Private AI
Unified Seedance 2.5 generation from text, start/end frames, multimodal references, or an input video, with native audio and 480p–4K output.
Added Aug 7, 2026
Approx. Price
$0.720 per video
Model Type
both
Generation controls available for this model.
Output Format
Default Duration
5
27 duration options
Aspect Ratio
Default
16:9
Options (6)
Ultra-wide (21:9), Landscape (16:9), Classic (4:3), Square (1:1) +2 more
Used for text and multimodal-reference generation; image and video inputs determine framing.
Duration
Default
5
Options (27)
4 seconds, 5 seconds, 6 seconds, 7 seconds +23 more
Output duration from 4 to 30 seconds
Generate Audio
Default
Yes
Generate synchronized sound effects, ambience, and speech.
Operation
Default
auto
Options (5)
Automatic (from inputs), Text / references to video, Image to video, Video edit +1 more
Automatically infer the operation from inputs, or explicitly select video extension.
No benchmark data is available yet for this model.
Resolution
Default
720p
Options (4)
480p, 720p, 1080p, 4K
Output resolution