🎙️ Brand Voice
Brand Voice shapes how drafts are written for your X account: suggested replies, Slack drafts, and generated posts all follow these settings. Set the tone once, add your facts and guardrails, and every AI-written draft sounds like you.
Configuration
To configure Brand Voice:
- Open your workspace in the Fren One webapp.
- In the sidebar under Channels, select the X account you want to configure. Its pages open beneath it.
- Select Agent Settings. Brand Voice is the second section of the page, below Language and Audience.
Agent Settings is open to the workspace Owner and Admins, and to any member holding the + X grant. Everyone else sees it locked in the sidebar: "Requires the X grant. Ask a workspace owner or admin."
Language and Audience
The first section of Agent Settings controls how the account handles language. Replies are written in the Reply language set here, not by a Brand Voice guardrail.
| Option | Description |
|---|---|
| Translate mentions to | Foreign-language mentions are translated into this language before they reach your inbox, Slack, and digest emails. Any of the webapp's 14 languages; default English. |
| Reply language | The language auto-drafted replies are written in: Match the post, or a specific language. Default English. |
| Primary audience | The region your posts mainly target; suggested posting times aim for this audience's peak hours. Auto (workspace time zone) (default), or a region such as North America, Europe or East Asia. |
Voice & persona
These settings define how drafts sound.
| Option | Description |
|---|---|
| Tone | Casual, Professional, Technical, Friendly (default), Empathetic, or Authoritative. |
| Reply length | Concise (default), Balanced, or Detailed. "Concise suits X best." |
| About this account | Facts the writer can rely on: what you do, who you serve, what you offer. Max 2,000 characters. |
| Voice samples | "Paste 2–3 of your best posts. Drafts imitate their rhythm and vocabulary." Max 2,000 characters. |
Guardrails
Guardrails are hard limits the writer must respect, regardless of tone.
| Option | Description |
|---|---|
| Never say | One rule per line: topics, claims, or phrases drafts must avoid. Overrides everything. Max 2,000 characters. |
| Emoji | Never, Sparingly (default), or Freely. |
| Hashtags | Never (default) or When relevant. |
Knowledge base grounding
"Ground drafts in your knowledge base" is on by default. It pulls facts from your workspace's knowledge base so replies answer with real information. With grounding on, each draft looks up relevant knowledge-base entries before writing, and each draft consumes AI credits.
Writing model
Choose which model writes your drafts:
| Option | Description |
|---|---|
| Fast | Lowest credit use. |
| Quality | "Best everyday writing. The default." |
| Reasoning | "Careful replies for tricky threads." |
Test drive
Try the voice before it writes anything real:
The test drive uses your current settings, including unsaved changes.
- Pick a mode: "Reply to a mention" (default) or "New post".
- Choose a scenario pill: Recent mention (shown when the account has one), Support question, Praise, or Complaint: or paste your own sample into the textarea (max 1,000 characters).
- Select "Generate sample".
Each sample is a real draft generated with your current settings: it costs AI credits just like a production draft.
How drafts are written
Every draft produced through Brand Voice follows the same runtime guardrails:
- Drafts are plain text, capped at 280 characters.
- The draft follows your emoji and hashtag policies and your Reply language, and stays within your chosen reply length.
- The writer is instructed to never invent facts, prices, dates, or promises.
- "Never say" rules are enforced last, with a final re-check before the draft is returned.
These settings power the drafts you see in inbox suggested replies, the Slack "Generate reply" action (see Integrations), and the test drive above. Drafts from Ask AI are a separate path that does not apply Brand Voice: see AI Post Drafting.
Saving your changes
Agent Settings uses one batched save for both sections: edits stay local until you select Save in the bar that appears at the bottom of the page. Leaving the page with unsaved changes shows a warning first.
Best practices
- Fill in About this account with concrete facts: it's the difference between a generic reply and one that answers correctly.
- Paste real posts into Voice samples; drafts imitate their rhythm and vocabulary, so pick your best.
- Keep Never say rules short and unambiguous: one clear rule per line beats a paragraph.
- Turn on knowledge-base grounding if members ask factual questions, and keep your knowledge base current.
- Use the test drive with the Complaint scenario: the hardest case is the best check of your guardrails.
Troubleshooting
Drafts aren't using your knowledge-base facts?
- Check that "Ground drafts in your knowledge base" is toggled on and the knowledge base actually contains the facts.
- If a knowledge-base lookup fails, the draft falls back to writing without it rather than failing entirely.
Ask AI drafts ignore these settings?
- That's expected: Ask AI drafts are grounded in workspace data but don't apply Brand Voice. Edit them in the Messages, or draft from a Brand Voice surface instead.
Agent Settings is locked for you?
- Brand Voice needs the Owner or Admin level, or the + X grant. Ask the Owner or an Admin to add the grant to your access.
Related features
- 📅 Messages: Compose, schedule, and publish the posts your voice produces
- 🤖 AI Post Drafting: Ask AI drafts, and why they don't use Brand Voice
- 📡 Listening: The mentions your suggested replies respond to
- 🔌 Integrations: Slack alerts with the Brand Voice "Generate reply" action