> 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/training-your-voice.md).

# Training your voice

**In short:** audenAI learns your voice from your real posts. On Twitter it reads your tweets through the API automatically; on LinkedIn it harvests your own posts with the Chrome extension, or you paste a few. Higher plans read more posts. The first training is free.

### Twitter

On a Twitter profile, training is automatic. In Voice Lab, click **Analyze my tweets** (or Re-analyze). VoiceMoat pulls your recent tweets through the Twitter API and builds your voice profile from them.

There is no upload and no paste. audenAI reads what you have already published.

### LinkedIn

LinkedIn does not offer an API for reading your posts, so training works one of two ways:

1. **Harvest with the Chrome extension (recommended).** With the extension installed and you signed in to LinkedIn, VoiceMoat reads your own recent posts from your session in one click.
2. **Paste your posts.** No extension? Paste 5 to 10 of your own posts (a minimum of 5) into Voice Lab and audenAI trains on those.

{% hint style="info" %}
LinkedIn voice trains only on **your own** LinkedIn posts. VoiceMoat used to be able to derive a LinkedIn voice from your Twitter writing; that is retired. Your LinkedIn voice now comes from LinkedIn, so it reflects how you actually write there.
{% endhint %}

### How much it reads

Higher plans read more of your posts when building the profile, so there is more to learn from:

| Plan       | Posts read when training |
| ---------- | ------------------------ |
| Free       | 20                       |
| Creator    | 50                       |
| Pro        | 100                      |
| Enterprise | 200                      |

(Free cannot build a voice profile in practice; training is a paid feature.)

### What it costs

The **first training is free**. Later re-trainings draw from your monthly training allowance and cost credits (20, or 30 on Pro and 50 on Enterprise, reflecting the larger read). Your monthly training allowance is 2 on Creator, 4 on Pro, and 8 on Enterprise. See Retraining your voice.

### Your data stays yours

{% hint style="success" %}
Your posts and the voice profile built from them are never used to train shared models or improve anyone else's experience. On LinkedIn, harvested data is locked to your own account identity, so it cannot be written to a different profile.
{% endhint %}

### Common questions

**How many posts do I need?** Enough to have a pattern. A handful works to start; more is better. If an account is brand new with very few posts, training may not have much to learn from yet.

**Can I train on someone else's writing?** No. Voice training is for your own voice. Studying other creators is a different feature; see Creator Library.

**I retrained and the voice changed a lot.** That is expected if your recent posting shifted. Training reflects your recent writing. If you want to steer it, use the Train audenAI tab's rules rather than retraining repeatedly.


---

# 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/training-your-voice.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.