Philipp Schmid· @_philschmid · X·· 3 小时前AI 评分65
AI 导读
Philipp Schmid 演示了如何结合 Gemini API CLI 与编码 Agent 来测试语音等多模态功能。具体步骤包括使用 Gemini API CLI 生成语音、通过 Chrome 配合特定参数模拟音频捕获、利用 Playwright 或 browser-use 点击麦克风按钮流式传输 WAV 文件，以及验证 DOM 中的转写和 UI 状态。
正文 · 原文
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:
- Use Gemini API CLI to generate speak
- Use Chrome with --use-file-for-fake-audio-capture=voice.wav%noloop
- Click the mic button via Playwright or browser-use so getUserMedia streams the WAV from 0.0s
- Verify the transcript and UI state in the DOM
Prompt below 👇
来源：Philipp Schmid · x.com