> For the complete documentation index, see [llms.txt](https://docs.voicemoat.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.voicemoat.com/voice-and-audenai/voice-lab.md).

# Voice Lab

**In short:** Voice Lab is where you train your voice and see what audenAI learned from it. It has four tabs, works per profile, and is platform-aware (a Twitter profile and a LinkedIn profile each have their own Voice Lab).

Open it from the sidebar. If a profile has not been trained yet, Voice Lab is the first thing it asks you to do.

### The four tabs

| Tab                | What it does                                                                                                            |
| ------------------ | ----------------------------------------------------------------------------------------------------------------------- |
| **Insights**       | Shows what audenAI learned from your real posts, and which of your recent posts broke out or fell flat.                 |
| **Dimensions**     | A deep read of your voice across seven sections (rhythm, hooks, vocabulary, formatting, and more), generated on demand. |
| **Train audenAI**  | Where you set writing rules, toggle the post-coach checks, keep a never-say list, and preview the effect live.          |
| **Engage persona** | Product mentions and the projects you are working on, so replies and posts can reference them naturally.                |

### What each tab is for

**Insights** is the "what does audenAI think I sound like" view. It is the fastest way to sanity-check that training worked.

**Dimensions** goes deeper: seven cached sections that break your voice down (voice dimensions, hook styles, sentence rhythm, emoji habits, vocabulary, formatting, topic clusters). It is generated by audenAI and refreshes on a limited schedule rather than on every visit.

{% hint style="info" %}
The Dimensions deep read refreshes on a rolling limit: once every 30 days on Creator, twice on Pro, and once every 7 days on Enterprise. Free plans do not generate it. Everyday drafting does not need a refresh; this is the occasional deep re-read.
{% endhint %}

**Train audenAI** is the steering wheel. You are not retyping your voice here; you are nudging it with explicit rules (emoji use, casing, punctuation, reply length), turning post-coach checks on or off, and listing words or phrases you never want to see. A live preview shows the effect as you change things.

**Engage persona** is what keeps replies grounded. It holds a short "about you", your writing rules for replies, and any product or project you want audenAI to be able to mention, so drafts sound like a real person with context, not a generic commenter.

### Per profile, per platform

Voice Lab always reflects the **active profile**. Switch profiles and you are looking at that profile's voice. A Twitter voice and a LinkedIn voice are trained and stored separately, because you write differently in each place.

### Who can use it

Voice Lab (training and all four tabs) is a paid feature. Free plans cannot train a voice; Creator, Pro, and Enterprise can, along with the trial.

### Next steps

* Training your voice: how training actually works on each platform.
* The 10 signals: what audenAI listens for.
* Retraining your voice: keeping it current as you evolve.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.voicemoat.com/voice-and-audenai/voice-lab.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.