POST
/
translate
curl --request POST \
  --url https://api.sarvam.ai/translate \
  --header 'Content-Type: application/json' \
  --data '{
  "input": "<string>",
  "source_language_code": "auto",
  "target_language_code": "en-IN",
  "speaker_gender": "Female",
  "mode": "formal",
  "model": "mayura:v1",
  "enable_preprocessing": false,
  "output_script": "roman",
  "numerals_format": "international"
}'
{
  "request_id": "<string>",
  "translated_text": "<string>",
  "source_language_code": "<string>"
}

Headers

​
api-subscription-key
string
default:

Your unique subscription key for authenticating requests to the Sarvam AI APIs. Here are the steps to get your api key

Body

application/json
​
input
string
required

The text you want to translate. This is the input text that will be processed by the translation model.

Maximum length: 1000
​
source_language_code
enum<string>
required

The language code of the input text. This specifies the source language for translation.

Note: The source language should either be an Indic language or English. As we supports both Indic-to-English and English-to-Indic translation.

Available options:
auto,
en-IN,
hi-IN,
bn-IN,
gu-IN,
kn-IN,
ml-IN,
mr-IN,
od-IN,
pa-IN,
ta-IN,
te-IN
​
target_language_code
enum<string>
required

The language code of the translated text. This specifies the target language for translation.

Note:The target language should either be an Indic language or English. As we supports both Indic-to-English and English-to-Indic translation.

Available options:
en-IN,
hi-IN,
bn-IN,
gu-IN,
kn-IN,
ml-IN,
mr-IN,
od-IN,
pa-IN,
ta-IN,
te-IN
​
speaker_gender
enum<string>

Please specify the gender of the speaker for better translations. This feature is only supported for the code-mixed translation models currently.

Available options:
Male,
Female
​
mode
enum<string>

Specifies the tone or style of the translation. Choose between formal, classic-colloquial and modern-colloquial translations. Default is formal.

Available options:
formal,
modern-colloquial,
classic-colloquial,
code-mixed
​
model
enum<string>

Specifies the translation model to use. Currently, only one model is supported.Note:- This parameter is optional but will be deprecated by the end of January; avoid including it in your requests.

Available options:
mayura:v1
​
enable_preprocessing
boolean
default:false

This will enable custom preprocessing of the input text which can result in better translations.

​
output_script
enum<string> | null

output_script: This is an optional parameter which controls the transliteration style applied to the output text.

Transliteration: Converting text from one script to another while preserving pronunciation.

We support transliteration with four options:

  • null(default): No transliteration applied.

  • roman: Transliteration in Romanized script.

  • fully-native: Transliteration in the native script with formal style.

  • spoken-form-in-native: Transliteration in the native script with spoken style.

Example:

English: Your EMI of Rs. 3000 is pending. Default modern translation: आपका Rs. 3000 का EMI pending है (when null is passed).

With postprocessing enabled, we provide the following style of outputs:

  • roman output: aapka Rs. 3000 ka EMI pending hai.
  • fully-native output: आपका रु. 3000 का ई.एम.ऐ. पेंडिंग है।
  • spoken-form-in-native output: आपका थ्री थाउजेंड रूपीस का ईएमअइ पेंडिंग है।
Available options:
roman,
fully-native,
spoken-form-in-native
​
numerals_format
enum<string>

numerals_format is an optional parameter with two options:

  • international (default): Uses regular numerals (0-9).
  • native: Uses language-specific native numerals.

Example:

  • If international format is selected, we use regular numerals (0-9). For example: मेरा phone number है: 9840950950.
  • If native format is selected, we use language-specific native numerals, like: मेरा phone number है: ९८४०९५०९५०.
Available options:
international,
native

Response

200
application/json
Successful Response
​
request_id
string | null
required
​
translated_text
string
required

Translated text result in the requested target language.

​
source_language_code
string
required

Detected or provided source language of the input text.