> For clean Markdown of any page, append `.md` to the page URL.
> For a complete documentation index, see https://docs.sarvam.ai/llms.txt.
> For full documentation content in one file, see https://docs.sarvam.ai/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server.

# Models

> Complete overview of Sarvam AI's specialized models for Indian languages. Choose the right model for your use case - from speech processing to text generation, translation, and document intelligence.

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](/api-reference-docs/building-for-india) — 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](/api-reference-docs/getting-started/models/saaras), [Bulbul v3 — Text to Speech](/api-reference-docs/getting-started/models/bulbul), [Mayura — Text Translation](/api-reference-docs/getting-started/models/mayura), [Sarvam-Translate — Extended Translation](/api-reference-docs/getting-started/models/sarvam-translate), [Sarvam-30B — Chat LLM](/api-reference-docs/getting-started/models/sarvam-30b), [Sarvam-105B — Flagship Chat LLM](/api-reference-docs/getting-started/models/sarvam-105b), [Sarvam Vision — Document Intelligence](/api-reference-docs/getting-started/models/sarvam-vision).

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

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

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

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

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

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

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)

| Language  | Code    |   | Language | Code     |
| --------- | ------- | - | -------- | -------- |
| Hindi     | `hi-IN` |   | Assamese | `as-IN`  |
| Bengali   | `bn-IN` |   | Urdu     | `ur-IN`  |
| Kannada   | `kn-IN` |   | Nepali   | `ne-IN`  |
| Malayalam | `ml-IN` |   | Konkani  | `kok-IN` |
| Marathi   | `mr-IN` |   | Kashmiri | `ks-IN`  |
| Odia      | `od-IN` |   | Sindhi   | `sd-IN`  |
| Punjabi   | `pa-IN` |   | Sanskrit | `sa-IN`  |
| Tamil     | `ta-IN` |   | Santali  | `sat-IN` |
| Telugu    | `te-IN` |   | Manipuri | `mni-IN` |
| English   | `en-IN` |   | Bodo     | `brx-IN` |
| Gujarati  | `gu-IN` |   | Maithili | `mai-IN` |
|           |         |   | Dogri    | `doi-IN` |

***

## Model Language Support Summary

| Model                                 | Languages                                  | Status        |
| ------------------------------------- | ------------------------------------------ | ------------- |
| **Saaras v3 Speech-to-Text Model**    | 23 languages (22 Indian + English)         | ✅ Recommended |
| **Bulbul v3 Text-to-Speech Model**    | 11 languages (10 Indian + English)         | ✅ Active      |
| **Mayura Translation Model**          | 11 languages (10 Indian + English)         | ✅ Active      |
| **Sarvam Translate Model**            | 23 languages (22 Indian + English)         | ✅ Active      |
| **Sarvam-30B Chat Completion Model**  | 23 languages (22 Indian + English)         | ✅ Active      |
| **Sarvam-105B Chat Completion Model** | 23 languages (22 Indian + English)         | ✅ Active      |
| **Sarvam Vision Model**               | 23 languages support (22 Indian + English) | ✅ Active      |

***

## Use Cases

### 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 →](/api-reference-docs/integration/integration-guides/build-voice-agent-with-live-kit)

### Localize content across Indian languages

Build end-to-end multilingual experiences from audio to translated speech:

1. **Transcribe speech**: Use Saaras v3 with `mode="transcribe"` to accurately convert audio in Indian languages into text.
2. **Translate at scale**: Convert transcripts across 23 languages (22 Indian + English) with Sarvam Translate.
3. **Generate localized audio**: Turn translated text into natural, production-ready speech with Bulbul's high-quality voices.

This gives you a complete pipeline — speech → text → translation → localized audio — enabling developers to deliver fully localized content for apps, videos, learning platforms, and product experiences with minimal engineering effort.

### Analyze multilingual customer interactions

1. **Speech Recognition**: Convert calls to text with Saaras v3 (`mode="transcribe"`)
2. **Translation**: Use Saaras v3 with `mode="translate"` for English output
3. **Insights**: Extract patterns and sentiment from conversations

Essential for customer experience optimization and compliance monitoring.

[Learn how to analyze calls with our analytics cookbook →](/api-reference-docs/cookbook/guides/call-analytics-pipeline)

### Create inclusive learning experiences

1. **Content Translation**: Make materials accessible in 23 languages (22 Indian + English)
2. **Audio Learning**: Generate pronunciation guides with Bulbul
3. **Interactive Chat**: Enable Q\&A with Sarvam-30B or Sarvam-105B in native languages

Perfect for online education, language learning, and skill development platforms.

### Extract and digitize document content

1. **Document Upload**: Submit PDFs or images of documents in Indian languages
2. **Text Extraction**: Use Sarvam Vision for accurate OCR across 23 languages
3. **Structured Output**: Get clean HTML, Markdown, or JSON output with tables preserved

Ideal for digitizing government forms, invoices, legal documents, and historical records in Indian languages.

[Learn more about Document Digitization →](/api-reference-docs/api-guides-tutorials/document-digitization/overview)

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

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

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)

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