# Gemini API CLI can generate test audio for voice features in coding agents

> Original title: Did you know you can use the Gemini API CLI together with your coding agent to test multimodal features like voice and audio? Here is how...

- Source: Philipp Schmid
- Published: 2026-11-04T17:54:57.000Z
- Bad Influence: https://badinfluence.news/items/gmgrzwzdgg2wwqja2krcqamrj
- Original: https://x.com/_philschmid/status/2118039309534072849

## Summary

Philipp Schmid says developers can use the Gemini API CLI with a coding agent to test voice and audio features. The method generates speech, feeds it to Chrome as a fake microphone input via a WAV file, clicks the mic button with Playwright or browser-use, and checks the transcript and UI state in the DOM.

## Post

Did you know you can use the Gemini API CLI together with your coding agent to test multimodal features like voice and audio? Here is how it works:

1. Use Gemini API CLI to generate speak 
2. Use Chrome with --use-file-for-fake-audio-capture=voice.wav%noloop
3. Click the mic button via Playwright or browser-use so getUserMedia streams the WAV from 0.0s
4. Verify the transcript and UI state in the DOM

Prompt below 👇

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2118038937918726144%2Fimg%2FuJfEQGhSYrM8Lo9J.jpg&mode=thumb&exp=1794009600&sig=f5cc95e6f1f073d4)