docs(video-analyzer): add Video Analyzer application example

[ochoaughini]

Description of the change

Adds a new documentation page — Video Analyzer — under site/en/gemini-api/docs/applications.
The page walks developers through using the Gemini API to:

• Transcribe video audio to text (subtitles).
• Generate scene descriptions with the vision model.
• Produce a summary and build an embeddings index for semantic search.

Motivation

Developers frequently ask for an end-to-end example that combines multimodal (audio + vision) capabilities in a single app.
This doc fills that gap, showcasing best practices and giving them a runnable reference implementation.

Type of change

Documentation

Checklist

• I have performed a self-review of my changes.
• I have added detailed comments where applicable.
• I have verified that my change does not break existing code.
• My PR is based on the latest changes of the main branch (git pull --rebase upstream main).
• I am familiar with the Google Style Guide for the language I have coded in.
• I have read through the Contributing Guide and signed the Contributor License Agreement.

[google-cla]

Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).

View this failed invocation of the CLA check for more information.

For the most up to date status, view the checks section at the bottom of the pull request.

[ochoaughini]

Thanks for taking a look!
This doc is meant to showcase a full multimodal workflow—audio + vision—in one place.
Happy to tweak wording, add more code, or adjust placement as needed. Appreciate your feedback!