Seedance 2.0 (Native)
Seedance 2.0 Pro is ByteDance's flagship text-to-video model — strong prompt adherence, natural motion, and optional multimodal references (images, videos, audio) to lock identity, style, and rhythm. This is the native ByteDance ModelArk endpoint; the WaveSpeed-routed siblings stay in the catalogue for users that already point at them.
Input
Describe the scene, action, camera movement and mood for the video.
Reference image URLs that guide visual style, characters or scene composition (0–9).
0 / 9
Reference video URLs (max 3, total length ≤ 15 s).
0 / 3
Reference audio URLs (max 3, total length ≤ 15 s).
0 / 3
Aspect ratio of the generated video.
Output video resolution.
Video duration in seconds (2–15).
Random seed. Pass -1 for a fresh seed every call.
Render a synchronized audio track alongside the video.
Lock the camera (best-effort hint appended to the prompt).
Embed a small platform watermark in the lower-right corner.
Output
Run the model to see output here.
Pricing
Features
API Examples
curl -X POST \
/api/v1/model/bytedance/seedance-2.0-text-to-video-native \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {}
}'