translate

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Translation with Mayura

基于Mayura的翻译

Mayura is Sarvam AI's translation model optimized for Indian languages with support for script variations, numeral formats, and code-mixed text.

Mayura是Sarvam AI专为印度语言优化的翻译模型，支持脚本变体、数字格式和混合代码文本。

Installation

安装

bash

pip install sarvamai

bash

pip install sarvamai

Quick Start

快速开始

python

from sarvamai import SarvamAI

client = SarvamAI()

response = client.translate.translate(
    input="Hello, how are you?",
    source_language_code="en-IN",
    target_language_code="hi-IN",
    model="mayura:v1"
)

print(response.translated_text)  # "नमस्ते, आप कैसे हैं?"

python

from sarvamai import SarvamAI

client = SarvamAI()

response = client.translate.translate(
    input="Hello, how are you?",
    source_language_code="en-IN",
    target_language_code="hi-IN",
    model="mayura:v1"
)

print(response.translated_text)  # "नमस्ते, आप कैसे हैं?"

Supported Languages

支持的语言

Code	Language	Code	Language
`hi-IN`	Hindi	`ta-IN`	Tamil
`bn-IN`	Bengali	`te-IN`	Telugu
`kn-IN`	Kannada	`ml-IN`	Malayalam
`mr-IN`	Marathi	`gu-IN`	Gujarati
`pa-IN`	Punjabi	`or-IN`	Odia
`en-IN`	English	`auto`	Auto-detect

代码	语言	代码	语言
`hi-IN`	印地语	`ta-IN`	泰米尔语
`bn-IN`	孟加拉语	`te-IN`	泰卢固语
`kn-IN`	卡纳达语	`ml-IN`	马拉雅拉姆语
`mr-IN`	马拉地语	`gu-IN`	古吉拉特语
`pa-IN`	旁遮普语	`or-IN`	奥里亚语
`en-IN`	英语	`auto`	自动检测

Translation Directions

翻译方向

English → Indian Language: Translate English to any supported Indian language
Indian Language → English: Translate any Indian language to English
Indian → Indian: Translate between Indian languages (via English pivot)

英语 → 印度语言： 将英语翻译为任何支持的印度语言
印度语言 → 英语： 将任何印度语言翻译为英语
印度语言 → 印度语言： 在印度语言之间进行翻译（以英语为中转）

Translation Modes

翻译模式

Formal Translation

正式翻译

python

response = client.translate.translate(
    input="Please submit the report by Friday",
    source_language_code="en-IN",
    target_language_code="hi-IN",
    model="mayura:v1",
    mode="formal"
)

python

response = client.translate.translate(
    input="Please submit the report by Friday",
    source_language_code="en-IN",
    target_language_code="hi-IN",
    model="mayura:v1",
    mode="formal"
)

Casual Translation

非正式翻译

python

response = client.translate.translate(
    input="Hey, what's up?",
    source_language_code="en-IN",
    target_language_code="hi-IN",
    model="mayura:v1",
    mode="casual"
)

python

response = client.translate.translate(
    input="Hey, what's up?",
    source_language_code="en-IN",
    target_language_code="hi-IN",
    model="mayura:v1",
    mode="casual"
)

Script Control

脚本控制

Choose the output script for languages with multiple scripts:

python

undefined

为有多脚本的语言选择输出脚本：

python

undefined

Hindi in Devanagari (default)

天城文印地语（默认）

response = client.translate.translate( input="Hello", source_language_code="en-IN", target_language_code="hi-IN", output_script="devanagari" )

Output: "नमस्ते"

输出："नमस्ते"

Hindi in Latin (transliteration)

拉丁化印地语（音译）

response = client.translate.translate( input="Hello", source_language_code="en-IN", target_language_code="hi-IN", output_script="latin" )

Output: "Namaste"

输出："Namaste"

undefined

undefined

Numeral Format

数字格式

Control numeral representation:

python

undefined

控制数字的显示格式：

python

undefined

International numerals (default)

国际数字格式（默认）

response = client.translate.translate( input="The price is 500 rupees", source_language_code="en-IN", target_language_code="hi-IN", numeral_format="international" )

Output: "कीमत 500 रुपये है"

输出："कीमत 500 रुपये है"

Native numerals

本地数字格式

response = client.translate.translate( input="The price is 500 rupees", source_language_code="en-IN", target_language_code="hi-IN", numeral_format="native" )

Output: "कीमत ५०० रुपये है"

输出："कीमत ५०० रुपये है"

undefined

undefined

Code-Mixed Input

混合代码输入

Mayura handles code-mixed text (e.g., Hinglish):

python

response = client.translate.translate(
    input="Yaar, let's go for a movie tonight",
    source_language_code="auto",  # Auto-detect
    target_language_code="hi-IN",
    model="mayura:v1"
)

Mayura支持处理混合代码文本（如印英混合语Hinglish）：

python

response = client.translate.translate(
    input="Yaar, let's go for a movie tonight",
    source_language_code="auto",  # 自动检测
    target_language_code="hi-IN",
    model="mayura:v1"
)

Output: "यार, चलो आज रात फिल्म देखने चलते हैं"

输出："यार, चलो आज रात फिल्म देखने चलते हैं"

undefined

undefined

Batch Translation

批量翻译

Translate multiple texts:

python

texts = [
    "Hello",
    "How are you?",
    "Thank you"
]

responses = []
for text in texts:
    response = client.translate.translate(
        input=text,
        source_language_code="en-IN",
        target_language_code="hi-IN",
        model="mayura:v1"
    )
    responses.append(response.translated_text)

print(responses)

翻译多条文本：

python

texts = [
    "Hello",
    "How are you?",
    "Thank you"
]

responses = []
for text in texts:
    response = client.translate.translate(
        input=text,
        source_language_code="en-IN",
        target_language_code="hi-IN",
        model="mayura:v1"
    )
    responses.append(response.translated_text)

print(responses)

[

"नमस्ते", "आप कैसे हैं?", "धन्यवाद" ]

undefined

"नमस्ते", "आप कैसे हैं?", "धन्यवाद" ]

undefined

JavaScript

JavaScript示例

javascript

import { SarvamAI
} from "sarvamai";

const client = new SarvamAI();

const response = await client.translate.translate({
  input: "Hello, how are you?",
  sourceLanguageCode: "en-IN",
  targetLanguageCode: "hi-IN",
  model: "mayura:v1"
});

console.log(response.translatedText);

javascript

import { SarvamAI
} from "sarvamai";

const client = new SarvamAI();

const response = await client.translate.translate({
  input: "Hello, how are you?",
  sourceLanguageCode: "en-IN",
  targetLanguageCode: "hi-IN",
  model: "mayura:v1"
});

console.log(response.translatedText);

cURL

cURL示例

bash

curl -X POST "https://api.sarvam.ai/translate" \
  -H "api-subscription-key: $SARVAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Hello, how are you?",
    "source_language_code": "en-IN",
    "target_language_code": "hi-IN",
    "model": "mayura:v1"
}'

bash

curl -X POST "https://api.sarvam.ai/translate" \
  -H "api-subscription-key: $SARVAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Hello, how are you?",
    "source_language_code": "en-IN",
    "target_language_code": "hi-IN",
    "model": "mayura:v1"
}'

Parameters

参数说明

Parameter	Type	Required	Description
`input`	string	Yes	Text to translate
`source_language_code`	string	Yes	Source language or `auto`
`target_language_code`	string	Yes	Target language code
`model`	string	Yes	`mayura:v1`
`mode`	string	No	`formal` or `casual`
`output_script`	string	No	`devanagari` , `latin` , etc.
`numeral_format`	string	No	`international` or `native`

参数	类型	是否必填	描述
`input`	string	是	需要翻译的文本
`source_language_code`	string	是	源语言代码或 `auto`
`target_language_code`	string	是	目标语言代码
`model`	string	是	`mayura:v1`
`mode`	string	否	`formal` （正式）或 `casual` （非正式）
`output_script`	string	否	`devanagari` （天城文）、 `latin` （拉丁字母）等
`numeral_format`	string	否	`international` （国际格式）或 `native` （本地格式）

Response

返回结果

json

{
    "request_id": "abc123",
    "translated_text": "नमस्ते, आप कैसे हैं?",
    "source_language_code": "en-IN",
    "target_language_code": "hi-IN"
}

See references/languages.md for language-specific notes.

json

{
    "request_id": "abc123",
    "translated_text": "नमस्ते, आप कैसे हैं?",
    "source_language_code": "en-IN",
    "target_language_code": "hi-IN"
}

有关语言的详细说明，请查看references/languages.md 。