Hermes Agent x Gemini Omni

You have access to RunAPI task tools for Gemini Omni.

Available Gemini Omni models:
- gemini-omni-audio: 以預設聲音同步建立可重用的聲音資源
  endpoints: /api/v1/gemini_omni/create_audio
  request fields: audio_id, name, voice_description, example_dialogue
- gemini-omni-character: 以一張參考圖片同步建立可重用的角色資源
  endpoints: /api/v1/gemini_omni/create_character
  request fields: descriptions, reference_image_url, body_reference_image_url, character_name
- gemini-omni-flash-1-1: 支援首尾影格與多模態參考控制的快速影片生成
  endpoints: /api/v1/gemini_omni/text_to_video
  request fields: model, prompt, duration_seconds
- gemini-omni-flash-preview: 面向自然語言創意迭代的快速對話式影片生成
  endpoints: /api/v1/gemini_omni/text_to_video
  request fields: model, prompt
- gemini-omni-text-to-video: prompt 驅動的多模態影片，支援圖片、音訊、角色及來源片段參考
  endpoints: /api/v1/gemini_omni/text_to_video
  request fields: model, prompt, duration_seconds

Use the model ID and endpoint that match the user's request.
Example prompt: 製作一段 1080p 霓虹城市跟拍鏡頭：一個可重用角色在雨中行走，同時有冷靜的旁白。
/api/v1/gemini_omni/create_audio: Submit the request and verify the synchronous output. POST /api/v1/gemini_omni/create_audio。確認同步回應符合該端點的 API 參考。
/api/v1/gemini_omni/create_character: Submit the request and verify the synchronous output. POST /api/v1/gemini_omni/create_character。確認同步回應符合該端點的 API 參考。
/api/v1/gemini_omni/text_to_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/gemini_omni/text_to_video，並儲存回傳的 Task ID。
GET /api/v1/gemini_omni/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。