General Translation  

FAQs

Do I own my translations?

Yes.

You, the customer, retain full ownership and rights to any translated output produced through the Services. We make no claim to your output.

For more, see our Terms of Use.

What are tokens?

When text is sent to GT APIs, it is broken down into chunks called tokens. Think of tokens as small pieces of your input text, like words or parts of words, that an AI model uses to understand and translate your content.

A helpful rule of thumb is that one token generally corresponds to ~4 characters of text for common English text. This translates to roughly ¾ of a word (so 100 tokens ~= 75 words).

For example, the string Hello, world! has 13 characters, and 4 tokens: Hello, ,, world, and !.

If you go over the token limit for your plan, we begin to charge based on token usage. We only ever charge based on the length of your input — never the length of the translation. Read more about our available plans here.

For example, imagine you have the string "Hello, world!", and your project's languages are "fr" (French), "es" (Spanish), and "de" (German). Token usage will be calculated as 4 * 3 = 12. That is, the 4 tokens of "Hello, world!", translated 3 times.

We currently tokenize with OpenAI's tiktoken, which is the same tokenizer used by GPT-4. You can explore this tokenizer here.

Locales? Languages? Regions? What's the difference?

Throughout this documentation, you will see us use the term locale and language somewhat interchangeably. For the most part, they do mean the same thing, but there are some subtle differences, and these will be made clear when necessary.

Language refers to a spoken or written form of communication used by humans.

Region refers to the area where a language is spoken or written. Of course, the language may remain the same, but vary between regions. For example, Canadian French versus French as spoken in France.

Locale is a combination of a language and a region, and is used to specify a particular language in a particular region. For example, en-US is English as spoken in the United States.

These differences are detailed further in our documentation on Locale Strings.

On this page