natively.
Rates vary by model version and output resolution, billed in DreamAPI credits. See the pricing table above for current rates.
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.
Turn every kind of inspiration into a story worth watching.