Alternative front-end for Google Translate, serving as a Free and Open Source translator with over a hundred languages available
Inspired by projects like NewPipe, Nitter, Invidious or Bibliogram, Lingva scrapes through Google Translate and retrieves the translation without directly accessing any Google-related service, preventing them from tracking.
For this purpose, Lingva is built, among others, with the following Open Source resources:
- Lingva Scraper, a Google Translate scraper built and maintained specifically for this project, which obtains all kind of information from this platform.
- TypeScript, the JavaScript superset, as the language.
- React as the main front-end framework.
- Next.js as the complementary React framework, that provides Server-Side Rendering, Static Site Generation or serverless API endpoints.
- ChakraUI for the in-component styling.
- Jest, Testing Library & Cypress for unit, integration & E2E testing.
- Apollo Server for handling the GraphQL endpoint.
- Inkscape for designing both the logo and the banner.
As Lingva is a Next.js project you can deploy your own instance anywhere Next is supported.
The only requirement is to set an environment variable called NEXT_PUBLIC_SITE_DOMAIN with the domain you're deploying the instance under. This is used for the canonical URL and the meta tags.
Optionally, there are other environment variables available:
NEXT_PUBLIC_FORCE_DEFAULT_THEME: Force a certain theme over the system preference set by the user. The accepted values arelightanddark.NEXT_PUBLIC_DEFAULT_SOURCE_LANG: Set an initial source language instead of the defaultauto.NEXT_PUBLIC_DEFAULT_TARGET_LANG: Set an initial target language instead of the defaulten.
An official Docker image is available to ease the deployment using Compose, Kubernetes or similar technologies. Remember to also include the environment variables (simplified to site_domain, force_default_theme, default_source_lang and default_target_lang) when running the container.
version: '3'
services:
lingva:
container_name: lingva
image: thedaviddelta/lingva-translate:latest
restart: unless-stopped
environment:
- site_domain=lingva.ml
- force_default_theme=light
- default_source_lang=auto
- default_target_lang=en
ports:
- 3000:3000
docker run -p 3000:3000 -e site_domain=lingva.ml -e force_default_theme=light -e default_source_lang=auto -e default_target_lang=en thedaviddelta/lingva-translate:latestAnother easy way is to use the Next.js creators' own platform, Vercel, where you can deploy it for free with the following button.
These are the currently known Lingva instances. Feel free to make a Pull Request including yours (please remember to add [skip ci] to the last commit).
Nearly all the Lingva instances should supply a pair of public developer APIs: a RESTful one and a GraphQL one.
Note: both APIs return the translation audio as a Uint8Array (served as number[] in JSON and [Int] in GraphQL) with the contents of the audio buffer.
- GET
/api/v1/:source/:target/:query
{
translation: string
info?: TranslationInfo
}- GET
/api/v1/audio/:lang/:query
{
audio: number[]
}- GET
/api/v1/languages/?:(source|target)
{
languages: [
{
code: string,
name: string
}
]
}In addition, every endpoint can return an error message with the following structure instead.
{
error: string
}/api/graphql
query {
translation(source: String target: String query: String!) {
source: {
lang: {
code: String!
name: String!
}
text: String!
audio: [Int]!
detected: {
code: String
name: String
}
typo: String
pronunciation: String
definitions: {
type: String
list: {
definition: String
example: String
field: String
synonyms: [String]
}
}
examples: [String]
similar: [String]
}
target: {
lang: {
code: String!
name: String!
}
text: String!
audio: [Int]!
pronunciation: String
extraTranslations: {
type: String
list: {
word: String
article: String
frequency: Int
meanings: [String]
}
}
}
}
audio(lang: String! query: String!) {
lang: {
code: String!
name: String!
}
text: String!
audio: [Int]!
}
languages(type: SOURCE|TARGET) {
code: String!
name: String!
}
}- Lingva Scraper - Google Translate scraper built and maintained specifically for this project
- SimplyTranslate - Very simple translation front-end with multi-engine support
- LibreTranslate - FOSS translation service that uses the open Argos engine
- Lentil for Android - Unofficial native client for Android that uses Lingva's public API
- Arna Translate - Unofficial cross-platform native client that uses Lingva's public API
- Translate-UT - Unofficial native client for Ubuntu Touch that uses Lingva's public API
Thanks goes to these wonderful people (emoji key):
 David ️️️️♿️ 💻 📖 🎨 |
 Mohammed Anas 💻 |
 TheFrenchGhosty 📖 |
This project follows the all-contributors specification. Contributions of any kind welcome!
Copyright © 2021 thedaviddelta & contributors.
This project is GNU AGPLv3 licensed.