Skip to navigation
Resources

Models

View as Markdown

Model APIs come in two families that share one API key, one SDK, and one credit balance:

  • Sarvam Models: Sarvam’s own models for Indian languages, covering speech to text, text to speech, translation, and document intelligence. Each is trained and evaluated on Indian languages, accents, and code-mixed input.
  • Token Factory (Open-Weight): open-weight LLMs (Sarvam 105B, GLM, Gemma, DeepSeek, and Kimi) on an OpenAI-compatible /v2 API, plus Sarvam Prism, a System-1 decision model built on Sarvam 105B.

This page lists every model in both families, with language support and how to choose.

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

Sarvam Models: trained for Indian languages:

ModelAPIDescription
Saaras v4Speech to TextLatest, default ASR model — 23 language support (22 Indian + Global/Indian English) and multiple output modes: transcribe, translate, verbatim, translit, codemix.
Saaras v3Speech to TextPrevious ASR model, still available — 23 languages (22 Indian + Indian English) with the same output modes as v4, without Global English.
Bulbul v4 FlashText to SpeechLatest text-to-speech model — 200+ persona voices with natural prosody, and the same request/response contract as v3.
Bulbul v3Text to SpeechStable text-to-speech model with 30+ named speakers across 11 languages (10 Indian + English). The API default when model is omitted.
Sarvam Instant Voice CloningInstant Voice Cloning (Beta)Create a voice from a short reference clip and synthesize speech with it across 12 Indian languages - clone inline per request, or save the voice once and reuse its ID.
MayuraText TranslationHigh-quality translation between 11 languages (10 Indian + English) with context preservation.
Sarvam-TranslateText TranslationExtended translation support for all 23 languages (22 Indian + English) with superior accuracy.
Sarvam VisionDocument IntelligenceExtract and digitize content from documents in 23 languages with accurate OCR and structured output.

Token Factory (Open-Weight)

Token Factory models are available on /v2 using the same Sarvam API key and credits.

DeepSeek V4 Pro, Kimi K3.1 Pro, Qwen 3.8 27B, Clef, and EmbeddingGemma 2 are on Provisioned Throughput and are enabled per organisation. See Provisioned Throughput.

ModelContext windowModalityReasoning
Sarvam 105B128K tokensText → textYes, low by default
Sarvam 105B Conversations32K tokensText → textNo
Sarvam Prism32,768 tokens per questionText → probabilities (Decisions API)No
GLM-5.31,048,576 tokensText → textYes
GLM-5.3 Flash1,048,576 tokensText + image → textYes
Gemma 4 31B262,144 tokensText + image → textYes, off by default
DeepSeek V4.1 Flash 10171,048,576 tokensText + image → textYes
DeepSeek V4 Pro1,000,000 tokensText → textYes
Kimi K3.1 Pro1,048,576 tokensText + image + video → textYes
Qwen 3.8 27B262,144 tokensText + image → textYes
Clef65,536 tokens per requestText + image → probabilities (Decisions API)No
EmbeddingGemma 28,192 tokens per inputText → 768-dimension embeddingNo

Compare the Token Factory models →

Already using these models through another provider? See the migration guides for OpenRouter, Fireworks AI, or Together AI.

Language Support Overview

Language coverage varies by model. Check the table below before picking one. Full per-model tables are linked from each model’s own page.

ModelLanguagesStatus
Saaras v4 (Speech to Text)23 (22 Indian + Global/Indian English), full listRecommended
Saaras v3 (Speech to Text)23 (22 Indian + Indian English), full listActive
Sarvam Translate (Text Translation)23 (22 Indian + English), full listActive
Sarvam Vision (Document Intelligence)23 (22 Indian + English), full listActive
Bulbul v4 Flash (Text to Speech)10 (Hindi, English, English–Hindi, Bengali, Gujarati, Kannada, Marathi, Punjabi, Tamil, Telugu), full listLatest
Bulbul v3 (Text to Speech)11 (10 Indian + English), full listActive (API default)
Sarvam Instant Voice Cloning12 Indian languages, full listActive (Beta)
Mayura (Text Translation)11 (10 Indian + English), full listActive
Sarvam-105B (Chat LLM)11 (10 Indian + English), sarvam-105bServerless
Sarvam-105B Conversations (Chat LLM)11 (10 Indian + English), sarvam-105b-conversationsServerless
GLM-5.3 (Chat LLM, open-weight)See the model page for language coverageServerless
GLM-5.3 Flash (Chat LLM, open-weight)See the model page for language coverageServerless
Gemma 4 31B (Chat LLM, open-weight)See the model page for language coverageServerless
DeepSeek V4.1 Flash 1017 (Chat LLM, open-weight)See the model page for language coverageServerless
DeepSeek V4 Pro (Chat LLM, open-weight)See the model page for language coverageProvisioned Throughput
Kimi K3.1 Pro (Chat LLM, open-weight)See the model page for language coverageProvisioned Throughput
Qwen 3.8 27B (Chat LLM, open-weight)Not published; test with your languagesProvisioned Throughput
Clef (Decision model, open-weight)Not published; test with your languagesProvisioned Throughput
EmbeddingGemma 2 (Text embeddings, open-weight)Not published; test with your languagesProvisioned Throughput

23-language set (Saaras v4, Sarvam Translate, Sarvam Vision)

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

11-language set (Bulbul v3, Mayura, Sarvam-105B)

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

Use Cases

Build a multilingual voice assistant

  1. Speech Input: Use Saaras v4 with mode="transcribe" to convert user speech to text
  2. Understanding: Process with 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 →