add-voice

name	add-voice
description	Give your Founder OS a voice - talk to it out loud and hear it answer. Trigger on "add voice", "let me talk to my OS", "voice mode", "talk to it out loud", or "set up voice mode". This is SPEAKING and LISTENING; if they mean how their WRITING sounds, that is voice-interview, not this. Installs the Tier-0 loop by default: your browser's built-in speech (ears and mouth) plus the reasoning CLI you already run the OS in (brain), with NO extra API key and NO paid service - the accessibility floor. Realtime voice (Gemini Live, free Google AI Studio key) and a premium mouth (ElevenLabs) are opt-in upgrades, never the default. Honest disclaimer up front: in Chrome/Edge the browser sends your audio to its vendor to transcribe (no key, no cost, not fully local); faster-whisper makes it fully local. Your brain - your files and answers - stays on your machine.
why	Voice is the most-asked extension and the easiest place to either silently bill the user or mishear them. Shipping it as a tiered skill - default that needs no key, upgrades that are opt-in and disclosed - holds the accessibility floor and keeps the honesty note load-bearing instead of buried.
enhance	Use Chrome or Edge for built-in speech input. Want speech that never leaves your machine? Add the faster-whisper upgrade in references/tiers.md. Want sub-second realtime conversation? That is Tier 1 - a free Google AI Studio key, with the cost-and-accuracy trade stated plainly before you commit.
summary	Talk to your OS and hear it back - default needs no key.
allowed-tools	["Bash","Read"]
mcp_requirements	[]

Add voice

Runs on: local-exec - the happy path runs a local Python setup that writes a gitignored voice/ runtime and serves a local page. On a read-only or cloud surface, explain the steps and the tiers but do NOT claim the install ran or the loop works - it has not until the user runs it locally.

This turns the documented "voice is a DIY mouth and ears" direction (docs/voice-extension.md) into a wired capability the user installs by asking. The OS ships as a complete text brain; this adds a sensory layer on top of the same brain. Nothing here is required.

Check you are in the right skill (say this first if the ask was ambiguous)

"Voice" means two different things in this OS, and "set up my voice" can mean either:

• This skill (add-voice) - SPEAKING and LISTENING. You talk to the OS out loud and hear it answer.
• voice-interview - your WRITING voice. It captures how you write so every email, post, and draft sounds like you. Nothing is spoken or heard.

If the user asked with a phrase that could be either ("set up my voice", "voice setup"), say one line before installing anything: "Quick check - do you mean talking to your OS out loud (this), or how your writing sounds (that is voice-interview)?" Do not install a runtime the user did not ask for.

The accessibility floor (the rule that governs the default)

The default install - Tier 0 - must work end-to-end on the one subscription the user already runs the OS in, with no extra API key and no paid service. That is non-negotiable. The brain answers through the reasoning CLI the OS already uses (claude -p by default - no API key, it uses the existing subscription); the browser hears and speaks. Everything past Tier 0 is opt-in and disclosed.

The tiers

Tier	What it adds	Needs	Default?
0	Browser speech-in + speech-out + brain on your one subscription	nothing extra	YES
0-local	Swap browser STT for faster-whisper so speech never leaves your machine	one pip install + a model download	no - opt-in
1	Realtime, sub-second spoken conversation (Gemini Live front)	a FREE Google AI Studio key