Seedance 2.5 Text to Video
Seedance 2.5 Text to Video is ByteDance's next-generation video model, turning a written brief into a single continuous take of up to 30 seconds — with dialogue, effects and ambience generated in the same pass. It renders up to native 4K and, when you need it, follows up to 30 reference images plus video and audio references for characters, products and motion.
Input
Describe the scene, action, camera movement, lighting, mood and sound for the video.
Optional images (up to 30) to guide characters, products, style or composition.
0 / 30
Optional clips (up to 10, 30 s in total) for motion or camera reference. Using them switches to per-second billing on output plus reference length.
0 / 10
Optional audio clips (up to 10, 30 s in total) for voice, music or rhythm reference.
0 / 10
Output aspect ratio.
Output resolution. Higher resolutions cost more per second.
Video length in seconds (4-30), generated as one continuous take.
Generate native, synchronised audio with the video. Does not change the price.
Output
Run the model to see output here.
Pricing
Features
API Examples
curl -X POST \
/api/v1/model/bytedance/seedance-2.5-text-to-video \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {}
}'