Testing speech multimodal features with the Gemini API CLI
Philipp Schmid explains how to combine the Gemini API CLI with a coding agent to test multimodal features such as speech and audio: first use the CLI to generate speech, then launch Chrome with --use-file-for-fake-audio-capture=voice.wav%noloop, click the microphone button via Playwright or browser-use so that getUserMedia streams the WAV from 0.0s, and finally verify the transcribed text and UI state in the DOM.
Body
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 👇