emaki API

Run Seedance 2.5 and Seedance 2.0 text-to-video and image-to-video from your own code with the API key from emaki.ai.

emaki runs Seedance 2.5, Seedance 2.0 and a handful of image models behind one account. The same API key that the website gives you runs them from your own code: text to video, image to video with a first frame you pass in, and images for that first frame. Finished clips can be sharpened with the AI video upscaler on the site.

日本語での使い方は シーダンス へ。

Start in three steps

1. Sign in on emaki.ai.
2. Create a key at emaki.ai/settings/apikeys.
3. export EMAKI_API_KEY=sk-... and call the API, an SDK or the MCP server.

curl -s -X POST https://emaki.ai/api/video/ai \
  -H "Authorization: Bearer $EMAKI_API_KEY" -H "Content-Type: application/json" \
  -d '{"prompt":"a paper boat drifting on a calm lake at sunrise, slow dolly in","model":"seedance_2_5","parameters":{"duration":5}}'

Every run costs credits on your emaki account, the same price as on the website. Checking the balance is free.

What every client does

1. POST /api/video/ai with a prompt, a model id and parameters; keep the returned id.
2. POST /api/video/status every 5 seconds until status is completed (the file URL is in videoUrl) or failed.

The HTTP API page describes both calls and every error, the models page lists ids and parameters.