Automatic suggestions¶
Changed in version 4.13: Prior to Weblate 4.13, the services were configured in the Configuration.
The support for several machine translation and translation memory services is built-in. Each service can be turned on by the administrator for whole site (under Automatic suggestions in Management interface) or at the project settings:
Note
They come subject to their terms of use, so ensure you are allowed to use them how you want.
The services translate from the source language as configured at Component configuration, see Source language.
Per-project automatic suggestion can also be configured via the Weblate’s REST API.
See also
Alibaba¶
Added in version 5.3.
- Service ID:
alibaba
- Configuration:
key
Access key ID
secret
Access key secret
region
Region ID
Alibaba Translate is a neural machine translation service for translating text and it supports up to 214 language pairs.
See also
Apertium APy¶
- Service ID:
apertium-apy
- Configuration:
url
API URL
A libre software machine translation platform providing translations to a limited set of languages.
The recommended way to use Apertium is to run your own Apertium-APy server.
See also
Amazon Translate¶
- Service ID:
aws
- Configuration:
key
Access key ID
secret
API secret key
region
Region name
Amazon Translate is a neural machine translation service for translating text to and from English across a breadth of supported languages. The service requires the TranslateFullAccess Managed Policy.
The service automatically uses Glossary, see Glossaries in automatic suggestion.
Baidu¶
- Service ID:
baidu
- Configuration:
key
Client ID
secret
Client secret
Machine translation service provided by Baidu.
This service uses an API and you need to obtain an ID and API key from Baidu to use it.
See also
Cyrtranslit¶
Added in version 5.7.
- Service ID:
cyrtranslit
- Configuration:
This service has no configuration.
Machine translation service using the Cyrtranslit library.
This service converts text between Cyrillic and Latin scripts for languages that have both scripts.
See also
DeepL¶
- Service ID:
deepl
- Configuration:
url
API URL
key
API key
formality
Formality
Uses the specified formality if language is not specified as (in)formal
context
Translation context
Describe the context of the translation to improve the accuracy of the translation.
DeepL is paid service providing good machine translation for a few languages. You need to purchase DeepL API subscription or you can use legacy DeepL Pro (classic) plan.
API URL to use with the DeepL service. At the time of writing, there is the v1 API as well as a free and a paid version of the v2 API.
https://api.deepl.com/v2/
(default in Weblate)Is meant for API usage on the paid plan, and the subscription is usage-based.
https://api-free.deepl.com/v2/
Is meant for API usage on the free plan, and the subscription is usage-based.
https://api.deepl.com/v1/
Is meant for CAT tools and is usable with a per-user subscription.
Previously Weblate was classified as a CAT tool by DeepL, so it was supposed to use the v1 API, but now is supposed to use the v2 API. Therefore it defaults to v2, and you can change it to v1 in case you have an existing CAT subscription and want Weblate to use that.
The easiest way to find out which one to use is to open an URL like the following in your browser:
https://api.deepl.com/v2/translate?text=Hello&target_lang=FR&auth_key=XXX
Replace the XXX with your auth_key. If you receive a JSON object which contains “Bonjour”, you have the correct URL; if not, try the other three.
Weblate supports DeepL formality, it will choose matching one based on the
language (for example, there is de@formal
and de@informal
).
The translation context can optionally be specified to improve translations quality. Read more on that in DeepL translation context documentation.
The service automatically uses Glossary, see Glossaries in automatic suggestion.
See also
Glosbe¶
- Service ID:
glosbe
- Configuration:
This service has no configuration.
Free dictionary and translation memory for almost every living language.
The API is gratis to use, but usage of the translations is subject to the license of the used data source. There is a limit of calls that may be done from one IP in a set period of time, to prevent abuse.
See also
Google Cloud Translation Basic¶
- Service ID:
google-translate
- Configuration:
key
API key
Machine translation service provided by the Google Cloud services.
This service uses the Google Translation API v2, and you need to obtain an API key and turn on billing in the Google API console.
See also
Google Cloud Translation Advanced¶
- Service ID:
google-translate-api-v3
- Configuration:
credentials
Google Translate service account info
Enter a JSON key for the service account.
project
Google Translate project
Enter the numeric or alphanumeric ID of your Google Cloud project.
location
Google Translate location
Choose a Google Cloud Translation region that is used for the Google Cloud project or is closest to you.
bucket_name
Google Storage Bucket name
Enter the name of the Google Cloud Storage bucket that is used to store the Glossary files.
Machine translation service provided by the Google Cloud services.
This service uses the Google Translation API v3 and you need credentials in JSON format to access it.
In order to use this service, you first need to go through the following steps:
Optionally, you can configure the service to use Glossary by setting up a Bucket:
IBM Watson Language Translator¶
Added in version 4.16.
- Service ID:
ibm
- Configuration:
url
API URL
key
API key
Warning
This service is deprecated by vendor and will be withdrawn entirely as of 10 December 2024.
IBM Watson Language Translator translates text from one language to another. The service offers multiple domain-specific models.
See also
LibreTranslate¶
Added in version 4.7.1.
- Service ID:
libretranslate
- Configuration:
url
API URL
key
API key
LibreTranslate is a free and open-source service for machine translations. The public instance requires an API key, but LibreTranslate can be self-hosted and there are several mirrors available to use the API for free.
https://libretranslate.com/
(official public instance)Requires an API key to use outside of the website.
Azure AI Translator¶
- Service ID:
microsoft-translator
- Configuration:
key
API key
base_url
Application base URL
Available choices:
api.cognitive.microsofttranslator.com
– Global (non-regional)api-apc.cognitive.microsofttranslator.com
– Asia Pacificapi-eur.cognitive.microsofttranslator.com
– Europeapi-nam.cognitive.microsofttranslator.com
– North Americaapi.translator.azure.cn
– Chinaapi.cognitive.microsofttranslator.us
– Azure US Government cloudendpoint_url
Authentication service URL
Regional or multi-service can be specified using region field below.
Available choices:
api.cognitive.microsoft.com
– Globalapi.cognitive.azure.cn
– Chinaapi.cognitive.microsoft.us
– Azure US Government cloudregion
Authentication service region
category
Category
Specify a customized system category ID to use it instead of general one.
Machine translation service provided by Microsoft in Azure portal as a one of Cognitive Services.
Weblate implements Translator API V3.
The service automatically uses Glossary via dynamic dictionary, see Glossaries in automatic suggestion.
Translator Text API V2¶
The key you use with Translator API V2 can be used with API 3.
Translator Text API V3¶
You need to register at Azure portal and use the key you obtain there.
With new Azure keys, you also need to set region
to locale of your service.
You can also specify a custom category to use custom translator.
Hint
For Azure China, please use your endpoint from the Azure Portal.
Azure OpenAI¶
Added in version 5.8.
- Service ID:
azure-openai
- Configuration:
key
API key
persona
Translator persona
Describe the persona of translator to improve the accuracy of the translation. For example: “You are a squirrel breeder.”
style
Translator style
Describe the style of translation. For example: “Use informal language.”
azure_endpoint
Azure OpenAI endpoint URL
Endpoint URL of the instance, e.g: https://my-instance.openai.azure.com.
deployment
Azure OpenAI deployment
The model’s unique deployment name.
Performs translation using OpenAI hosted on Azure.
See also
ModernMT¶
Added in version 4.2.
- Service ID:
modernmt
- Configuration:
url
API URL
key
API key
context_vector
Context vector
Comma-separated list of memory IDs:weight. e.g: 1234:0.123,4567:0.456
The service automatically uses Glossary, see Glossaries in automatic suggestion.
See also
MyMemory¶
- Service ID:
mymemory
- Configuration:
email
Contact e-mail
username
Username
key
API key
Huge translation memory with machine translation.
Free, anonymous usage is currently limited to 100 requests/day, or to 1000
requests/day when you provide a contact e-mail address in email
.
You can also ask them for more.
See also
Netease Sight¶
- Service ID:
netease-sight
- Configuration:
key
Client ID
secret
Client secret
Machine translation service provided by NetEase.
This service uses an API, and you need to obtain key and secret from NetEase.
See also
OpenAI¶
Added in version 5.3.
- Service ID:
openai
- Configuration:
key
API key
base_url
OpenAI API base URL
Base URL of the OpenAI API, if it differs from the OpenAI default URL
model
OpenAI model
Available choices:
auto
– Automatic selectiongpt-4o
– GPT-4ogpt-4-1106-preview
– GPT-4 Turbogpt-4
– GPT-4gpt-3.5-turbo-1106
– Updated GPT 3.5 Turbogpt-3.5-turbo
– GPT-3.5 Turbocustom
– Custom modelcustom_model
Custom model name
Only needed when model is set to ‘Custom model’
persona
Translator persona
Describe the persona of translator to improve the accuracy of the translation. For example: “You are a squirrel breeder.”
style
Translator style
Describe the style of translation. For example: “Use informal language.”
Performs translation using OpenAI.
The OpenAI API is powered by a diverse set of models with different capabilities and price points. Automatic selection chooses the best model available, but you might want to choose a specific model that matches your needs.
Use persona and style fields to further fine-tune translations. These will be used in a prompt for OpenAI and allow you to change the style of the translations.
The service automatically uses Glossary, see Glossaries in automatic suggestion.
Changed in version 5.7: Support for custom model and base URL was added.
See also
SAP Translation Hub¶
- Service ID:
sap-translation-hub
- Configuration:
url
API URL
key
API key
username
SAP username
password
SAP password
enable_mt
Enable machine translation
domain
Translation domain
The ID of a translation domain, for example, BC. If you do not specify a domain, the method searches for translations in all available domains.
Machine translation service provided by SAP.
You need to have a SAP account (and the SAP Translation Hub enabled in the SAP Cloud Platform) to use this service.
You can also configure whether to also use machine translation services, in addition to the term database.
Note
To access the Sandbox API, you need to set url
and key
.
To access the productive API, you need to set url
, username
and password
.
Systran¶
- Service ID:
systran
- Configuration:
key
API key
Machine translation service provided by Systran.
This service uses an API, and you need to obtain API key at <https://translate.systran.net/en/account>.
tmserver¶
- Service ID:
tmserver
- Configuration:
url
API URL
You can run your own translation memory server by using the one bundled with Translate-toolkit and let Weblate talk to it. You can also use it with an amaGama server, which is an enhanced version of tmserver.
First you will want to import some data to the translation memory:
build_tmdb -d /var/lib/tm/db -s en -t cs locale/cs/LC_MESSAGES/django.po
build_tmdb -d /var/lib/tm/db -s en -t de locale/de/LC_MESSAGES/django.po
build_tmdb -d /var/lib/tm/db -s en -t fr locale/fr/LC_MESSAGES/django.po
Start tmserver to listen to your requests:
tmserver -d /var/lib/tm/db
Configure Weblate to talk to it, the default URL is
http://localhost:8888/tmserver/
.
See also
tmserver, Installing amaGama, Amagama, Amagama Translation Memory
Weblate¶
- Service ID:
weblate
- Configuration:
This service has no configuration.
Weblate machine translation service can provide translations based on the exact matches of a string in the currently existing strings in a Translated, Approved, or Read-only states inside Weblate.
Weblate Translation Memory¶
- Service ID:
weblate-translation-memory
- Configuration:
This service has no configuration.
Use Translation Memory as a machine translation service. Any string that has been translated before (or uploaded to the translation memory) can be translated in this way. This suggestion source works with fuzzy matching.
Note
Recreating Translation Memory reduces capabilities of this TM source.
Yandex¶
- Service ID:
yandex
- Configuration:
key
API key
Machine translation service provided by Yandex.
This service uses a Translation API, and you need to obtain an API key from Yandex.
Yandex v2¶
Added in version 5.1.
- Service ID:
yandex-v2
- Configuration:
key
API key
Machine translation service provided by Yandex.
This service uses a Translation API, and you need to obtain an API key from Yandex Cloud.
Youdao Zhiyun¶
- Service ID:
youdao-zhiyun
- Configuration:
key
Client ID
secret
Client secret
Machine translation service provided by Youdao.
This service uses an API, and you need to obtain an ID and an API key from Youdao.
Custom machine translation¶
You can also implement your own machine translation services using a few lines of
Python code. This example implements machine translation in a fixed list of
languages using dictionary
Python module:
# Copyright © Michal Čihař <michal@weblate.org>
#
# SPDX-License-Identifier: GPL-3.0-or-later
"""Machine translation example."""
import dictionary # type: ignore[import-not-found]
from weblate.machinery.base import DownloadTranslations, MachineTranslation
class SampleTranslation(MachineTranslation):
"""Sample machine translation interface."""
name = "Sample"
def download_languages(self):
"""Return list of languages your machine translation supports."""
return {"cs"}
def download_translations(
self,
source,
language,
text: str,
unit,
user,
threshold: int = 75,
) -> DownloadTranslations:
"""Return tuple with translations."""
for t in dictionary.translate(text):
yield {"text": t, "quality": 100, "service": self.name, "source": text}
You can list your own class in WEBLATE_MACHINERY
and Weblate
will start using that.