AI Translations is a new task type that enables you to quickly and accurately translate content in a fully automated way. It uses Lokalise AI assistant built on OpenAI's GPT API to automatically translate content taking into account context, such as your glossary terms, and instructions you provide when creating a task.
AI Translations is a new task type that is built on top of the Lokalise AI. AI Translations task provides the following capabilities:
Create a task to translate content in 30 languages and their variations (see full list below)
The task will be automatically assigned to Lokalise AI assistant
During the ongoing task, all translation keys will be automatically locked until Lokalise AI assistant finishes the job for the respective language
Provide additional instructions to Lokalise AI upon task creation, such as specifics about target audience, tone of voice or formality level to be used
Receive notifications upon language translation completion
Leverage existing terminology to ensure that all translations respect your glossary terms
On average, AI Translations takes just a few minutes to complete but this heavily depends on the amount of content and number of languages that you decide to perform it on. You would be able to see estimated time of completion once you selected languages and scope.
AI Translations currently supports the following languages and their variations for different locales: Afrikaans, Arabic, Catalan, Czech, Danish, German, English, Spanish, Estonian, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Lithuanian, Latvian, Dutch, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Swedish, Turkish, Ukrainian, Urdu, Vietnamese, Chinese Traditional, Chinese Simplified.
Additionally, the following locales and their variations are supported in beta: Azerbaijani, Bulgarian, Bengali, Greek, French (Reunion), Croatian, Armenian, Georgian, Kazakh, Kyrgyz, Malay, Norwegian, Slovenian, Albanian, Serbian, Thai, Uzbek. These languages have been added recently and we’re still evaluating its quality. Thus, we recommend to double-check the AI translation results.
This is not an exhaustive list. It will be updated based on the quality level and our confidence in quality for the respective language. In case you want us to support other languages and are happy to help with translation quality evaluation, let us know.
Using AI Translations
Creating a new AI Translations task
To get started with AI Translations, open any project in Lokalise and create a new task. There are two ways to create a task.
First, you can select multiple keys in the editor by ticking checkboxes next to their names and then choosing Create task... from the bulk actions menu. This will open the task creation page with a predefined task scope, limited to the keys you have just selected.
Alternatively, open your project and proceed to the Tasks page:
Click Create a task to open the task creation wizard.
In the task creation wizard you will see a new task type called Automatic translation (Lokalise AI). Choose this type:
Provide the task name and fill in instructions for Lokalise AI. These instructions will be used to translate content more accurately.
Some examples of what you can include as 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.
Instructions field has a 2000 character limit. Once you have completed instructions, proceed to the next step.
You can also attach a style guide to the task. Please refer to the corresponding article to learn more.
Adjusting task options
Advanced task options will be limited to the following:
Apply 100% translation memory matches — when enabled, Lokalise attempts to find exact (100%) matches in the translation memory for the strings included in the task. If a match is found, it will be used straight away. This feature provides consistent results with the translation history.
In this case Lokalise AI will not perform any additional modifications to the translated text, meaning this option doesn't consume AI words.
Please note that if the system detects a 100% matching TM entry, the subsequent option Use the best 75%-100% TM match as context for AI (see below) will not affect the current translation.
Use the best 75%-100% TM match as context for AI — when enabled, Lokalise will try to search for the best translation memory entries for the strings included in the task. If a match within 75-100% similarity range is identified, it will be provided to the AI as contextual reference. Please note that only the best match is sent to the AI, rather than all found entries.
This functionality consumes AI words since the identified match is sent only as contextual reference, and the AI will still need to perform the actual translation.
Enable this option if you'd like the AI to be creative and not rely solely on existing 100%-matching TM entries.
Save translations performed by AI to Translation memory — you can choose whether you want translations performed by Lokalise AI to be saved into your translation memory or not.
Tag keys after the task is closed — tag translation keys added to the current task once it's completed. This way you'll be able to easily identify these keys afterwards.
Save as task template — this task can be used as a base when creating other tasks (scope and languages will be pre-selected).
Adjusting task scope
Select the scope and languages:
Task scope — adjust the filter to choose the keys that should be added to the task.
Source language — choose the language that should be used as a reference for performing quality evaluation.
Target languages — choose one or more languages that should be evaluated by Lokalise AI assistant.
Task assignees — you won't be able to modify assignees as all languages will be assigned to Lokalise AI assistant for automatic translation.
To the right, you'll see the task summary and your Lokalise AI words balance:
In this summary you can see the AI words quota for your team and the number of AI words to be consumed in this exact task. Please refer to the Team quotas article to learn about the words quota.
You will also see the estimated delivery time for this task. Please note this is an approximate number and it can fluctuate depending on the load on our system.
Frequently asked questions
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 key descriptions, 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. This data is not used for other purposes, such as model training.