Brand Voice

Brand Voice — How the Brand Sounds

You own the reusable voice-and-tone system: 3–5 personality traits → concrete linguistic rules → a position on the four tone dimensions → a use/avoid word bank → a tone-by-context matrix → a paste-into-the-prompt voice-DNA block. The output is a persisted document, never a finished piece of copy.

The line: brand-voice owns the reusable definition of how the brand sounds. The moment you write one finished piece against it, that is a copywriting skill — page hero/value prop/CTA is landing-copy; launch emails and channel posts are ../marketing/SKILL.md; blog and article systems are content-engine, article-writing, newsletter, social-publisher; an investor narrative is ../pitch-deck/SKILL.md; a live customer ticket is customer-support (it consumes this guide, it does not author it). The way the brand looks — logo, color, type, design tokens — is brand-identity, and layout/motion is ../design/SKILL.md.

Voice vs. tone (the load-bearing distinction)

Voice is constant; tone flexes by context. Voice is the brand's fixed personality across everything it writes. Tone is the local adjustment for the reader's emotional state and the topic's sensitivity. A frustrated user does not want a joke; a celebration screen does not read like a financial disclosure — yet both are the same voice. (Nielsen Norman Group, "The Four Dimensions of Tone of Voice," pub. 2016-07-17, updated 2023-08-16.)

Why it matters: you author one voice and apply many tones. Conflate them and you get a guide that says "be playful" on a fraud-alert page — unusable. The guide locks voice once and tabulates tone per context (Step 5).

Why bother at all: consistent brand presentation correlates with revenue uplift — ~23% average, up to ~33% at the upper range across 1,800 brands in 14 industries (Lucidpress/Marq, "State of Brand Consistency"). Treat it as calibration for the effort, not a causal promise — it is a correlational study.

The flow (six steps)

1 Traits (3–5)  →  2 Rules (Bad→Good)  →  3 Four dimensions (ratios)
       →  4 Word bank (use/ban)  →  5 Tone-by-context matrix
              →  6 AI voice-DNA block  →  persist + audit

Step 1 — Traits (pick 3–5)

Distill the brand to 3–5 adjectives. Fewer than 3 is not a personality; more than 5 is unmemorable and nobody applies them. (Sprout Social brand-voice guide; Inkbot Design brand-voice chart.)

Reject brand-neutral adjectives. If a competitor would never claim the opposite, the word is filler and says nothing. "Innovative," "passionate," "customer-focused," "cutting-edge" — no brand claims "stagnant" or "indifferent," so these traits exclude nothing.

Each trait gets a one-line this means / this does not mean, so it is testable:

Plain-spoken
  this means:        we say "we fixed it" — short Anglo-Saxon words, no hedging
  this does NOT mean: dumbed-down or curt; we still explain the why
Quietly confident
  this means:        we state the benefit and stop; no exclamation marks
  this does NOT mean: arrogant, or making claims we can't back with proof

Step 2 — Rules (each trait → 2–3 linguistic rules)

Vague directives fail, especially for an LLM: "be professional" produces nothing reproducible. Voice only transfers when quantified into linguistic rules. (Search Engine Land, "How to train in-house LLMs on brand voice," 2025; Fishtank, "Train Generative AI to Speak in Your Brand Voice," 2025.)

Per trait, write 2–3 rules across these levers — person, sentence-length ceiling, active vs. passive, contractions, jargon policy — and show one Bad→Good rewrite per cluster:

Trait: Plain-spoken
  R1  Active voice. Subject does the verb.
  R2  Sentence ceiling ~20 words; break anything longer.
  R3  Jargon only when defined in-line on first use.

  Bad : "Optimal outcomes are facilitated through the leveraging of our
         platform's robust capabilities."  (passive, 12-word abstraction, banned words)
  Good: "Our platform does the heavy lifting so your team ships faster."

Trait: Quietly confident
  R1  First person plural ("we"), second person for the reader ("you").
  R2  Use contractions ("we're", "you'll") — formal-but-human, not stiff.
  R3  Zero exclamation marks; the claim carries the energy.

  Bad : "We are SO excited to announce our amazing new feature!!!"
  Good: "New: branch previews ship with every PR. No config."

Step 3 — Plot the four dimensions (decision table)

Tone of voice is measurable on four sliding scales, not switches. (Nielsen Norman Group, same article.) Pick a position on each as a ratio, not "somewhere in the middle" — a ratio forces a defensible choice. (Sprinklr / Bigeye brand-voice frameworks, 2025.) A financial brand might run 80/20 formal; a fitness app 30/70 serious-vs-playful.

This branches per brand, so the table earns its place:

Fill the ratios from the traits, not from taste. If a ratio contradicts a trait, one of them is wrong — reconcile before moving on.

Step 4 — Word bank

Two lists. Power words and a ban list. (Oxford College of Marketing, "AI Brand Voice Guidelines," 2025-08-04.)

• Power words (15–20): the vocabulary the brand leans on, derived from the traits. "Plain-spoken + confident" → ship, fix, build, fast, clear, done, plain, real, works. Not a thesaurus dump — words a human would recognize as this brand.
• Ban list (the drift killer): corporate filler and AI tells. This list is what stops off-brand drift and the generated-by-a-bot smell. Starter set: leverage, seamless, elevate, delve, robust, unlock, game-changer, in today's fast-paced world, revolutionize, synergy, cutting-edge, best-in-class. Add brand-specific bans (e.g. never say "users," say "teams").

The full starter ban list and the method for deriving power words from traits live in references/word-bank.md.