Audio/video Q&A

Audio/video Q&A

You can query a model directly and test the results returned when using different parameter values with the Cloud console, or by calling the Vertex AI API directly.

Prompt Freeform

Look through each frame in the video carefully and answer the question. Only base your answers strictly on what information is available in the video attached. Do not make up any information that is not part of the video and do not be too verbose.

Questions: - When does a red lantern first appear and what is written in the lantern? Provide a timestamp. - What language is the person speaking and what does the person say at that time?


  • 00:13 - The lantern says "紅燈"
  • The person is speaking Japanese. The person says "新しいピクセルには動画ブーストって機能があるんですけど暗いところだと夜警モードが作動して画質がさらに上がるんです"
Model: gemini-1.5-flash-001
Temperature: 1
Max output tokens: 8192
TopK: 40
TopP: 0.95