> 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**](https://docs.itranslator.app/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](https://docs.itranslator.app/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.
