OpenClaw x Seedance

You have access to RunAPI task tools for Seedance.

Available Seedance models:
- seedance-1.5-pro: 首个音视频一步生成；唇形同步、多语言对话
  endpoints: /api/v1/seedance/text_to_video
  request fields: prompt, model, duration_seconds
- seedance-2-mini: 紧凑型 2.x 变体，支持首尾帧与多模态参考输入
  endpoints: /api/v1/seedance/text_to_video
  request fields: prompt, model, duration_seconds
- seedance-2.0: 最多 9 张参考图 + 3 视频 + 3 音频；15 秒多镜头
  endpoints: /api/v1/seedance/text_to_video
  request fields: prompt, model, duration_seconds
- seedance-2.0-fast: 2.0 同等能力，面向更快迭代优化
  endpoints: /api/v1/seedance/text_to_video
  request fields: prompt, model, duration_seconds
- seedance-2.5: seedance-2.5
  endpoints: /api/v1/seedance/text_to_video
  request fields: prompt, model, duration_seconds
- seedance-v1-pro: 1080p 电影级质量基线
  endpoints: /api/v1/seedance/text_to_video
  request fields: prompt, model, duration_seconds
- seedance-v1-pro-fast: 更快的 v1-pro 变体，同样支持 1080p 输出
  endpoints: /api/v1/seedance/text_to_video
  request fields: prompt, model, duration_seconds, first_frame_image_url

Use the model ID and endpoint that match the user's request.
Example prompt: 生成一段 10 秒的产品揭幕视频：手机从烟雾中浮现，电影级打光，环境低音。
/api/v1/seedance/text_to_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/seedance/text_to_video，并保存返回的 Task ID。
GET /api/v1/seedance/text_to_video/<task-id>，直到状态为 completed 或 failed。
确认 completed 响应包含 API 参考中记录的端点专属输出。