# overview: FAQs
URL: https://generaltranslation.com/en-US/docs/overview/faqs.mdx
---
title: FAQs
description: Frequently Asked Questions
---
### What is a locale?
A locale is **a language or dialect**.
For example, `en-US` is a locale code, which refers to the English language as spoken in the United States of America.
* [Read more about locales](/docs/core/locales)
* [List of supported locales](/docs/platform/supported-locales)
### Can I use the libraries without using the General Translation platform?
Yes you can!
General Translation internationalization libraries are free, open-source, and can be configured to fetch translations from any source.
Read the docs on how to load your own translations [here](/docs/next/api/config/load-translations).
### Section-specific FAQs
- Platform (coming soon)
- Locadex AI Agent (coming soon)
- Next.js App Router (coming soon)
- React (coming soon)
- React Native (coming soon)
- CLI (coming soon)
- Sanity Plugin (coming soon)
{/*
- [Platform](/docs/platform/faqs)
- [Locadex AI Agent](/docs/platform/faqs)
- [Next.js App Router](/docs/next/faqs)
- [React](/docs/react/faqs)
- [React Native](/docs/react-native/faqs)
- [CLI](/docs/cli/faqs)
- [Sanity Plugin](/docs/sanity/faqs)
*/}
{/* REMOVED BELOW, BECAUSE THEY SHOULD BE IN FRAMEWORK SPECIFIC FAQs */}
{/*
### What happens if there are missing translations in production?
If a translation for some content is missing in production, GT libraries automatically fallback to the original source text.
### Why do I have to install the CLI tool?
The CLI tool parses the content inside all `` components and generates translations for that content in advance,
so that all the translations are ready when your app is deployed to production.
In development, you don't need it because you can use development API keys to translate on demand.
## Technical FAQs
### Where does the `` get its translations? What translations does it use?
`` can technically load translations from anywhere depending on how you've configured the library.
If you have a project ID, the library can hit a free CDN.
It can also store translations locally, or do a mix of the two.
See the [load-translations docs](/docs/next/api/config/load-translations#fetching-translations-from-your-bundle) for more details.
During development, so you can see the translations hot-reload when you change content, the `` component hits an API which uses a small AI model to create temporary translations. These translations aren't stored anywhere, they're just served back to the app.
In production, `` won't do this in order to not leak your API keys.
### Does the AI translation also work with dynamic content and variables?
The `` component doesn't support translating dynamic content and variables,
because this means the translations could potentially change with every re-render.
However, you can still include dynamic content and variables inside a `` by wrapping them with
``, ``, `` components.
This is similar to how other libraries do string interpolation.
For gt-next, there is also a `` server-side component which does actually do translations on the spot in production,
and supports any form of dynamic content, but it requires an API key.
### How does the offline system work? Can I deploy an application with GT without dependency on your servers?
Yes you can, but you'd have to do the translations yourself,
then load them either from your own bundle or your own CDN.
See our docs on that: [here](/docs/next/api/config/load-translations#fetching-translations-from-your-bundle).
## Business 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](https://generaltranslation.com/terms).
## General FAQs
### What are tokens?
When text is sent to [GT](https://www.generaltranslation.com) 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](https://generaltranslation.com/pricing).
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](https://openai.com/index/gpt-4/). You can explore this tokenizer [here](https://platform.openai.com/tokenizer).
### 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.
*/}