chore(genai): Update live_audio_with_txt to gemini-2.5-flash-native-audio

[angelcaamal]

Description

Fixes #481442791

Note: Before submitting a pull request, please open an issue for discussion if you are not associated with Google.

Checklist

• I have followed Sample Guidelines from AUTHORING_GUIDE.MD
• README is updated to include all relevant information
• Tests pass: nox -s py-3.9 (see Test Environment Setup)
• Lint pass: nox -s lint (see Test Environment Setup)
• These samples need a new API enabled in testing projects to pass (let us know which ones)
• These samples need a new/updated env vars in testing projects set to pass (let us know which ones)
• This sample adds a new sample directory, and I updated the CODEOWNERS file with the codeowners for this sample
• This sample adds a new Product API, and I updated the Blunderbuss issue/PR auto-assigner with the codeowners for this sample
• Please merge this PR for me once it is approved

[gemini-code-assist]

Summary of Changes

Hello @angelcaamal, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request focuses on upgrading the generative AI model utilized within the live_audio_with_txt.py sample. By transitioning to the gemini-2.5-flash-native-audio-latest model, the sample will benefit from the most current capabilities and improvements in live audio processing and text generation, ensuring it remains up-to-date with the latest advancements in the Gemini Flash model series.

Highlights

• Model Update: The gemini-2.0-flash-live-preview-04-09 model used in the live_audio_with_txt.py sample has been updated to the newer gemini-2.5-flash-native-audio-latest model.

Changelog

• genai/live/live_audio_with_txt.py
  • Updated the model variable from gemini-2.0-flash-live-preview-04-09 to gemini-2.5-flash-native-audio-latest.

Activity

• The pull request was opened by angelcaamal to address issue #481442791.
• The author has included a comprehensive checklist in the PR description, indicating various pre-merge tasks and guidelines followed.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request updates the model used in the live_audio_with_txt.py sample from a dated preview version to gemini-2.5-flash-native-audio-latest. The change is correct and improves the sample by using a more stable model version. I have provided one suggestion to improve code style by defining the model name as a constant, following PEP 8 guidelines.

[gemini-code-assist]

For better readability and adherence to Python conventions (PEP 8), it's recommended to define constant values using UPPER_CASE_WITH_UNDERSCORES. This makes it clear that the value is not intended to change.

After this change, you will also need to update the model parameter in the client.aio.live.connect call on line 54.

Suggested change

	model = "gemini-2.5-flash-native-audio-latest"
	MODEL = "gemini-2.5-flash-native-audio-latest"