Skip to main content
All CollectionsTranslate and collaborateTasks
AI Translations
AI Translations

Assign tasks to AI to quickly and accurately translate content in a fully automated way.

Ilya Krukowski avatar
Written by Ilya Krukowski
Updated over 2 months ago

You might also be interested in learning about AI-powered language quality assurance and the AI suggestions features.

Also make sure to check our free Lokalise AI course covering all AI-based features and providing best practices.

AI Translations is a new task type that allows you to translate content swiftly and accurately using full automation.

Powered by Lokalise AI assistant, built on OpenAI's GPT API, this feature translates content while considering context, including your glossary terms and any instructions provided during task creation. This ensures that translations are not only fast but also aligned with your project's specific requirements.

Introduction

AI Translations is a task type designed to make use of Lokalise AI for translating your content. Here’s what it offers:

  • Create tasks to translate content into 30 languages and their variations (see the full list below).

    • The task is automatically assigned to the Lokalise AI assistant.

    • During the task, all translation keys are automatically locked until the Lokalise AI assistant completes the job for each respective language.

  • Provide additional instructions to the AI when creating the task, such as specifics about the target audience, tone of voice, or formality level.

  • Receive notifications when the translation for each language is finished.

  • Ensure that translations respect your glossary terms by leveraging existing terminology.

AI Translations usually take just a few minutes to complete, although the time can vary depending on the amount of content and the number of languages selected. You’ll be able to see the estimated completion time once you’ve chosen the languages and scope.

Supported languages

AI Translations currently supports the following languages and their variations for different locales:

Fully supported locales

  1. Afrikaans

  2. Arabic

  3. Catalan

  4. Chinese Simplified

  5. Chinese Traditional

  6. Czech

  7. Danish

  8. Dutch

  9. English

  10. Estonian

  11. Finnish

  12. French

  13. German

  14. Hebrew

  15. Hindi

  16. Hungarian

  17. Indonesian

  18. Italian

  19. Japanese

  20. Korean

  21. Latvian

  22. Lithuanian

  23. Polish

  24. Portuguese

  25. Romanian

  26. Russian

  27. Slovak

  28. Slovenian

  29. Spanish

  30. Swedish

  31. Turkish

  32. Ukrainian

  33. Urdu

  34. Vietnamese

Additionally, the following locales and their variations are supported in beta. These languages have been added recently, and we're still evaluating their quality. Therefore, we recommend double-checking the AI translation results for these languages:

Locales in beta

  1. Albanian

  2. Armenian

  3. Azerbaijani

  4. Basque (Spain)

  5. Bengali

  6. Bulgarian

  7. Chinese Traditional (Hong Kong, zh_HK)

  8. Chinese Traditional (Hong Kong, zh_Hant_HK)

  9. Congolese Swahili

  10. Croatian

  11. French (Reunion)

  12. Georgian

  13. Greek

  14. Icelandic

  15. Icelandic (Iceland)

  16. Irish

  17. Kazakh

  18. Kyrgyz

  19. Malay

  20. Maltese

  21. Norwegian

  22. Persian

  23. Persian (Afghanistan)

  24. Persian (Iran)

  25. Serbian

  26. Swahili

  27. Swahili (Kenya)

  28. Swahili (Tanzania)

  29. Tajik

  30. Thai

  31. Uzbek

Note: This is not an exhaustive list. It will be updated based on the quality level and our confidence in each language. If you'd like us to support additional languages and are willing to help with translation quality evaluation, please let us know!

Using AI Translations

Creating a new AI Translations task

Keep in mind that AI Translations consume AI words quota. If the team that the project belongs to does not have any AI words left, you won't be able to create the AI Translations task. Refer to the Team quotas article to learn more.

To get started with AI Translations, open any project in Lokalise and create a new task. There are two ways to create a task.

Via the editor

It's important to remember that a translation key cannot be assigned to a new task if it is already part of another ongoing task. To include such a key in a new task, you have two options:

  1. Wait for the existing task to be completed: Once the task is finished, the key will be available for reassignment in a new task.

  2. Remove the key from the current task: If you need to reassign the key immediately, go to the project editor, select the key, and use the Remove from task option available in the bulk actions menu. This will free up the key, allowing it to be included in a different task. However, if the key is already marked as completed in the task, it won't be possible to remove it from that task.

Start by selecting multiple keys in the editor. You can do this by ticking the checkboxes next to the keys you want to include in the task.

Once selected, choose Create task... from the bulk actions menu. This will take you directly to the task creation page, where the task scope is automatically set to the keys you’ve selected.

Via the Tasks page

Alternatively, you can create a task from the Tasks page in your project. Simply navigate to your project and go to the Tasks page:

Click Create a task. This will open the task creation wizard, where you can define the task's details and scope.

Providing general task information

In the task creation wizard, you'll find a new task type called Automatic translation (Lokalise AI). Select this type to begin.

Start by providing a task name and filling in instructions for Lokalise AI. These instructions help the AI translate content more accurately, tailored to your specific needs.

Here are some examples of what you might include in the instructions:

  • Translate idioms into equivalents appropriate for the target audience.

  • Maintain a conversational tone.

  • Use simple language.

  • Do not translate idiomatic expressions word-for-word.

  • Avoid unnecessary abbreviations.

Please note that the instructions field has a 2000-character limit. Once you’ve completed your instructions, proceed to the next step.

You can attach a style guide to the task to give further context and guidance to the AI.

Lokalise AI will also respect your project glossary and use entries from it during the translation process.

Adjusting advanced task options

When setting up an AI Translation task, the advanced options are limited to the following:

  • Apply 100% translation memory matches — when enabled, Lokalise will search for exact (100%) matches in the translation memory for the strings included in the task. If a match is found, it will be used directly, ensuring consistency with previous translations.

    • With this option, Lokalise AI will not modify the translated text, so no AI words are consumed.

    • If a 100% matching TM entry is found, the next option, Use the best 75%-100% TM match as context for AI, will not affect the current translation.

  • Use the best 75%-100% TM match as context for AI — when enabled, Lokalise will search for the best matches in the translation memory within a 75%-100% similarity range. If such a match is found, it will be provided to the AI as contextual reference. Only the best match is sent to the AI, not all found entries.

    • This option consumes AI words since the AI still performs the translation, using the match as a guide..

    • Enable this option if you want the AI to be creative and not rely solely on exact TM matches.

  • Save translations performed by AI to Translation memory — choose whether you want translations done by Lokalise AI to be saved into your translation memory. This can help build a more robust TM for future tasks.

  • Tag keys after the task is closed — tnable this option to automatically tag the translation keys added to the task once it’s completed. This helps in easily identifying and managing these keys later.

  • Save as task template — you can save this task as a template, allowing you to reuse the scope and language settings for future tasks. This streamlines the process when creating similar tasks in the future.

Adjusting task scope

Select the scope and languages:

  • Task scope — adjust the filter to select the specific keys that need to be included in the task. This ensures that only the relevant content is translated.

  • Source language — choose the language that will serve as the reference for the translations. This is the language from which Lokalise AI will translate.

  • Target languages — select one or more languages that you want the Lokalise AI assistant to translate into.

    • Ensure that you choose the correct locale for each target language. Incorrect or unspecified regions can lead to unexpected translation results. For instance, selecting "Portugal" might cause the AI to use Brazilian Portuguese. To avoid this, make sure to choose "Portuguese (Portugal)" for translations intended for that region.

  • Task assignees — you cannot modify assignees in AI Translation tasks, as all translations will be automatically handled by the Lokalise AI assistant.

Task summary

On the right side of the task creation wizard, you'll see the task summary and your Lokalise AI words balance:

  • AI words quota: This section shows the AI words quota for your team and the number of AI words that will be consumed by this specific task. For more details on your team's quota, refer to the Team quotas article.

  • Estimated delivery time: The summary also provides an estimated delivery time for the task. Keep in mind that this is an approximate figure and may fluctuate depending on the current system load.

Frequently asked questions

What context is used for the AI translations task?

The AI will use:

Will Lokalise AI overwrite existing translations?

If a key is added to an AI translation task, its existing translations will be overwritten. The only exception is when you enable the Apply 100% translation memory matches option. In this case, the AI will attempt to find exact (100%) matches in the translation memory. If a match is found, it will be used right away, and the AI words quota won't be affected.

What features are available?

You'll be able to use the AI Translations to provide instructions to Lokalise AI and run automatic translations in bulk taking into account the context and your terminology.

How does Lokalise AI translation work?

Lokalise AI uses Open AI models to assist with content translation. At Lokalise, we add an extra layer on top of OpenAI’s models to improve the precision and accuracy of your translations. For example, we give you the option to add context, like glossary terms and style guides, which Lokalise AI takes into account to deliver terms and phrases that are more accurately translated.

What types of content can be translated using Lokalise AI?

Lokalise AI translation is incredibly versatile and can handle a wide range of content types, including websites, documents, emails, marketing materials, user-generated content, and more. It can adapt to different industries and content formats, making it the perfect solution for businesses aiming to reach global audiences.

How accurate are Lokalise AI translations?

Lokalise AI translations can vary depending on factors like language pair and content complexity. But based on feedback from our customers, we can give you a ballpark estimation of around 80% accuracy. In most cases, you might just need to make minor changes for the remaining 20% to make it perfect for your specific needs.

Can Lokalise AI handle translations of highly specialized or technical content?

Absolutely! Lokalise AI can handle translations of highly specialized or technical content. Our AI models are trained to understand complex terminology, ensuring accurate translations even for the most specialized industries.

How will my data be used?

The only data being processed by LQA is the source text, target translations, key descriptions, and glossary terms matching the content. We’ll use the data for machine learning unless you explicitly withdraw your consent to do so. Machine learning is vital for us as it'll allow to introduce new AI-powered features and enhance the existing ones.

Related Articles
Tasks
Automations
Machine translation
Translation editor
AI LQA
Did this answer your question?