> For the complete documentation index, see [llms.txt](https://docs.letr.ai/en/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.letr.ai/en/overview/3-project.md).

# #3 Project

Work and content localization is done in projects.

Projects can be divided into text, video, and image, depending on the source content type.

<figure><img src="/files/slxupn30WTIfvbtPSV60" alt=""><figcaption></figcaption></figure>

## Text project

Here is the text localization project.

{% hint style="info" %}
**Which text file formats are supported?**

Supports **docx, doc, xlsx, xls, pptx, ppt, txt, and vue** formats.

However, the result files are the same as the original format. (e.g. docx -> docx)
{% endhint %}

Text projects are completed in the following categories.

<table><thead><tr><th width="263">Category</th><th>Description</th></tr></thead><tbody><tr><td>Correction</td><td>Checks the text of the source</td></tr><tr><td>Translation</td><td>Translates the original source text</td></tr><tr><td>Review</td><td>Check and revise source text and translation results</td></tr></tbody></table>

## Video Project

This is a project for localizing video subtitles.

{% hint style="info" %}
**What video file formats are supported?**

Supports **YouTube video** or **mp4** format.
{% endhint %}

Video projects are completed in the following categories.

<table><thead><tr><th width="256">Category</th><th>설명</th></tr></thead><tbody><tr><td>Transcription</td><td>Review subtitles and timecode generated by analyzing the source video</td></tr><tr><td>Translation</td><td>Check the timecode of translated subtitles</td></tr><tr><td>Review</td><td>Check and edit translated subtitles</td></tr></tbody></table>

{% hint style="info" %}
**What is transcription?**

It refers to automatically generating subtitles and timecode by breaking down the audio in the video.

**What languages can you transcribe?**

Currently, 'Korean,' 'English,’ 'Japanese,' and 'Chinese' transcriptions are available.
{% endhint %}

You can upload the subtitle file directly for a faster transcription process.

* The timecode value in the uploaded file is applied to the project.&#x20;

{% hint style="info" %}
**What subtitle file formats are supported?**

Supports **.srt, .vtt, .csv, .ttml** files of up to 1MB or less.
{% endhint %}

## Image project

This project is for text localization within images (webtoons, etc.).

{% hint style="info" %}
**What image content formats are supported?**

Supports **jpg/jpeg, png, tif/tiff, bmp, gif, dcx, pcx, jp2, jpc, jfif** formats.

However, the result file is only in **png** format.
{% endhint %}

Image projects are completed in the following categories.

<table><thead><tr><th width="263">Category</th><th>Description</th></tr></thead><tbody><tr><td>Correction</td><td>Check the text in the source image</td></tr><tr><td>Translation</td><td>Translate text from the source image</td></tr><tr><td>Review</td><td>Check and modify the text and work results</td></tr></tbody></table>

## [Related project](https://docs.letr.ai/project/3)

We proceed with the type of project that best suits the situation at each stage of content localization, ensuring consistent work by linking the projects. This approach leads to excellent localization results.

{% hint style="info" %}
**How can I create a related project?**

You can create it in your workspace after completing the project.
{% endhint %}

Related projects can be carried out in the following types.

<table><thead><tr><th width="263"> Type</th><th>Description</th></tr></thead><tbody><tr><td>Translation</td><td>Translates original text into another language</td></tr><tr><td>Review</td><td>Modifies and supplements translations</td></tr><tr><td>Dubbing</td><td>Converts translation into voice</td></tr><tr><td>Syncsub</td><td>Adjusts subtitle timing</td></tr></tbody></table>

{% content-ref url="/pages/75poGxDivTl9D8QSI0cg" %}
[Project management](/en/pj_mm/1-classification-and-permissions.md)
{% endcontent-ref %}


---

# 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.letr.ai/en/overview/3-project.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.