Available Endpoints
Start building with the Seedance 2.0 API
Multiple endpoints for text-to-video, image-to-video, and reference-to-video generation, including optimized fast variants.
ByteDance's most advanced video generation model, launched April 9, 2026. Cinematic output with native audio, real-world physics, and director-level camera control. Accepts text, image, audio, and video inputs.
Multiple endpoints for text-to-video, image-to-video, and reference-to-video generation, including optimized fast variants.
The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.
import { fal } from "@fal-ai/client";
const result = await fal.subscribe("bytedance/seedance-2.0/text-to-video", {
input: {
prompt: "An octopus throws a football in the ocean",
duration: "5",
resolution: "720p",
},
logs: true,
onQueueUpdate: (update) => {
if (update.status === "IN_PROGRESS") {
update.logs.map((log) => log.message).forEach(console.log);
}
},
});
console.log(result.data);
console.log(result.requestId);The model handles complex camera work that other models struggle with. Dolly zooms, rack focuses, tracking shots, POV switches, and smooth handheld movement all work as expected. You describe the shot, and the camera executes it.
Fight scenes, vehicle chases, explosions, falling debris. Seedance 2.0 understands how objects interact under force. Collisions have weight, fabric tears realistically, and characters move with physical believability even in high-action sequences.
fal is the official Seedance 2.0 API, supporting two tiers so you can pick the right balance of quality, speed, and cost for your workflow.
US companies can now run Seedance 2.0 on infrastructure hosted entirely in the United States. US hosting is available at 480p and 720p with its own pricing, and our team coordinates access for each account.
Seedance 2.0 runs on US-hosted infrastructure at 480p and 720p today. 1080p support is planned.
Available to US companies, with Seedance 2.0 hosted entirely on US infrastructure. Faces and additional IP permissions are subject to a separate approval process.
US hosting has different pricing from standard Seedance 2.0. Request access and our team will confirm pricing, contract details, and setup for your account.
From film studios to fashion brands, teams across industries are building with Seedance 2.0 on fal.
World class luxury look and feel all rendered within minutes. Seedance 2.0 brings photorealistic textures, lighting, and spatial depth to architectural visualization and interior design workflows.
Studios and independent filmmakers can generate storyboard-quality pre-visualization content directly from a script or shot list. Camera moves, lighting moods, and action sequences can be previewed before a single frame is shot, cutting pre-production timelines significantly.
Turn on audio to hear the native sound generation. Every example below was generated in a single pass with no post-production.
"Camera follows a man in black sprinting through a crowded street, a group chasing close behind. The shot cuts to a side tracking angle as he panics and crashes into a roadside fruit stall, scrambles to his feet, and keeps running. Sounds of a frantic crowd"
"A spear-wielding warrior clashes with a dual-blade fighter in a maple leaf forest. Autumn leaves scatter on each impact. Wide shot pulls into tight close-ups of parrying blades, then cuts to a slow-motion overhead as both leap into the air"
"Spy thriller style. Front-tracking shot of a female agent in a red trench coat walking forward through a busy street, pedestrians constantly crossing in front of her. She rounds a corner and disappears. A masked girl lurks at the corner, glaring after her. Camera pans forward as the agent walks into a mansion and vanishes. Single continuous take, no cuts"
"15s commercial. Shot 1: side angle, a donkey rides a motorcycle bursting through a barn fence, chickens scatter. Shot 2: close-up of spinning tires on sand, then aerial shot of the donkey doing donuts, dust clouds rising. Shot 3: snow mountain backdrop, the donkey launches off a hillside, text 'Inspire Creativity, Enrich Life' revealed behind it as dust settles"
Send a POST request to any Seedance 2.0 endpoint with your prompt and parameters. The fal serverless infrastructure handles GPU allocation, inference, and scaling automatically. You get back a URL to the generated video. Use the Python or JavaScript SDK for the simplest integration, or call the REST API directly.
Input: text prompts, images (JPEG, PNG, WebP), video files (MP4, MOV), and audio files (WAV, MP3). Output: MP4 video with synchronized audio. Resolutions: 480p and 720p. Durations: 4 to 15 seconds. Aspect ratios: 21:9, 16:9, 4:3, 1:1, 3:4, and 9:16.
Get up and running in minutes. No GPUs to manage, no infrastructure to set up.
Pick your package manager. For Python, use pip.
npm install --save @fal-ai/client
Sign up to get access to the dashboard and your API keys.
Locate your API credentials in the developer dashboard. Set FAL_KEY as an environment variable in your runtime.
Use fal.subscribe() to submit your request with a prompt and parameters. The client handles the async queue automatically, providing progress updates via onQueueUpdate, and returns the final video URL when generation is complete.
Start generating Seedance 2.0 videos instantly in the playground. No API key needed, just describe your scene and hit generate.
Open Playground →Grab an API key from your dashboard and integrate Seedance 2.0 into your app with a few lines of code. Python and JavaScript SDKs available, plus a REST API for any language.
Get API Key →Prompting techniques, audio-video generation, image-to-video, reference-to-video, multi-shot workflows, and pricing explained.
Read the Guide →Want to learn more about integrating Seedance 2.0 into your workflow? Leave your details and our team will reach out.
Seedance 2.0 generates audio natively alongside video. Music carries deep bass and cinematic warmth. Dialogue is clear with precise lip-sync. Sound effects land exactly on cue. No post-production audio layering needed.
Brands can generate polished, on-brief video assets from a single prompt. Product showcases, lifestyle sequences, and cinematic brand ad spots, produced at the speed of a prompt, not a shoot.
Game studios can use Seedance 2.0 to generate high-fidelity cinematic sequences, environmental previews, and in-engine concept footage — all without a dedicated animation pipeline.
Generate editorial-quality video content without booking a studio, a crew, or a location. Seedance 2.0 handles fabric movement, lighting, and texture with cinematic precision — ideal for lookbooks, campaign content, seasonal drops, and digital runway presentations.
Seedance 2.0 can replicate the handheld, lo-fi aesthetic of user-generated content while maintaining full creative control. Generate UGC-style video that feels organic and platform-native — ideal for TikTok, Instagram Reels, and YouTube Shorts.
Generations complete in under 2 minutes. Fast-tier endpoints offer lower latency and cost for production workloads. Standard-tier endpoints prioritize maximum quality. Both tiers run on fal's serverless infrastructure with automatic scaling and no cold starts for sustained traffic.
Seedance 2.0 is available now on fal as of April 9th, 2026. You can start generating videos immediately in the playground with no setup required. If you are a developer looking to integrate via API, sign up and grab an API key from your dashboard, then use the Python or JavaScript SDK, or call the REST API directly.
The Seedance 2.0 API is available globally through fal's infrastructure. Developers and enterprises in any country can access and integrate the API into their applications.
Yes. US hosting for Seedance 2.0 is live on fal. US companies can run Seedance 2.0 on infrastructure hosted entirely in the United States at 480p and 720p, with separate pricing and team-coordinated onboarding. Learn more and request US access.
Seedance 2.0 is ByteDance's latest video generation model. It uses a unified multimodal audio-video architecture that accepts text, image, audio, and video inputs. It generates cinematic video with native audio, multi-shot cuts, and realistic physics in a single generation.
Seedance 2.0 accepts text prompts, reference images, audio clips, and video inputs. You can combine these to control the output. For example, provide a reference image for visual style, an audio clip for the soundtrack, and a text prompt for the scene description.
Seedance 2.0 generates videos up to 15 seconds in a single generation. Within that duration, the model can produce multiple shots with natural cuts and transitions, so a single output can feel like an edited sequence rather than a single continuous clip.
The audio quality is a standout feature. Music has deep bass and cinematic presence. Dialogue is clear with accurate lip-sync. Sound effects are contextually appropriate and well-timed. The model generates audio natively alongside the video, so everything stays in sync without post-production.
Yes. Seedance 2.5 is ByteDance's next-generation video model and is available on fal today. It generates native 30-second video at super high resolution and combines up to 50 multimodal references in a single generation. Seedance 2.0 remains available and is the faster, shorter-form option.
