Starting April 29, 2025, Gemini 1.5 Pro and Gemini 1.5 Flash models are not available in projects that have no prior usage of these models, including new projects. For details, see Model versions and lifecycle.
Stay organized with collections
Save and categorize content based on your preferences.
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.
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?
Response
0:23: "灯籠"
Japanese, "Sancha is where I used to live when I first moved to Tokyo. I have a lot of great memories here."
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-04 UTC."],[],[],null,["Audio/video Q\\&A\n\n|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| 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. - For an example of using the Vertex AI API, see [Quickstart using the Vertex AI API](/vertex-ai/generative-ai/docs/start/quickstarts/api-quickstart). - To view this sample in the Cloud console: [Go to Google Cloud console](https://console.cloud.google.com/vertex-ai/generative/language/prompt-examples/Audio%2Fvideo%20Q&A) \u003cbr /\u003e ||\n| Prompt Freeform Your browser does not support HTML5 video. 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? Response - 0:23: \"灯籠\" - Japanese, \"Sancha is where I used to live when I first moved to Tokyo. I have a lot of great memories here.\" | |------------------------|----------------------| | **Model:** | gemini-1.5-flash-002 | | **Temperature:** | 0.2 | | **Max output tokens:** | 8192 | | **TopK:** | 40.0 | | **TopP:** | 0.95 | |"]]
