fix: Gemini 2.0 live api audio not working

[LivioGama]

Description

Thank you for opening a Pull Request!
Before submitting your PR, there are a few things you can do to make sure it goes smoothly:

• Follow the CONTRIBUTING Guide.
• You are listed as the author in your notebook or README file.
• Your account is listed in CODEOWNERS for the file(s).
• Make your Pull Request title in the https://www.conventionalcommits.org/ specification.
• Ensure the tests and linter pass (Run nox -s format from the repository root to format).
• Appropriate docs were updated (if necessary)

[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.

[code-review-assist]

Hi team,

Gemini here! I'm currently reviewing this pull request and will post my full review in a few minutes. In the meantime, here's a quick summary to get everyone up to speed:

This PR addresses an issue where the Gemini 2.0 live API audio wasn't working in the websocket-demo-app. The changes include:

• Updating CODEOWNERS: Added LivioGama as a code owner for the gemini/multimodal-live-api/websocket-demo-app/ directory.
• Modifying README.md: Clarified the setup instructions for the frontend, specifically emphasizing the need to use ws://localhost:8000 instead of wss:// for the PROXY_URL and providing more explicit steps for setting up the Google Cloud project and obtaining an access token. Also, corrected a minor inaccuracy in the voice input description.
• Improving gemini-live-api.js: Refactored the code to handle audio and text responses more robustly, improving the logic for determining the message type.
• Refining live-media-manager.js: Added error handling for microphone disconnection and improved the audio processing logic for smoother playback.
• Cleaning up pcm-processor.js: Removed redundant code, streamlining the audio processing workflow.

Overall, this PR makes the websocket-demo-app significantly more user-friendly and reliable, fixing the audio issue and improving the clarity of the instructions. The changes are well-structured and easy to follow.

---

And now, a little haiku to lighten the mood:

Audio streams flow,
Bugs fixed, code sings a new song,
Smooth sounds fill the air.

Looking forward to discussing this further!

Best,
code-review-assist

[LivioGama]

This fixes those issues:

[code-review-assist]

This pull request addresses a critical issue with the Gemini 2.0 live API demo app where audio was not working. The core fix involves reorganizing the message handling logic in gemini-live-api.js to correctly identify and process audio messages. The additional changes in the README and other files improve the clarity of the setup instructions and enhance error handling, contributing to a better user experience. Overall, the changes are well-considered and effectively resolve the reported issue. I recommend merging this pull request after addressing the following suggestions.

[zorrofox]

Can someone review this PR? These bugs real block the this demo.