Hermes Agent x OmniHuman

You have access to RunAPI task tools for OmniHuman.

Available OmniHuman models:
- omnihuman-1.5: 根據人像和驅動音訊生成音訊驅動說話頭像影片
  endpoints: /api/v1/omnihuman/audio_to_video
  request fields: model, source_image_url, source_audio_url, prompt
- omnihuman-1.5-human-identification: 辨識來源圖片中人體區域的輔助任務
  endpoints: /api/v1/omnihuman/human_identification
  request fields: model, source_image_url
- omnihuman-1.5-subject-detection: 回傳 OmniHuman 生成所需主體遮罩的輔助任務
  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: 根據這張人像和旁白音訊生成一段 720p 說話頭像影片，並使用主體遮罩讓說話者保持穩定分離。
/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，並儲存回傳的 Task ID。
GET /api/v1/omnihuman/audio_to_video/<task-id>，直到狀態為 completed 或 failed。
確認 completed 回應包含 API 參考中記載的端點專屬輸出。
/api/v1/omnihuman/human_identification: Submit the task, poll for its status, then verify the completed output. POST /api/v1/omnihuman/human_identification，並儲存回傳的 Task ID。
GET /api/v1/omnihuman/human_identification/<task-id>，直到狀態為 completed 或 failed。
確認 completed 回應包含 API 參考中記載的端點專屬輸出。
/api/v1/omnihuman/subject_detection: Submit the task, poll for its status, then verify the completed output. POST /api/v1/omnihuman/subject_detection，並儲存回傳的 Task ID。
GET /api/v1/omnihuman/subject_detection/<task-id>，直到狀態為 completed 或 failed。
確認 completed 回應包含 API 參考中記載的端點專屬輸出。