NameAPI is a web API
to handle people's names
in your software.

News

18.11.2024

Dictionary Update: Ukrainian Names

A member of the East Slavic family, the Ukrainian language shares deep historical roots with...


04.11.2024

New Python Client Library Released

We have implemented a Python client library, now available on PyPI, providing easy access to...


22.10.2024

Software Version 10.6.0 Released

This update brings several improvements and new features designed to enhance the accuracy and...


11.10.2024

Discovering Czech Names

As part of the West Slavic group, the Czech language shares similarities with Slovak and Polish,...


25.09.2024

Romanian Names Added

The Romanian language, a Romance language derived from Latin, is unique in Eastern Europe,...


   

Name Genderizer


       
Attempts to detect the person's gender based on the inputs, especially the person's name.
See also the Swagger specification.
                    
POST
       
application/json (you must set the content-type as http header)
       
We have integrated Swagger directly into our API.
Visit https://api.nameapi.org/rest/swagger-ui/.

   

Input

               
See Context.
   
{
  "context" : {
     "priority" : "REALTIME",
     "properties" : [ ]
   },
  "inputPerson" : {
    "type" : "NaturalInputPerson",
    "personName" : {
      "nameFields" : [ {
        "string" : "Andrea",
        "fieldType" : "GIVENNAME"
      }, {
        "string" : "Bocelli",
        "fieldType" : "SURNAME"
      } ]
    },
    "gender" : "UNKNOWN"
  }
}      
   

   

Output

       
Possible values:

The person is clearly 'male'.

The person is clearly 'female'.

Can be either male or female. See malePercent.

No gender could be computed, but better intelligence should be able to tell the gender. An example is a name input of which we have never heard before.

From the given data it is or seems impossible to tell the gender.
For example all terms are gender-inapplicable, or there are no names at all. Thus this differs from NEUTRAL where something is clearly known to be neutral.

There are conflicting genders in the given data.
Example: "Mr Daniela Miller" (salutation vs. given name).
The input data must be manually reviewed. It is impossible and useless to make a guess (garbage in would only cause garbage out).

       
If neutral (otherwise null) then this may be specified (but does not have to be), 0-1, the remaining % are for female.
       
0-1 where 1 is the best.
   
{
  "gender" : "MALE",
  "confidence" : 0.9111111111111111
}