Language AI works with two types of translation engines:
- Generic Engines
- Custom-Trained Engines
By default, Language AI uses pre-trained generic engines for translations. However, Language AI is flexible and can be configured to work with custom-trained engines based on branding requirements.
Generic Engines
Generic engines are pre-trained AI models designed to translate text from one language to another. They're created by training on a diverse set of data sources to ensure broad coverage of languages and content. List of supported languages for Generic Engines of Language AI for FAQ translations.
Custom-trained Engines
Custom-trained engines provide AI models fine-tuned with your specific data. This delivers key advantages over default generic engines:
- Precise, contextual translations that accurately reflect industry and brand terminology
- Consistent brand voice and style across languages
- Ideal for translating industry-specific content containing unique jargon
By training models with your own data, these tailored engines ensure maximum relevance and accuracy for your content, maintaining your brand identity globally. List of supported languages for custom-trained engines of Language AI for FAQ translations.
Brands can deploy a single custom-trained engine at the domain level or multiple custom-trained engines at the app level within a domain, based on the number of apps, supported languages, and brand specific requirements. With a single domain-level custom engine, all translation requests are mapped to that engine.
When multiple app-level engines are used, issue translations and FAQ translations are handled by their respective custom-trained engines. However, text template translations use generic engines, as they cannot be associated with any specific app.
Note: Custom engine training is an add-on service. Please contact success@helpshift.com to know more about custom-trained engines.
List of supported languages for Generic engines of Language AI for FAQ and Text Template Translations:
Sr No | Language |
1 | Afrikaans |
2 | Albanian |
3 | Amharic |
4 | Arabic |
5 | Armenian |
6 | Azerbaijani |
7 | Basque |
8 | Belarusian |
9 | Bulgarian |
10 | Catalan |
11 | Chinese-Traditional |
12 | Chinese-Simplified |
13 | Croatian |
14 | Czech |
15 | Danish |
16 | Dutch |
17 | English |
18 | Estonian |
19 | Filipino (Tagalog) |
20 | Finnish |
21 | French |
22 | Galician |
23 | Georgian |
24 | German |
25 | Greek |
26 | Gujarati |
27 | Hebrew |
28 | Hindi |
29 | Hungarian |
30 | Igbo |
31 | Indonesian |
32 | Irish |
33 | Italian |
34 | Japanese |
35 | Kannada |
36 | Kazakh |
37 | Korean |
38 | Lao |
39 | Latvian |
40 | Lithuanian |
41 | Malay |
42 | Maltese |
43 | Marathi |
44 | Nepali |
45 | Norwegian |
46 | Pashto |
47 | Persian |
48 | Polish |
49 | Portuguese |
50 | Punjabi |
51 | Quechua |
52 | Romanian |
53 | Russian |
54 | Samoan |
55 | Serbian |
56 | Sesotho |
57 | Sinhala |
58 | Slovak |
59 | Slovenian |
60 | Somali |
61 | Spanish |
62 | Swahili |
63 | Swedish |
64 | Tajik |
65 | Tamil |
66 | Telugu |
67 | Thai |
68 | Turkish |
69 | Turkmen |
70 | Ukrainian |
71 | Urdu |
72 | Uzbek |
73 | Vietnamese |
74 | Xhosa |
75 | Zulu |
List of supported languages for custom-trained engines of Language AI for FAQ and Text Template Translations:
Sr No | Language |
1 | Arabic |
2 | Bulgarian |
3 | Chinese (Traditional) |
4 | Chinese (Simplified) |
5 | Croatian |
6 | Czech |
7 | Danish |
8 | Dutch |
9 | English |
10 | Finnish |
11 | French |
12 | German |
13 | Greek |
14 | Hebrew |
15 | Hindi |
16 | Hungarian |
17 | Indonesian |
18 | Italian |
19 | Japanese |
20 | Korean |
21 | Latvian |
22 | Norwegian |
23 | Polish |
24 | Portuguese |
25 | Romanian |
26 | Russian |
27 | Slovak |
28 | Slovenian |
29 | Spanish |
30 | Swedish |
31 | Thai |
32 | Turkish |