Hermes Agent x Kling

You have access to RunAPI task tools for Kling.

Available Kling models:
- kling-3.0: 原生 4K，最長 15 秒，支援多鏡頭分鏡
  endpoints: /api/v1/kling/text_to_video, /api/v1/kling/motion_control
  request fields: model, prompt, duration_seconds, aspect_ratio, output_resolution
- kling-ai-avatar-pro: 1080p，強化對嘴與臉部微表情
  endpoints: /api/v1/kling/ai_avatar
  request fields: model, source_image_url, source_audio_url, prompt
- kling-ai-avatar-standard: 720p 基本對嘴
  endpoints: /api/v1/kling/ai_avatar
  request fields: model, source_image_url, source_audio_url, prompt
- kling-ai-avatar-v1-pro: V1 Pro 虛擬人像生成，以音訊驅動對嘴
  endpoints: /api/v1/kling/ai_avatar
  request fields: model, source_image_url, source_audio_url, prompt
- kling-o1: 支援圖片與影片參考的全能影片生成
  endpoints: /api/v1/kling/image_to_video, /api/v1/kling/text_to_video
  request fields: model, prompt, duration_seconds, aspect_ratio
- kling-v1-avatar-standard: V1 Standard 虛擬人像生成，高效製作說話頭像
  endpoints: /api/v1/kling/ai_avatar
  request fields: model, source_image_url, source_audio_url, prompt
- kling-v2.1-master-image-to-video: 頂級 V2.1 圖片生成影片，算圖效果更強
  endpoints: /api/v1/kling/image_to_video
  request fields: model, prompt, first_frame_image_url
- kling-v2.1-master-text-to-video: 頂級 V2.1 文字生成影片，算圖效果更強
  endpoints: /api/v1/kling/text_to_video
  request fields: model, prompt, duration_seconds, aspect_ratio
- kling-v2.1-pro: 圖片生成影片，可選擇控制結尾影格
  endpoints: /api/v1/kling/image_to_video
  request fields: model, prompt, first_frame_image_url
- kling-v2.1-standard: 較低成本的 V2.1 圖片動畫，適合快速草稿
  endpoints: /api/v1/kling/image_to_video
  request fields: model, prompt, first_frame_image_url
- kling-v2.5-turbo-image-to-video-pro: 1080p 以圖片為基準；輸入圖片作為首影格
  endpoints: /api/v1/kling/extend_video, /api/v1/kling/image_to_video
  request fields: model, prompt, first_frame_image_url
- kling-v2.5-turbo-text-to-video-pro: 1080p，最長 10 秒，30 fps；快速文字生成影片草稿
  endpoints: /api/v1/kling/text_to_video, /api/v1/kling/extend_video
  request fields: model, prompt, duration_seconds, aspect_ratio
- kling-v2.6: 文生與圖生影片一體化生成，支援同步原生音訊
  endpoints: /api/v1/kling/text_to_video, /api/v1/kling/image_to_video, /api/v1/kling/motion_control
  request fields: model, prompt, duration_seconds, aspect_ratio
- kling-v3-omni: Kling v3 Omni 全方位影片生成，原生 4K、影音同步，支援彈性的 3–15 秒片長。
  endpoints: /api/v1/kling/image_to_video, /api/v1/kling/text_to_video
  request fields: model, prompt, duration_seconds, aspect_ratio, output_resolution
- kling-v3-omni-edit: 使用可選參考圖編輯來源影片
  endpoints: /api/v1/kling/edit_video
  request fields: model, prompt, source_video_url, reference_image_urls, duration_seconds, output_resolution, aspect_ratio, enable_sound
- kling-v3-omni-reference: 以參考圖像或來源影片引導的可控影片生成
  endpoints: /api/v1/kling/text_to_video, /api/v1/kling/edit_video
  request fields: model, prompt, duration_seconds, aspect_ratio, output_resolution, reference_image_urls
- kling-v3-turbo-image-to-video: 3-15 秒的圖片生成影片片段，以單張首影格圖片生成
  endpoints: /api/v1/kling/image_to_video
  request fields: model, prompt, first_frame_image_url
- kling-v3-turbo-text-to-video: 3-15 秒的文字生成影片片段，720p 或 1080p
  endpoints: /api/v1/kling/text_to_video
  request fields: model, prompt, duration_seconds, aspect_ratio, output_resolution

Use the model ID and endpoint that match the user's request.
Example prompt: 製作一段 10 秒影片：一個人走過秋天的森林，落葉紛飛，搭配電影感的鏡頭平移。
/api/v1/kling/text_to_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/kling/text_to_video，並儲存回傳的 Task ID。
GET /api/v1/kling/text_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/kling/motion_control: Submit the task, poll for its status, then verify the completed output. POST /api/v1/kling/motion_control，並儲存回傳的 Task ID。
GET /api/v1/kling/motion_control/<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/kling/ai_avatar: Submit the task, poll for its status, then verify the completed output. POST /api/v1/kling/ai_avatar，並儲存回傳的 Task ID。
GET /api/v1/kling/ai_avatar/<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/kling/image_to_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/kling/image_to_video，並儲存回傳的 Task ID。
GET /api/v1/kling/image_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/kling/extend_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/kling/extend_video，並儲存回傳的 Task ID。
GET /api/v1/kling/extend_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/kling/edit_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/kling/edit_video，並儲存回傳的 Task ID。
GET /api/v1/kling/edit_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。