Seedance 2.0 Video Generation on AI Gateway
By Steven Van ·
Standard and Fast variants add native audio, reference-to-video, and in-video text rendering, available now via the AI SDK.
Vercel's AI Gateway now offers Bytedance's Seedance 2.0 video generation model, accessible without a separate Bytedance provider account. It comes in two variants: Standard, for the highest quality output, and Fast, which prioritises generation speed and lower cost.
The model holds motion stability and fine detail across frames, including in complex scenes with facial expressions and physical interactions, and generates synchronized audio natively with support for speech in multiple languages and dialects. Beyond text-to-video and image-to-video, it adds:
- Multimodal reference-to-video, combining image, video, and audio inputs as reference material in a single generation
- Video editing and video extension
- Professional camera movements and multi-shot composition
- In-video text rendering
To use it, set the model to bytedance/seedance-2.0 or bytedance/seedance-2.0-fast in the AI SDK, or try it in the AI Gateway Playground.
