Transliteration API
Overview
Transliteration API
The Transliteration API is a REST API used to transliterate the content from English to Indic languages and vice-versa.
The solution is an automated solution that converts the content in real-time. It is easy to integrate into your applications and display content in the 11 most popular Indian languages
What is Transliteration?
Transliteration is the process of converting texts from one script to another based on phonetic similarity. Here, the text is displayed in alphabets of different languages, but the pronunciation, grammar, and sense of the original version remain intact in these new characters.
Transliteration is involved while converting the names, addresses, titles, and more into Indian languages as localization is important without changing meaning. For a better understanding, refer to the below examples:
| Type | English Alphabets (Latin Script) | Hindi Alphabets (Devanagari Script) |
|---|---|---|
City Name | New Delhi | न्यू दिल्ली |
City Name | Pune | पुणे |
City Name | Bengaluru | बेंगलुरु |
Brand | Bata | बाटा |
Brand | Bajaj | बजाज |
Brand | Reliance | रिलायन्स |
Person Name | A R Rahaman | ए आर रहमान |
Person Name | Mani Ratnam | मणि रत्नम |
Person Name | Anu Malik | अनु मलिक |
In the above example, only the script of the content is converted from the English language (Latin Script) to the Hindi language (Devanagari Script).
But, the pronunciation of the words remains the same.
Supporting Languages
Transliteration API supports 22 Indic languages, including Rare languages. It converts scripts from English to 22 Indic languages and 12 Indic languages to English. It also transliterates scripts from one regional language to another (for example: Hindi to Tamil).
Languages Supported for English to Indic Conversion (Forward Transliteration)-
|
|
|
|
|
|
|
|
|
|
|
|
13. Sindhi | 14. Dogri | 15. Konkani | 16. Bodo |
|
| 19. Manipuri | 20. Nepali |
|
|
Languages Supported for Indic to English Conversion (Reverse Transliteration)-
|
|
|
|
|
|
|
|
|
|
|
|
Key Features
The Transliteration API has effectual features that recognize it as the best in the content localization industry:
Word-sense Disambiguation:
The API will successfully identify the context of a word used in the source content and then transliterates accordingly. This feature will decrease the editorial work as it can recognize the meaning of the word and help the native language users consume the content in the right order.
Example 1:
Consider: Source Language = English & Target Language = Hindi
| Source Content | Transliterated Content |
|---|---|
1St main, 3rd St, St. Johns Road | फर्स्ट (1St) मेन, थर्ड (3rd) स्ट्रीट, सेण्ट. जोन्स रोड |
In the above example, the word St will appear thrice:
suffix for 1
Acronym for Street
Acronym for Saint
The intelligent solution will automatically analyze the statement’s context and transliterate as First, 3rd street, and Saint appropriately.
Example 2:
Consider: Source Language = English & Target Language = Hindi
Note: Source content consists of Hindi language words written in English Script (Latin Script)
| Source Content | Transliterated Content |
|---|---|
Singh Sahab The Great, aap Kahan the | सिहं साहब द ग्रेट, आप कहाँ थे |
In the above example, the word "The" is used twice
Singh Sahab the Great: Used as an Adjective
Aap Kahan the: The sentence in the Hindi language meaning, "where were you?" The smart solution will analyze the sentences of different languages and transliterate accurately.
Customizable Vocabulary Model
Tailor the vocabulary to generate accurate transliterations specific to your use-cases, such as product names, domain-specific terminology, or individual names
One Solution for Multiple Use-cases
Through API integration, our solution is easily deployable on all the digital platforms. We support both On-premise and Cloud-based deployment models.
Supporting Domains
| Domain ID | Domain Name | Description |
|---|---|---|
1 | Default | Domain ID 1 will transliterate generic content irrespective of domain |
2 | Names | Use domain ID 2 to transliterate the people’s names. |
4 | OnlyEnglish | The domain developed to transliterate the source content from the English script to the Indic language script. |
5 | Cricketers | The domain developed to transliterate the names of the cricket players. It will efficiently transliterate foreign people’s names. |
6 | Banking | The Banking domain will transliterate the banking and financial terminologies accurately. |
7 | Brands | The domain is specially designed to transliterate the Brand & product catalog. |
9 | Addresses | Domain developed to transliterate the location details like street name, city name, state, etc. |
10 | NumberInWords | The NumberInWords domain will accurately convert the numbers into words in the target language script. |
22 | Food | Domain developed to transliterate the food item name like the food menu of a restaurant etc. |
25 | Media & Entertainment | The domain is built especially for the entertainment industry. It will transliterate the song lyrics, song title, movie titles, artist names, and more media-related information. |
26 | Grocery | This domain is mostly designed for online shopping of grocery items. It will transliterate grocery & essential item names like rice, dals, oil, packaged food, dairy items, pet food, household cleaning items & personal care products and more. |
27 | Healthcare | This domain is for the healthcare industry and it will transliterate words like - insurance, medicine, fever, cheston cold tablet, paracetamol. Note - This is only available for Hindi language. |
28 | Enterprise | This domain is mostly designed for job titles, company names etc. It will transliterate names like - urbanclap, biostatistician, recruiter, developer, practo. |
Some of the examples that describe how our transliteration API produces different results based on domain:
| Input | English | Name | Address | Banking | Native | Grocery |
|---|---|---|---|---|---|---|
dr | डॉक्टर | डेबिट | ||||
hr | एच.आर | आवर | ||||
unsalted | अन्सैल्ट्ड | अनसॉल्टेड | ||||
gandhi st | गांधी स्ट्रीट | |||||
st vincent | सटें वि न्सेन्ट | |||||
pt | पी.टी. | पंडित | ||||
teethers | टीदर्स | टीथर्स | ||||
paltu | पल्टू | पालतू | ||||
gela | गेला | गिला | ||||
neelay | निलय | नीले | ||||
dhar | धर | धार | ||||
mohd rafi | मोहम्मद रफी | मोहम्मद रफी |
Supporting Use-Cases
The Transliteration API will support a wide range of use-cases, and the prominent are listed below:
| Use-Case | Description |
|---|---|
People Name | Conversion of people names into native scripts to help to pronounce accurately |
Address/ Location | Convert the location/ address details like place name, street details, etc. available on digital platforms like Map app, Unique Identity cards, and more into the native scrip |
Music File Content | Convert song lyrics and media file properties like song name, movie name, artist name, and more into Indic language scripts in real-time. |
Product Catalog | Accurately convert brand catalog details like brand name, product name, product specifications, etc. into Indic languages and build customer rapport. |
Financial Transactions/ Invoice | Using our Transliteration API, provide the financial transaction details & invoice in Indian languages. The financial transactions/ invoice will include purchased items, transaction description, transaction type, amount, etc. |
Food & Grocery Content | Conversion of food and grocery item names, and quantities into indic language |
Healthcare | Conversion of Medicine names, and healthcare products into indic language |
Last updated