Phil Schmid shares trick to test voice features with coding agents using Chrome's fake audio capture
_philschmid · x · 2026-11-05
Phil Schmid shared a mic-free recipe for letting coding agents end-to-end test voice/audio features:
- Generate spoken WAV test files with the Gemini API CLI;
- Launch Chrome with --use-file-for-fake-audio-capture=voice.wav%noloop to feed the WAV as fake mic input;
- Click the mic button via Playwright or browser-use so getUserMedia streams the WAV from 0.0s;
- Verify transcript and UI state in the DOM.
He followed up with a full prompt template — installing the gemini-api-cli skill from google-gemini/gemini-skills, plus headless Chrome fake-media-stream flags — ready to hand to any coding agent.
Related event: Phil Schmid Ships Gemini API CLI Skill for One-Command Multimodal Agents(5 posts)→
More from coding & agent
- Vector search finds resemblance, not proof: where Microsoft Fabric Graph fits — WirelessLife · 2026-11-05
- Databricks recipe: multi-tenant Genie isolation via OAuth custom identity claims + ABAC — Wise_Ear_4064 · 2026-11-05
- How do you teach AI agents company-specific jargon? Four glossary approaches, none great — ladybawss · 2026-11-05
- Garry Tan spends $200K/yr on a 23-skill Claude Code setup — benchmarks show elaborate harnesses can lose to vanilla — echen · 2026-11-05
- Teams experiment: cheap models for subagents, top model only on the primary agent — cramforce · 2026-11-05
- Mistral's Vibe CLI releases version 3.1 — qtnx_ · 2026-11-05