- This version is built on a deep neural network capable of detecting more than 180 different languages.
- Bug fixed when for non-latin languages no variant was found.
- Bug fixed for language detection for languages with accent marks.
- More languages are supported, including script languages.
- Languages now are output as different objects within a list, instead of elements of a string.
- More information has been added to the language: its ISO codes, its name, an optionally other information about the language.
threshold parameter has been added so the languages in the results can be filtered by relevance.
- A new parameter has been added to define a white list of the languages the results should be limited to.
- Improved false negatives in English.
- Bug fixed in the XML output.
- Python client has been improved.
- The response headers have been updated so the content type is correct for all output formats supported.
- The documentation has been improved, both in format and contents.
- Error messages in all APIs have been unified.
- New features:
- The response now contains information regarding the credits consumed by the request and the remaining credits in the
- The output has been homogenized to follow the new standard for array elements in all APIs.
- A feedback section has been added to the website.
- HTTPS support has been added.
Click on the version number to see the changelog.