ByteDance

Seedance 2.0

ByteDance's text to video model with dialogue, ambience and effects generated in sync with the picture.

Use it for people, performance and anything that needs sound. It follows multi-beat prompts well: describe the action in order and it keeps the order.

Clip length
4 to 15 seconds
Aspect ratios
16:9, 9:16, 1:1, 4:3, 3:4, 21:9
Modes
Text to video
Audio
Generated with the picture
480p
7 credits/s
720p
14 credits/s
1080p
34 credits/s

Frame Nest is an independent AI video creation platform. Model names such as HappyHorse, Seedance, Sora, Veo and Wan are referenced only to describe supported generation options. Frame Nest is not affiliated with, endorsed by, or sponsored by the model owners or their respective providers unless explicitly stated.