| name | add-mouth |
| description | Give your Founder OS a mouth - have it read an answer out loud or render it to an audio file, from any skill, without the full conversational voice loop. Trigger on "add a mouth", "add mouth", "read this out loud", "let it speak", "give it a voice out", or "set up text-to-speech". The default holds the accessibility floor: your operating system's built-in speech (Windows SAPI, macOS say, Linux espeak), NO extra key and NO paid service. A free fully-local upgrade (Piper) gives a better voice offline; a premium mouth (ElevenLabs) is an opt-in paid choice, never the default. This is the swappable "mouth" from the brain / mouth / hands scaffold - it plugs into the same brain as text or voice.
|
| why | The mouth is separate from the full voice loop on purpose: a founder often wants an answer read aloud (a brief while driving, a draft heard back) without holding a conversation. Shipping it as its own tiered skill keeps the accessibility floor - a real, keyless, local default - and makes the better and premium voices clean opt-in upgrades with their cost stated up front. |
| enhance | Want a better voice that still never leaves your machine? Add the free Piper upgrade in references/mouth-options.md. Want broadcast quality for something you publish? ElevenLabs is the paid mouth - a deliberate spend, stated before you commit, never on by default. |
| summary | Have your OS read an answer out loud - default needs no key. |
| allowed-tools | ["Bash","Read"] |
| mcp_requirements | [] |
Add a mouth
Runs on: local-exec - the happy path runs a local Python setup that writes a gitignored voice/ config and a say helper, then speaks through your machine. On a read-only or cloud surface, explain the options but do NOT claim the mouth is wired or that anything spoke - it has not until the user runs it locally.
The OS ships complete as text. This adds a mouth: it can speak an answer out loud or render it to an audio file you keep. It is the voice-OUT half of the sensory layer, and it is deliberately separate from add-voice (the full talk-and-listen loop). You can have a mouth without ever holding a conversation - useful when you want a brief read back while your hands are busy, or a draft heard aloud before you send it.
This is the swappable mouth from the brain / mouth / hands scaffold. The brain (your files and answers) stays the same; the mouth is how it speaks. Nothing here is required.
The accessibility floor (the rule that governs the default)
The default mouth is your operating system's own built-in speech - Windows SAPI, macOS say, Linux espeak or spd-say. No extra key, no paid service, no pip install, no model download. It speaks on the subscription-free tools your machine already has. Everything past that is opt-in and disclosed.
The options
| Option | What it adds | Needs | Default? |
|---|
| OS-native | Speak through your machine's built-in voice; render to a file | nothing extra | YES |
| Piper | A noticeably better voice that still runs fully offline | one download + Piper on PATH | no - opt-in, free |
| ElevenLabs | Broadcast-quality voice for something you publish | a paid API key | no - opt-in, paid |
| Browser | The voice the add-voice page already uses, inside that loop | the add-voice skill | no - that is the voice loop |
Full detail, the exact install per option, and the cost-and-locality trade are in references/mouth-options.md. The trade is load-bearing: the engine you pick changes voice quality, whether your text leaves the machine, and whether it costs anything. State it before they commit, never after.
