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
  • Model Selection Guide
  • Language Support Overview
  • Saaras v3 & Sarvam Translate: Complete 23 Language Support (22 Indian + English)
  • Model Language Support Summary
  • Use Cases
  • Build a multilingual voice assistant
  • Localize content across Indian languages
  • Analyze multilingual customer interactions
  • Create inclusive learning experiences
  • Extract and digitize document content
  • Saarika v2.5 Language Support (11 languages)
Getting Started

Models

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

Saaras

Next
Built with

Sarvam AI provides a purpose-built AI stack for building applications in Indian languages. Our models span speech-to-text, speech translation, text translation, and high-quality text-to-speech—designed specifically for India’s linguistic diversity, accents, and real-world usage patterns.

Each model is trained and evaluated on Indian languages and culturally grounded data, enabling higher accuracy in production scenarios. With simple, well-documented APIs and predictable performance, developers can build, deploy, and scale India-first AI experiences without managing model complexity.

New to building for Indian languages? Start with Building for Indian Languages — a practical guide to language coverage, code-mixing, scripts, native numerals, 8kHz telephony audio, and pronunciation control.

Model Selection Guide

Available models: Saaras v3 — Speech to Text, Bulbul v3 — Text to Speech, Mayura — Text Translation, Sarvam-Translate — Extended Translation, Sarvam-30B — Chat LLM, Sarvam-105B — Flagship Chat LLM, Sarvam Vision — Document Intelligence.

Saaras v3: Speech to Text

State-of-the-art ASR with 23 language support (22 Indian + English) and multiple output modes: transcribe, translate, verbatim, translit, codemix.

Bulbul v3: Text to Speech

Natural-sounding voices for 11 languages (10 Indian + English) with customizable pitch, pace, and speaker options.

Mayura: Text Translation

High-quality translation between 11 languages (10 Indian + English) with context preservation.

Sarvam-Translate: Text Translation

Extended translation support for all 23 languages (22 Indian + English) with superior accuracy.

Sarvam-30B: Chat LLM

30B parameter multilingual chat model delivering strong reasoning and conversational capabilities at a balanced performance-to-cost ratio.

Sarvam-105B: Flagship Chat LLM

105B parameter flagship model — our most capable chat model for the highest quality Indian language understanding, reasoning, and generation.

Sarvam Vision: Document Intelligence

Extract and digitize content from documents in 23 languages with accurate OCR and structured output.

Language Support Overview

Saaras v3 & Sarvam Translate: Complete 23 Language Support (22 Indian + English)

LanguageCodeLanguageCode
Hindihi-INAssameseas-IN
Bengalibn-INUrduur-IN
Kannadakn-INNepaline-IN
Malayalamml-INKonkanikok-IN
Marathimr-INKashmiriks-IN
Odiaod-INSindhisd-IN
Punjabipa-INSanskritsa-IN
Tamilta-INSantalisat-IN
Telugute-INManipurimni-IN
Englishen-INBodobrx-IN
Gujaratigu-INMaithilimai-IN
Dogridoi-IN

Model Language Support Summary

ModelLanguagesStatus
Saaras v3 Speech-to-Text Model23 languages (22 Indian + English)✅ Recommended
Bulbul v3 Text-to-Speech Model11 languages (10 Indian + English)✅ Active
Mayura Translation Model11 languages (10 Indian + English)✅ Active
Sarvam Translate Model23 languages (22 Indian + English)✅ Active
Sarvam-30B Chat Completion Model23 languages (22 Indian + English)✅ Active
Sarvam-105B Chat Completion Model23 languages (22 Indian + English)✅ Active
Sarvam Vision Model23 languages support (22 Indian + English)✅ Active

Use Cases

Voice Assistant
Content Localization
Call Center Analytics
Educational Platform
Document Processing

Build a multilingual voice assistant

  1. Speech Input: Use Saaras v3 with mode="transcribe" to convert user speech to text
  2. Understanding: Process with Sarvam-30B or Sarvam-105B for intelligent responses
  3. Speech Output: Convert responses to speech with Bulbul

Perfect for customer service, smart home devices, and accessibility applications.

Learn how to build a voice agent with LiveKit →

Legacy Models

The following models are still available but are being phased out. We recommend migrating to the newer models listed above.

Sarvam-M: Chat & Reasoning (Deprecated)

24B parameter multilingual chat model with hybrid reasoning. Deprecated and no longer available through the API — migrate to Sarvam-30B or Sarvam-105B.

Saarika v2.5: Speech to Text

Legacy ASR model supporting 11 Indian languages. Migrate to Saaras v3 for improved accuracy and 23 language support.

Saarika v2.5 Language Support (11 languages)

LanguageCodeLanguageCode
Hindihi-INKannadakn-IN
Bengalibn-INMalayalamml-IN
Tamilta-INMarathimr-IN
Telugute-INPunjabipa-IN
Gujaratigu-INOdiaod-IN
Englishen-IN