The Cloud Natural Language API supports a variety of languages.
These languages are specified within a request using the optional language
parameter. Language code parameters conform to
ISO-639-1 or
BCP-47 identifiers.
If you do not specify a language
parameter, then the language for
the request is auto-detected by the Natural Language API.
The list of supported languages differs depending on the feature.
Content classification
Language |
ISO-639-1 Code |
Chinese (Simplified) |
zh |
Chinese (Traditional) |
zh-Hant |
Dutch |
nl |
English |
en |
French |
fr |
German |
de |
Italian |
it |
Japanese |
ja |
Korean |
ko |
Portuguese (Brazilian & Continental) |
pt |
Russian |
ru |
Spanish |
es |
Language |
ISO-639-1 Code |
English |
en |
Syntactic analysis
Language |
ISO-639-1 Code |
Chinese (Simplified) |
zh |
Chinese (Traditional) |
zh-Hant |
English |
en |
French |
fr |
German |
de |
Italian |
it |
Japanese |
ja |
Korean |
ko |
Portuguese (Brazilian & Continental) |
pt |
Russian |
ru |
Spanish |
es |
Entity analysis
Language |
ISO-639-1 Code |
Chinese (Simplified) |
zh |
Chinese (Traditional) |
zh-Hant |
English |
en |
French |
fr |
German |
de |
Italian |
it |
Japanese |
ja |
Korean |
ko |
Portuguese (Brazilian & Continental) |
pt |
Russian |
ru |
Spanish |
es |
Sentiment analysis
Language |
ISO-639-1 Code |
Arabic |
ar |
Chinese (Simplified) |
zh |
Chinese (Traditional) |
zh-Hant |
Dutch |
nl |
English |
en |
French |
fr |
German |
de |
Indonesian |
id |
Italian |
it |
Japanese |
ja |
Korean |
ko |
Portuguese (Brazilian & Continental) |
pt |
Spanish |
es |
Thai |
th |
Turkish |
tr |
Vietnamese |
vi |
Entity sentiment analysis
Language |
ISO-639-1 Code |
English |
en |
Japanese |
ja |
Spanish |
es |
Text moderation
Language |
ISO-639-1 Code |
Arabic |
*ar |
Chinese (Simplified) |
zh |
Dutch |
*nl |
English |
en |
French |
fr |
German |
de |
Hindi |
*hi |
Indonesian |
*id |
Italian |
it |
Japanese |
ja |
Korean |
ko |
Portuguese (Brazilian & Continental) |
pt |
Russian |
*ru |
Spanish |
es |
*language support is limited based on the type of text (eg. webpage, chat message, etc) for some attributes. In any case, we recommend thorough evaluation for your use case.