Doubao-Seedance-2.5 - ByteDance AI Video Model (China)
Doubao-Seedance-2.5 is ByteDance's Seedance 2.5 video model on Volcano Ark. Build prompts and ModelArk API requests for 30-second, audio-synced video free.
Describe your scene — Seedance 2.5 generates up to 30 seconds of native audio-visual output.
Tip: put spoken dialogue in "double quotes" for better synced audio.
a cinematic scene. with natural ambient sound.
{
"model": "dreamina-seedance-2-5-260628",
"content": [
{
"type": "text",
"text": "a cinematic scene. with natural ambient sound."
}
],
"resolution": "720p",
"ratio": "16:9",
"duration": 10,
"generate_audio": true,
"camera_fixed": false,
"output_format": "mp4"
}Your files are processed locally in your browser. Nothing is uploaded to any server.
How to Use Doubao-Seedance-2.5
Select the Model
Doubao-Seedance-2.5 is the China-region name for Seedance 2.5. Use the model ID doubao-seedance-2-5-260628 when calling the Volcano Ark (ModelArk) API.
Build Your Shot
Describe the scene, choose ratio, resolution and duration up to 30 seconds, and toggle native audio. The builder assembles the full request body.
Generate the Video
Copy the prompt or JSON and send it to ModelArk. Doubao-Seedance-2.5 and the global Dreamina-Seedance-2.5 share the same underlying model and version.
Doubao-Seedance-2.5 FAQ
What is Doubao-Seedance-2.5?
Doubao-Seedance-2.5 is the China-region product name for ByteDance's Seedance 2.5 video generation model, served through the Volcano Ark (ModelArk) platform. The call name is doubao-seedance-2-5-260628. Internationally the same model is offered as Dreamina-Seedance-2.5.
How is it different from the global version?
There is no capability difference — Doubao-Seedance-2.5 (China) and Dreamina-Seedance-2.5 (global) are the same model and version 260628. Only the product name and the region endpoint differ, so prompts and request bodies transfer directly between them.
What can Doubao-Seedance-2.5 do?
It generates up to 30-second clips with synchronized native audio, supports text-to-video and image-to-video, accepts up to 30 reference images plus reference video and audio, and offers first/last frame and camera control. Output is available as mp4 or high-color mov.