Call 4 ByteDance models through one Aibubu API, try them in the playground, and pay per call in credits.
4 models
Videoseedance-2
Unified audio-video generation with text, image, video and audio references, producing clips up to 15 seconds with stereo audio.
Videoseedance-2-fast
A faster Seedance 2 variant for text, reference-image and reference-video generation, built for quick shot iteration.
Videoseedance-2-mini
A lighter Seedance 2.0 video model that generates audio-video clips up to 15 seconds at 480p or 720p from text, reference images or reference videos.
Videoseedance-2-5
Seedance 2.5 generates audio-video clips up to 30 seconds with multi-round extension, accepts up to 30 images, 10 videos and 10 audio clips as references, and supports timestamp-level editing.
Create an API key in the console, set model to any model ID below, and submit to the same endpoint. Every model page has copy-ready code.
The capability labels and tagline on each card describe what a model does best. Open a model page to see examples and try it online.
Compare price tiers and supported resolutions and durations. Pick the higher tier for quality and the lighter one for speed and cost. The Price tab on each model page lists every tier.
One API key reaches models from many providers with the same request format, task polling and webhooks, billed per call in credits, with no separate integrations or top-ups.
