"Dad will hear this reply, not read it." — the first line of the spoken-turn instruction
About the Medium, Never the Persona
The spoken-reply instruction is short, and what it leaves out matters as much as what it says. It never tells the soul who to be. Pippa stays Pippa, Ttori stays a cheeky kid, Feynman stays Feynman, each with their own vault voice and their own language. The instruction is only about the medium: this turn will be synthesized in your own voice and played aloud, so for this turn these rules replace the readability guidance in your system prompt, and everything else about you stays exactly as it is.
The Rules, and Why Each One Exists
- Lead with the answer in a sentence or two, then leave room. Offer more ("want to hear more?") instead of unloading everything. A listener can't skim; a long preamble is a long wait.
- One idea at a time. Weave at most about three items into a sentence and group anything longer. Nobody remembers the fifth item of a spoken list.
- If the ask is ambiguous, ask back in one short line. A wrong guess costs a whole spoken answer.
- No length limit. If Dad asks for a long explanation or a story, talk as long as it needs, as speech and not as a document. The house never caps a soul's length pre-emptively; short is the default shape, not a ceiling.
- Nothing that only works on a screen. No headings, bullets, numbered lists, tables, bold, code, links, URLs or file paths. When Dad needs to see something, it goes into a card, the subject of the third lesson.
Korean Rules, Added and Then Removed
Today the spoken instruction carries no Korean-specific rule at all: a soul writes Korean the way it writes Korean anywhere, numbers included. For its first three weeks it carried three, and why they came and why they went is this section.
Most of what makes Korean speech sound machine-made comes from the text, not the voice. So the first instruction carried three Korean-specific rules. Write loanwords in Hangul, the way they are said, and use English only as whole sentences: a voice that meets English words in the middle of a Korean sentence reads them with the wrong accent. Write a quantity that carries a unit in digits (6분, 20%, 3시 30분), and never spell it out in Hangul: the voice engine sends the digits as written and the voice reads each one by its meaning, while a spelled number fixes one reading, and 여섯 분 is six people, not six minutes (Track 4 tells that story). Counts you would write as words, like 한 번 or 두 가지, stay words. And where a soul would call someone 네 (your) or 네가 (you), write the spoken 니 or 니가, or use a name, because in speech that syllable is heard as 내 (my) and the sentence turns around to mean the speaker. 너, 넌 and 널 sound distinct and stay, and the numeral 네 and the polite 네 for yes are different words altogether. Pippa never uses that word for Dad in the first place; a younger soul talking to a friend would.
Prompts Are Data
Every voice instruction (spoken, dictated, posture, heard-until and now On Air's) lives in the same place as every other runtime prompt the house uses, editable from Admin without a deploy. They are templates: the spoken one receives the approved list of audio tags when it is rendered, so the prompt can never name a tag that list lacks. That list is cwkPippa's copy of the one the voice engine strips, though, and the engine keeps the original. Rendering closed the gap between the prompt and the copy; the gap between the copy and the original is still guarded only by care, and a check that compares them is the missing piece. Dad can tune a word of the wording tonight and hear the difference on the next turn.
What Going Live Sounded Like
Three live turns on 2026-09-25 checked the shape end to end. The replies contained no Markdown at all. Loanwords came out in Hangul. The soul used her own [happy], [sighs] and [softly] tags. And each reply ended by handing the turn back, one of them with "Want to hear more? Or will you tell me about your day first?" That last habit is the one a document never has.