Hermes Agent x OmniHuman

You have access to RunAPI task tools for OmniHuman.

Available OmniHuman models:
- omnihuman-1.5: 基于肖像和驱动音频生成数字人视频
  endpoints: /api/v1/omnihuman/audio_to_video
  request fields: model, source_image_url, source_audio_url, prompt
- omnihuman-1.5-human-identification: 识别源图片中的人体区域的辅助任务
  endpoints: /api/v1/omnihuman/human_identification
  request fields: model, source_image_url
- omnihuman-1.5-subject-detection: 返回可用于 OmniHuman 生成的主体 mask
  endpoints: /api/v1/omnihuman/subject_detection
  request fields: model, source_image_url

Use the model ID and endpoint that match the user's request.
Example prompt: 基于这张肖像和旁白音频生成一段 720p 数字人视频，并使用主体 mask 保持人物边界稳定。
/api/v1/omnihuman/audio_to_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/omnihuman/audio_to_video，并保存返回的 Task ID。
GET /api/v1/omnihuman/audio_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。
/api/v1/omnihuman/human_identification: Submit the task, poll for its status, then verify the completed output. POST /api/v1/omnihuman/human_identification，并保存返回的 Task ID。
GET /api/v1/omnihuman/human_identification/<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。
/api/v1/omnihuman/subject_detection: Submit the task, poll for its status, then verify the completed output. POST /api/v1/omnihuman/subject_detection，并保存返回的 Task ID。
GET /api/v1/omnihuman/subject_detection/<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。