“Friendly but professional” is not a voice guide — it’s a wish. Brand voice docs fail because they describe taste without giving anyone (human or AI) a way to apply it. This walks through a workflow that distills voice from real examples into a doc with specific phrases, sentence-length distribution, and “never write this” anti-examples — the kind of doc that actually changes what gets shipped.
What this covers
A reproducible workflow that turns 5-10 of your best pieces of content into a 1-2 page voice doc, then validates the doc by generating test pieces and comparing. The output is loadable into a Custom GPT or Claude Project so every future draft (human or AI) starts from the same voice baseline.
Who this is for
Solo creators producing content under one personal brand. Small marketing teams (2-5 people) where consistency drift is starting to show. Content engineers integrating AI into a content pipeline who need a stable voice prompt to load. Founders who can write in their own voice but can’t yet articulate it to a teammate or freelancer.
When to reach for it
When 2+ people start producing content. When AI starts producing content (the doc becomes the system prompt). When you re-read your own articles from 6 months ago and they sound like a different person. Once the voice doc exists, feed it into a real Claude writing workflow so every draft inherits the same voice. To pressure-test whether a draft actually lives up to that voice doc, run it through AI writing feedback — a senior-editor critique catches the places AI quietly slipped back into AI-grey.
Before you start
- Have 5-10 pieces of your best on-brand content. Long-form preferred (blog posts, newsletters) — short copy doesn’t carry enough voice signal.
- Pick ones you genuinely think of as “right.” Mediocre samples will produce a mediocre voice. Brutal selectivity.
- Decide who the doc is for: humans, AI, or both. The format differs slightly — AI prompts need explicit do/don’t lists; human docs can be more narrative.
Step by step
- Collect 5-10 on-brand pieces. Paste them into one document, separated by clear delimiters.
- Run the analysis prompt:
Analyze these pieces of writing for voice. Output:
- 3 adjectives that describe the voice + 3 opposites it avoids
- 5 specific phrases the writer uses (signature words/phrases)
- 5 phrases or words the writer would NEVER use
- Sentence-length distribution: short/medium/long ratio
- Formality level (academic / professional / conversational / casual)
- Joke or humor style if any, with one example
- Common openings (how do paragraphs start)
- Pet structures (parallelism, lists, em-dashes, rhetorical questions)- Review the AI’s analysis. Where it’s wrong, correct it explicitly: “No, we use em-dashes more than this suggests.” The corrections matter more than the initial output.
- Generate test pieces. Prompt: “Using the voice doc above, write a 200-word piece about [a topic you know well].” Read it. Note where it drifts.
- Iterate: when AI drifts, add a rule to the doc that prevents that drift. After 3-4 test generations, the doc stabilizes.
- Save the final doc as a Custom GPT system prompt, a Claude Project context, or a
voice.mdyour team loads into every draft conversation. - Quarterly: re-run analysis on your last 90 days of content. Voice drifts; the doc should too.
First-run exercise
- Pick ONE long-form piece (a 2000-word article) you wrote and love. Just one.
- Run the analysis on just that one piece. Read the output. Is the AI’s distillation recognizable as your voice, or generic?
- If generic, add 2-3 more pieces and re-run. The voice signal needs density.
- Once the analysis reads like “yes that’s me,” do a 500-word test generation. The first AI-generated piece should feel 70% you. Add corrections to reach 90%.
Quality check
- Are the “5 signature phrases” actually phrases from your writing, or generic ones the AI assumed? If you can grep your archive and not find them, the AI hallucinated.
- Are the “never use” rules specific enough to be checkable? “Don’t be too formal” is unverifiable; “never use ‘leverage’, ‘utilize’, or ‘synergy’” is checkable.
- Does the test generation pass a 5-second sniff test from someone who knows your writing? If they say “this isn’t you,” the doc isn’t tight enough yet.
- Is the doc short enough that someone actually reads it? Aim for 1-2 pages. A 10-page voice doc is ignored.
How to reuse this workflow
- Save the analysis prompt as a template. Re-run it quarterly on new samples; voice evolves.
- Maintain a “rejected outputs” log: AI generations that drifted, with notes on why. These become future negative examples.
- Load the voice doc into every AI writing tool you use — Custom GPT, Claude Project, Cursor for marketing copy. One doc, many integrations.
Recommended workflow
Collect 8 long-form pieces → analysis prompt → distillation (3 adj, 5 phrases, 5 anti-phrases, sentence distribution) → review and correct → 3 test generations → 4 doc tightening iterations → save as system prompt → load into Custom GPT + team handbook → quarterly refresh. Before the voice doc is useful, the team also needs one shared positioning anchor — pair this tutorial with our AI positioning statement workflow so voice and message stop drifting against each other.
Common mistakes
- Defining voice from 2 examples — too thin. The signal is in the patterns across samples, not any single piece.
- No regular update — voice drifts and the doc becomes archaeology. Quarterly refresh.
- Voice doc that’s 10 pages — no one reads it, including the AI you load it into. Edit ruthlessly.
- Using only “great” pieces without bad examples — anti-examples are half the signal. Include 1-2 pieces the AI should NOT sound like.
- Trusting the AI’s “joke style” analysis without verification — humor is the hardest signal; AI often misreads it.
- Stopping at the voice doc when the creator is a person, not a brand — extend with AI creator brand tutorial so the doc captures founder voice, not generic brand voice.
FAQ
- Which model for the analysis?: Claude Sonnet 4.6+ or GPT-5.5. Smaller models miss voice nuance and over-generalize.
- Can the voice doc replace a copy editor?: Not for facts, structure, or first drafts. It enforces tone consistency, which is one slice of editing.
- My voice changes by channel (newsletter vs Twitter vs landing pages). One doc?: Multiple docs, one per channel. Cross-link them in a master index.
- What if my writing is bad and I want a better voice?: Then this isn’t the right tool yet. Develop the voice in your own writing first; then distill it.
- How do I share this across a team?: Voice doc in the team handbook + loaded as Claude Project context + 30-minute team walkthrough on the rationale. The walkthrough matters more than the doc.