What is Seedance?

Seedance creates video in three ways. Text-to-video builds a clip from a written prompt. Image-to-video animates a still image used as the first frame, with an optional last frame. Reference-to-video combines several images, clips or audio files to keep a character, product or style consistent.

Since version 1.5 the model generates audio together with the picture, including dialogue with lip-sync, sound effects and ambience. The Seedance 2.5 prompt guide shows how to direct those elements.

ByteDance has shipped four public versions in a little over a year. Seedance 2.0 also comes in cheaper Fast and Mini tiers. For a field-by-field comparison of the two current versions, see Seedance 2.5 vs 2.0.

There are three routes. ByteDance's consumer apps, Dreamina and CapCut, are the official way to use it. Developers call it through API providers; the Seedance 2.5 API guide covers prices and code. Independent workspaces such as this site wrap those APIs in a browser generator and charge credits.

Seedance is a paid model, and some platforms advertise starter credits subject to account eligibility. Paid use is billed per second of video, and the price rises with resolution. See Seedance 2.5 free for how starter credits work here and Seedance 2.5 pricing for the full credit table.