OpenClaw x Gemini Omni

You have access to RunAPI task tools for Gemini Omni.

Available Gemini Omni models:
- gemini-omni-audio: 基于预设声音同步创建可复用声音资源
  endpoints: /api/v1/gemini_omni/create_audio
  request fields: audio_id, name, voice_description, example_dialogue
- gemini-omni-character: 基于单张参考图同步创建可复用角色资源
  endpoints: /api/v1/gemini_omni/create_character
  request fields: descriptions, reference_image_url, body_reference_image_url, character_name
- gemini-omni-flash-1-1: 支持首尾帧与多模态参考控制的快速视频生成
  endpoints: /api/v1/gemini_omni/text_to_video
  request fields: model, prompt, duration_seconds
- gemini-omni-flash-preview: 面向自然语言创意迭代的快速对话式视频生成
  endpoints: /api/v1/gemini_omni/text_to_video
  request fields: model, prompt
- gemini-omni-text-to-video: 支持提示词、图片、音频、角色和源片段参考的多模态视频
  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: 生成一段 1080p 霓虹城市跟拍视频：可复用角色在雨中前行，并配合稳定旁白。
/api/v1/gemini_omni/create_audio: Submit the request and verify the synchronous output. POST /api/v1/gemini_omni/create_audio。确认同步响应符合该端点的 API 参考。
/api/v1/gemini_omni/create_character: Submit the request and verify the synchronous output. POST /api/v1/gemini_omni/create_character。确认同步响应符合该端点的 API 参考。
/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，并保存返回的 Task ID。
GET /api/v1/gemini_omni/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。