LILT Platform supports the following language features:
  • 445 language pairs with Contextual AI and Machine Translation support.
  • Unlimited languages using Translation Memory (TM).
  • Ability to specify language locales (regional variations) on a per-project basis.
LILT’s Baseline Contextual AI models are trained at the language level. Baseline Contextual AI models aren’t trained at the locale level because we use public domain data for training, and there isn’t enough locale-specific public data available to train locale-level models. However, each project has an associated Translation Memory and its own unique Contextual AI model. Both of these adapt to the locale of a project as TM entries are added (either by importing existing TM data or by translating segments in LILT Translate).

New Language Support

We add new AI-supported languages to the LILT Platform continuously based on three criteria:
  • Community and customer demand
  • Availability of training data
  • Baseline translation quality that is competitive with Google Translate and Microsoft Translator
Email us at sales@LILT.com to request LILT support for additional languages.

LILT V3 and V3.5 supported languages

Our models are trained in systems (i.e. groups) as opposed to single language pairs. V3.5 models are available for any two languages within each system.  Our V3.5 models are trained on 1.3 billion parameters, and have an improved ability to adapt to Data Sources, learn new terminology, and make translations sound more natural. Additionally, these models use context from the entire document and memory to improve the quality of your translations. Any language combination within a system below where one of the languages has a *, will be supported with a V3 model. The only difference from the V3.5 models is that these pairs will not use context from the entire document and memory.
SystemLanguage grouping (Any two)CodesModel
1English, German, Spanish, French, Italian, PortugueseEN,DE,ES,FR,IT,PTV3.5
2English, Japanese, Korean, Chinese (Simplified), Chinese (Traditional)EN,JA,KO,ZH,ZTV3.5
3English, Belarusian*, Bulgarian, Czech, Croatian, Lithuanian, Latvian, Polish, Romanian, Russian, Slovak, Slovenian, Albanian, Serbian, UkrainianEN, BE*, BG, CS, HR, LT, LV, PL, RO, RU, SK, SL, SQ, SR, UKV3.5
4English, Afrikaans, Danish, German, Greek, Estonian, Finnish, Hungarian, Armenian, Dutch, Norwegian, Swedish, TurkishEN, AF, DA, DE, EL, ET, FI, HU, HY, NL, NO, SV, TRV3.5
5English, Arabic, Bengali*, Kurdish*, Persian (Farsi), Dari, Gujarati, Hebrew, Hindi, Kannada*, Malayalam*, Marathi, Nepali*, Punjabi*, Pashto*, Tamil*, Telugu*, Tajik, UrduEN, AR, BN*, CKB*, FA, FS, GU, HE, HI, KN*, ML*, MR, NE*, PA*, PS*, TA*, TE*, TG, URV3.5
6English, Indonesian, Igbo*, Javanese*, Malay, Burmese (Myanmar), Thai, Tagalog (Filipino)*, Samoan*, Somali*, Swahili*, VietnameseEN, ID, IG*, JV*, MS, MY, TH, TL*, SM*, SO*, SW*, VIV3.5

Extended language support

The following languages are available for human verification:
  • Amharic
  • Azeri
  • Bosnian
  • Catalan
  • Creole
  • Icelandic
  • Kazakh
  • Khmer
  • Kinyarwanda
  • Lao
  • Maori
  • Mongolian
  • Sinhala
  • Zulu

Third-party provider support

Alternate LLMs that can be configured that may support other languages. Please reference the LILT Custom Models page for more information about third-party provider language support.