> For the complete documentation index, see [llms.txt](https://docs.itranslator.app/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.itranslator.app/amazing-features/conversation-mode.md).

# Conversation Mode

Group messages from the same user and translate them together for better context and improved efficiency — a Pro exclusive feature.

{% hint style="info" %}
This feature requires [**Pro**](/overview/premium.md).
{% endhint %}

<figure><img src="https://3955709218-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FuW8Vjy8RHWcWMwcAWdcy%2Fuploads%2Fgit-blob-b52ebee0003cb16bafb195d70e968b7afbd02bb9%2Fconversation-mode-test.gif?alt=media" alt="Several messages sent in a row are translated together as one"><figcaption></figcaption></figure>

## What is Conversation Mode?

People often send several short messages in a row. Instead of translating each one the moment it arrives, iTranslator waits for a short delay and groups all the messages sent by the **same user** in the **same channel** during that time. The whole batch is then translated as a single unit.

The translation engine gets more context, so the result is more natural and coherent, and your server makes fewer translation calls.

## How does it work?

{% stepper %}
{% step %}

### A member sends a message

It is sent in a channel where iTranslator is active.
{% endstep %}

{% step %}

### iTranslator starts a timer

Instead of translating immediately, it waits for the delay you configured.
{% endstep %}

{% step %}

### The following messages join the batch

Any other message sent by the **same user** in the **same channel** before the timer ends is added to the batch.
{% endstep %}

{% step %}

### The batch is translated

When the timer ends, all the messages of the batch are translated together.
{% endstep %}
{% endstepper %}

{% hint style="info" %}
Messages that contain embeds are **translated immediately**: they always bypass the delay.
{% endhint %}

## Set the delay

The delay goes from **0 to 10 seconds**. Setting it to **0** disables Conversation Mode and brings back the standard translation, message by message.

{% tabs %}
{% tab title="Dashboard" %}
Open your server in the [dashboard](/fundamentals/dashboard.md), go to **Server → Configuration** and set **Delay (seconds)** in the **Conversation Mode** card.

<figure><img src="https://3955709218-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FuW8Vjy8RHWcWMwcAWdcy%2Fuploads%2Fgit-blob-033bfa6915275243104217cc5c90b103cae16a40%2Fdashboard-config.png?alt=media" alt="The Configuration page of the dashboard with the Conversation Mode card"><figcaption></figcaption></figure>
{% endtab %}

{% tab title="Commands" %}
The commands require the **Manage Server** permission.

<table><thead><tr><th width="300">Command</th><th>Description</th></tr></thead><tbody><tr><td><code>/conversation-mode delay &#x3C;delay></code></td><td>Sets the batch delay in seconds (0–10). <strong>0</strong> disables Conversation Mode.</td></tr><tr><td><code>/conversation-mode help</code></td><td>Displays a summary of the feature and the delay configured on your server.</td></tr></tbody></table>

For example, to batch the messages sent within 3 seconds:

```
/conversation-mode delay 3
```

{% endtab %}
{% endtabs %}

## Conversation Mode vs standard translation

|                         | Conversation Mode     | Standard translation         |
| ----------------------- | --------------------- | ---------------------------- |
| **Availability**        | Pro only              | All plans                    |
| **Processing**          | Batched after a delay | Immediate, per message       |
| **Efficiency**          | Higher (fewer calls)  | Lower (one call per message) |
| **Translation context** | The grouped messages  | Each message on its own      |
| **Embed messages**      | Processed immediately | Processed immediately        |

## Tips

* **Start with a short delay (2–3 s).** It is long enough to catch quick follow-up messages while still feeling responsive.
* **Use 0 to disable.** Nothing else has to be changed.
* **Best for active communities.** The feature shines in busy channels where members often send several short messages in a row.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.itranslator.app/amazing-features/conversation-mode.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.