Video Official partner

Seedance 2.0 API

Reference-driven video with native 4K output.

Seedance 2.0 is ByteDance's advanced video generation model, and the Seedance 2.0 API brings text to video, image to video, and reference to video together at one endpoint. Generate AI video with synchronized sound, multimodal inputs, and creative control, then receive every generated video through async jobs and webhooks behind one api key — with no separate ByteDance account to manage.

Get API key Read the docs

4K
Native output: 15s
Max clip length: 15
Reference inputs: 8 credits/s
From

Video · example

Playground

Try Seedance 2.0 right here.

model: seedance-2

Prompt

Aspect ratio Duration Resolution

Generate audio

Media inputs

Start image End image Reference images Reference videos Reference audio

Advanced settings

Return last frame Also return the final frame as a still image. Web search Lock camera Disable camera movement. Seed

Estimated cost 64–1672 credits · $0.64–$16.72 Generate in Studio

Output Example

Animate this product photo on a turntable, gentle rotation, studio lighting, subtle reflections — ideal for virtual try on videos.

Capabilities

What's new in Seedance 2.0.

Multimodal reference inputs

The Seedance 2.0 API takes mixed inputs in a single request (text, image, audio, and video inputs): a text prompt, reference images, a short reference clip, and an audio track. Tag each input with a role so the model knows which one drives style, motion, or sound.

Reference to video, your way

Drive a reference to video generation from input image urls, a short reference clip, or audio references, and combine them when a shot needs more than one cue. The same Seedance 2.0 API endpoint also handles plain text to video and image to video generation from static images.

Text to video and image to video

Start from a text prompt for text to video, or animate a still image as the first frame for an image start. Supply both the first and last frames when you want precise frame control over how Seedance 2.0 begins and ends the generated video.

Synchronized native audio generation

Seedance 2.0 performs audio video joint generation, so every clip ships with synchronized audio instead of a silent video output. That native audio covers music, sound effects, beat-aware cuts, and lip-sync, and you can steer it with an audio reference for tighter audio generation.

Direct camera movement with director level control

A single Seedance 2.0 API call can return multiple shots with natural cuts, delivering cinematic video generation that feels edited rather than a single take. Direct camera movement and camera motion with plain language for cinematic output with director level control.

An AI video generator built for realism

Seedance 2.0, ByteDance's flagship video model, improves motion stability and realistic physics over earlier models, holding motion stable through fast action and multi-subject scenes. Reference-driven shots also preserve the original motion of your source clip at maximum quality.

Character consistency across shots

It keeps a character identity stable across movement, angle changes, and scene transitions, so you get consistent characters with believable facial features. That makes the Seedance 2.0 API a fit for realistic human faces in films and ads.

Video editing and extension

Beyond first-pass generation, the Seedance 2.0 API supports video editing and video extension: modify clips, characters, or actions, replace elements, and continue a shot from its first and last frames without regenerating the whole finished video.

Full creative control

Set aspect ratio, video length, and visual style per request for full creative control over each output video. The Seedance 2.0 API exposes the same controls whether you want a quick draft or maximum quality.

Use cases from ad creative to game pre visualization

Teams use the Seedance 2.0 API for cinematic ai video, ad creative, music clips, and virtual try on videos. One advanced video generation model spans every mode you need.

Simple API workflow

Authenticate the Seedance AI API with your api key from an environment variable, then send a POST request with your request body. Each call returns a job you can poll for task status, and the video url arrives by webhook with its asset id.

Free credits and an api key to start

Create an Apiframe account to get an api key and free credits, then call the Seedance 2.0 API right away. New users can try it before adding billing, and the same api key works across every model, including Kling 3.0.

Showcase

See what Seedance 2.0 can create.

Real outputs generated with Seedance 2.0 on Apiframe, each with the prompt behind it.

Try Seedance 2.0

Text to video: a cinematic clip of a chef plating a dessert in a warm restaurant kitchen, slow push-in, soft key light.

Animate this product photo on a turntable, gentle rotation, studio lighting, subtle reflections — ideal for virtual try on videos.

A cinematic clip of a city at dawn, a wide skyline cutting to a close-up of a coffee cup, smooth transition.

A music clip of a dancer moving in sync with an upbeat track, neon-lit interior, beat-matched cuts, audio generated with the clip.

Reference to video: a tracking shot following a cyclist along a coastal road at golden hour, motion matched to a reference video.

Image to video from a first frame: the camera continues past a doorway into a sunlit garden, using its first and last frames.

Pricing

Simple per-second pricing.

8–209 credits per second of output ≈ $0.08–$2.09

The rate depends on the resolution and options you pick.

A 8s clip runs 64–1672 credits (≈ $0.64–$16.72).

You only pay for successful generations. Failed jobs are refunded automatically.
One credit balance across every model on Apiframe, no per-model plans.
Start with free credits. No subscription required.
Volume discounts on larger plans.

See plans and credit packs Provider prices Compare Seedance 2.0 pricing vs fal.ai and others

Specs

At a glance.

Provider ByteDance

Model ID seedance-2

Aspect ratios 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

Resolutions 480p, 720p, 1080p, 4k

Durations 4s, 6s, 8s, 10s, 12s, 15s

Image input Supported

Audio Supported

Avg. time ~180s

Comparison

Seedance 2.0 vs Seedance 2.5 vs Kling 3.0

Seedance 2.0 against its successor and its closest competitor. Pick per job, since all three run on the same API key.

Feature	Seedance 2.0	Seedance 2.5	Kling 3.0
Max resolution	Native 4K	720p	4K mode
Max clip length	15s	30s in a single pass	15s
Reference inputs	Up to 15 (9 images, 3 videos, 3 audio)	Up to 50 (30 images, 10 videos, 10 audio)	Start & end frames
Native audio	Co-generated, optional	Co-generated with lip-sync	Optional
Price from	8 credits/s (≈$0.08)	13 credits/s (≈$0.13)	11 credits/s (≈$0.11)
Best for	4K reference-driven ads and try-on video	Long-form narrative and localization	Multi-shot social & marketing clips

Specs reflect what each model supports on Apiframe today, from the live catalog.

Quickstart

How to call the Seedance 2.0 API.

Send one POST /v2/videos/generate request with your API key. The call returns a jobId you can poll, or pass a webhook_url and the result is pushed to you the moment it's ready.

Swap seedance-2 for any other model and nothing else changes.

Get API key Read the docs

generate.js

const response = await fetch("https://api.apiframe.ai/v2/videos/generate", {
  method: "POST",
  headers: {
    "X-API-Key": "afk_your_api_key_here",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
    "model": "seedance-2",
    "seedanceParams": {
      "resolution": "720p",
      "start_image": "https://example.com/input.jpg",
      "generate_audio": false,
      "end_image": "https://example.com/input.jpg"
    }
  }),
});
const { jobId } = await response.json();
console.log(jobId);

import requests

response = requests.post(
    "https://api.apiframe.ai/v2/videos/generate",
    headers={
        "X-API-Key": "afk_your_api_key_here",
        "Content-Type": "application/json",
    },
    json={
        "prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
        "model": "seedance-2",
        "seedanceParams": {
            "resolution": "720p",
            "start_image": "https://example.com/input.jpg",
            "generate_audio": False,
            "end_image": "https://example.com/input.jpg"
        }
    },
)
print(response.json())  # { "jobId": "...", "status": "QUEUED" }

curl -X POST https://api.apiframe.ai/v2/videos/generate \
  -H "X-API-Key: afk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
        "model": "seedance-2",
        "seedanceParams": {
            "resolution": "720p",
            "start_image": "https://example.com/input.jpg",
            "generate_audio": false,
            "end_image": "https://example.com/input.jpg"
        }
    }'

let job;
do {
  await new Promise((r) => setTimeout(r, 2000));
  job = await fetch("https://api.apiframe.ai/v2/jobs/JOB_ID", {
    headers: { "X-API-Key": "afk_your_api_key_here" },
  }).then((r) => r.json());
} while (job.status !== "COMPLETED" && job.status !== "FAILED");
console.log(job.result);

import requests, time

while True:
    job = requests.get(
        "https://api.apiframe.ai/v2/jobs/JOB_ID",
        headers={"X-API-Key": "afk_your_api_key_here"},
    ).json()
    if job["status"] in ("COMPLETED", "FAILED"):
        break
    time.sleep(2)
print(job["result"])

curl https://api.apiframe.ai/v2/jobs/JOB_ID \
  -H "X-API-Key: afk_your_api_key_here"

Input schema

Every field Seedance 2.0 accepts, with types and defaults. The full reference lives in the docs.

Field	Type	Description
prompt required	string	Text description of what to generate.
model required	string	The model identifier for this endpoint. Default:"seedance-2" · "seedance-2"
seedanceParams.resolution	string	Resolution Default:"720p" · "480p", "720p", "1080p", "4k"
seedanceParams.start_image	string (URL)	Use a still as the first frame of the clip.
seedanceParams.generate_audio	boolean	Generate audio Default:false
seedanceParams.end_image	string (URL)	Optional last frame to control the ending.
seedanceParams.reference_image_urls	string[] (URLs)	Reference images
seedanceParams.reference_video_urls	string[] (URLs)	Reference videos
seedanceParams.reference_audio_urls	string[] (URLs)	Reference audio
seedanceParams.return_last_frame	boolean	Also return the final frame as a still image. Default:false
seedanceParams.web_search	boolean	Web search Default:false
seedanceParams.camera_fixed	boolean	Disable camera movement. Default:false
seedanceParams.seed	number	Reuse a number to reproduce the same result. step 1

Seedance versions

Every Seedance video model on Apiframe. Switch with one parameter.

Use cases

What teams build with Seedance 2.0.

Ad creative & product video

Native 4K output with reference images that pin a product look, plus first/last-frame control for precise openings and endings on brand spots.

Music-driven clips

Audio-video joint generation delivers beat-aware cuts and lip-sync in one pass, steer the soundtrack with a reference audio track.

Virtual try-on & e-commerce

Reference-to-video keeps characters, garments, and products consistent across shots, which is what try-on and catalog video pipelines need.

Film & game pre-visualization

Direct camera movement in plain language and get multi-shot sequences with natural cuts, fast, edited-feeling previz from a text prompt.

Reviews

9,800+ developers. One API.

Real Apiframe reviews from Trustpilot and G2.

Seamless experience, excellent support

Just created 6 videos and the experience has been seamless. Wanted to write a review for appreciation — the customer support has also been excellent. They helped me in some process I was stuck in.

Vaibhav Sharma July 2026 Trustpilot

Stable, easy image & video generation

I like that I can generate images and videos without complicated setup. It works stable and is easy to use even if you are not a big developer. It saves me time and makes the whole process much simpler.

Anakin S. July 2026 G2

Honestly the best AI API

They got every engine possible and it's great to have them all in one place.

Daniel Zborowski July 2026 Trustpilot

Seedance 2.0 questions

What teams ask before shipping with Seedance 2.0. Everything else lives in the docs.

What is Seedance 2.0?

Seedance 2.0 is ByteDance's second-generation, multimodal AI video generator, released in February 2026. It handles text to video, image to video, and reference to video, and produces lifelike, edited-feeling results.

How do I call the Seedance 2.0 API?

Get an api key, store it in an environment variable, and send a POST request to the Seedance 2.0 API. The Seedance AI API uses the same api key for every model, and the Seedance API documentation lists every field you can send. The generation request returns a video task; poll the task endpoint for task status, and the video url is delivered to your webhook.

How do reference images and multimodal inputs work?

Pass reference images, a reference video, or audio as input image urls in the request body, and tag each with a role. The Seedance 2.0 API blends these inputs so a reference to video shot follows your intended framing and pacing.

What is the difference between text to video and image to video?

Text to video starts only from a text prompt, while image to video animates a still image as the first frame. For image to video generation you can also supply the first and last frames for frame control.

Does Seedance 2.0 generate audio?

Yes. Seedance 2.0 does audio video joint generation, so every generated video ships with synchronized audio, produced as native audio: music, sound effects, beat sync, and lip-sync. Provide reference audio to guide audio generation.

Can it produce multiple shots and cinematic output?

A single call can return several shots with natural cuts, giving cinematic output from one generation. This cinematic video generation is why teams reach for the Seedance 2.0 API for cinematic ai video.

How do I control the camera and visual style?

Describe camera movement, camera motion, and camera language directly in your text prompt, and Seedance 2.0 follows it with cinematic precision. You keep creative control over the look, pacing, and framing.

Can Seedance 2.0 edit or extend a video?

Yes. The Seedance 2.0 API supports video editing and video extension: modify clips, replace elements, or continue a shot from its last frame without rebuilding the finished video.

How consistent are characters and faces?

Seedance 2.0 maintains strong character consistency, holding character identity and facial features across shots so you get consistent characters and realistic faces, which is useful for ads and product videos.

What video duration, aspect ratio, and resolution are supported?

The Seedance 2.0 API supports a video duration from 4 to 15 seconds at up to native 4K (3840×2160, 10-bit), across aspect ratios from 21:9 to 9:16. Set the aspect ratio, resolution, and video length per request.

How do I get an api key and free credits?

Create an Apiframe account to get an api key and free credits, then call the Seedance 2.0 API right away. New users start with free credits, so you can test it before adding billing.

How do I track a video task and its status?

Each call returns a job. Poll the task endpoint with the task id and your user id to read task status, and the output video url is returned when the task completes.

How is the Seedance 2.0 API priced?

The Seedance 2.0 API is billed per second of video output, so a longer clip costs proportionally more. Resolution affects the per-second rate, and you can estimate any job before sending the request.

How does Seedance 2.0 compare to other models?

Compared with other ai video generator tools, Seedance 2.0 leads on physical realism, consistent characters, and motion stability while generating audio in the same pass. One model replaces several separate tools in a typical pipeline.

Where can you access it?

You can access Seedance 2.0 through the Apiframe API, as well as ByteDance's CapCut and Dreamina apps. Apiframe gives you one Seedance AI API and key alongside other models.