For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
CommunityAPI StatusAPI PricingSign Up
DocumentationAPI ReferencesCookbookIntegrationDeveloper Tools
DocumentationAPI ReferencesCookbookIntegrationDeveloper Tools
  • Getting Started
    • Welcome
    • Quickstart
    • SDKs & Libraries
    • Building for Indian Languages
    • Models
      • Saaras
      • Bulbul
      • Mayura
      • Sarvam Translate
      • Sarvam 30B
      • Sarvam 105B
      • Sarvam Vision
      • Saarika (Legacy)
    • Credits & Rate Limits
    • Errors & Troubleshooting
    • Talk to us
    • Pricing
    • Changelog
  • API Guides & Tutorials
LogoLogo
CommunityAPI StatusAPI PricingSign Up
On this page
  • Key Features
  • Language Support
  • Corpus BLEU (Bilingual Evaluation Understudy) Benchmark
  • Key Capabilities
  • Next Steps
Getting StartedModels

Sarvam Translate

||View as Markdown|
Was this page helpful?
Previous

Sarvam-30B

Next
Built with

Sarvam Translate enables high-quality translation between English and 22 Indian languages. It provides comprehensive coverage of all scheduled Indian languages with formal translation style, making it ideal for official and professional communication needs.

Key Features

Wide Language Support

Support for all 22 scheduled Indian languages and English for comprehensive translation coverage.

Formal Style Translation

Default translation mode is formal to ensure clarity and consistency in professional communications.

Numeral Format Control

Option to choose between international and native numeral systems for culturally appropriate translations.

Comprehensive Coverage

Complete support for all official Indian languages as per the Constitution of India.

High Quality Translation

Formal translation style optimized for professional and official communication needs.

Language Support

Sarvam Translate supports all 22 scheduled Indian languages as per the Constitution of India:

LanguageCode
Assameseas-IN
Bengalibn-IN
Bodobrx-IN
Dogridoi-IN
Englishen-IN
Gujaratigu-IN
Hindihi-IN
Kannadakn-IN
Kashmiriks-IN
Konkanikok-IN
Maithilimai-IN
Malayalamml-IN
Manipurimni-IN
Marathimr-IN
Nepaline-IN
Odiaod-IN
Punjabipa-IN
Sanskritsa-IN
Santalisat-IN
Sindhisd-IN
Tamilta-IN
Telugute-IN
Urduur-IN

Supports bidirectional translation for all listed languages.

All languages support bidirectional translation. Specify the exact source language code for optimal translation quality.

Corpus BLEU (Bilingual Evaluation Understudy) Benchmark

Corpus BLEU score is a metric that evaluates the overall quality of machine translation by comparing it to reference translations across an entire dataset. Higher scores (closer to 100) indicate better performance.

051015202530354045Corpus BLEU Score29.22Assamese8.10Bengali25.20Bodo18.03Dogri28.41Gujarati32.15Hindi23.08Kannada3.56Kashmiri22.30Konkani26.78Maithili14.17Malayalam7.42Manipuri29.13Marathi21.52Nepali23.71Odia19.79Punjabi25.56Sanskrit12.82Santali7.04Sindhi8.03Tamil29.25Telugu40.65UrduLanguages

Key Capabilities

Basic Usage
Advanced Options

Simple translation between any of the 22 supported Indian languages and English.

1from sarvamai import SarvamAI
2
3client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
4
5response = client.text.translate(
6 input="भारत एक महान देश है। इसकी संस्कृति बहुत पुरानी और समृद्ध है।",
7 source_language_code="hi-IN",
8 target_language_code="gu-IN",
9 model="sarvam-translate:v1"
10)
11
12print(response)

The output_script option is not supported in Sarvam Translate. For script control, use the Mayura model.

Next Steps

Developer quickstart

Learn how to integrate translation into your application.

API Reference

Complete API documentation for translation endpoints.

Cookbook

Step-by-step tutorial for translation implementation.