> 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/engaging/replies-and-engage-twitter.md).

# Replies and Engage (Twitter)

**In short:** the Engage tab finds tweets worth replying to and drafts a reply in your voice. You pick a tone, audenAI writes one reply, and you post it through the reply window. Replies are a paid feature.

Open **Replies** from the sidebar. On a Twitter profile you will see the **Engage** grid and an **Extension** tab. (You must have a trained voice first; an untrained profile is asked to train before replying.)

### How Engage works

1. VoiceMoat surfaces up to five candidate tweets worth replying to.
2. For each one, pick a **tone** (or let audenAI pick) and it drafts **one** reply in your voice.
3. Edit if you want, then **post through the reply window** and mark it done.

There is one reply per generate, not a pile of variants to sift through. You get one free regenerate per tweet if the first is not right.

{% hint style="info" %}
Replies are drafted in **your own** voice plus your **Engage persona** (the "about you" and product notes you set in Voice Lab). It is not a "reply as this creator" tool; it is you, sounding like you, with context.
{% endhint %}

### Where candidates come from

Your Engage grid blends three sources, ranked and de-duplicated:

* your **home timeline**,
* recent posts matching your **keywords**,
* and recent posts from the **creators you track**.

Fresh candidates appear through the day, and you can **Refresh** anytime to pull more. A paid **extra pull** (40 more slots for 5 credits) is there when you want a bigger batch.

### The two limits worth understanding

Replying touches two separate caps. They are easy to confuse, so here they are side by side:

|                                 | Free | Creator | Pro | Enterprise |
| ------------------------------- | ---- | ------- | --- | ---------- |
| **Replies per day (overall)**   | 10   | 150     | 300 | 500        |
| **Engage reply budget per day** | 0    | 30      | 70  | 100        |
| Candidate pulls per day         | 0    | 60      | 100 | 150        |
| Keyword searches                | 0    | 3       | 5   | 10         |
| Tracked creators                | 0    | 5       | 10  | 20         |

* The **overall** reply limit is your total replies a day, including those from the Chrome extension.
* The **Engage budget** is the smaller allowance specifically for replies sent from the Engage grid.

{% hint style="info" %}
The Engage budget only ticks when you **mark a reply done**. Drafting and regenerating do not spend it. Each drafted reply does cost 1 credit from your daily pool.
{% endhint %}

Free plans cannot use Engage (it is a paid feature). For replying on LinkedIn, see Replies on LinkedIn.

### Common questions

**Why does posting open a window instead of posting directly?** Twitter replies go out through the reply window so you confirm each one. You then mark it done, which ticks your Engage budget.

**Do skips cost anything?** No. Skipping a candidate is free.

**Can I reply without opening the dashboard?** Yes. The Chrome extension puts a reply coach on every tweet in your feed.


---

# 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/engaging/replies-and-engage-twitter.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.