Skip to content
Trending storyDeveloping

Gemini API CLI generates test audio for testing voice features in coding agents

2 articles1 sourcesince Nov 4Last article 1h ago ·

Overview

AISummary of 2 articles

Philipp Schmid says developers can use the Gemini API CLI, with a coding agent, to test voice and audio features without a physical microphone.

The CLI's gemini-api tts command generates spoken WAV files. Chrome then plays a WAV as its microphone input through fake-device flags, starting from 0.0 seconds after the mic button is clicked, and Playwright or browser-use clicks the button.

According to Schmid, the agent then checks the resulting transcript and UI state in the DOM. The method is described in posts dated 2026-11-04 on X.

Written by AI from the articles below · updated Nov 4, 1:16 PM ET

Check the sources:

Latest developmentNov 4, 12:54 PM ET
Gemini API CLI can generate test audio for voice features in coding agents

Developments

2 developments

  1. Nov 4, 12:54 PM ET · 1 article
    Gemini API CLI can generate test audio for voice features in coding agents
    Philipp Schmid: Gemini API CLI can generate test audio for voice features in coding agents
  2. Nov 4, 12:54 PM ET · 1 article
    Test a Gemini app's voice feature end-to-end with fake microphone audio
    Philipp Schmid: Test a Gemini app's voice feature end-to-end with fake microphone audio

Article timeline

The articles in this story. Times are ET.

Nov 4
  1. Philipp SchmidX
    Gemini API CLI can generate test audio for voice features in coding agents

    AIPhilipp 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.

    Video from @_philschmid's post
  2. Philipp SchmidX
    Test a Gemini app's voice feature end-to-end with fake microphone audio

    AIPhilipp Schmid shows how to test a voice feature without a physical microphone by installing the gemini-api-cli skill and generating spoken WAV files with gemini-api tts. He says headless Chrome can then stream the WAV through getUserMedia using fake-device flags, starting from 0.0 seconds after the mic button is clicked.

Heat Trend

Not enough continuous observations to show a trend yet.