Sarvam AI Developer Platform

AI for all from India.

Speech, text, and document models trained for 22 Indian languages and English, plus no-code platforms for voice agents, work agents, coding agents, and content production. Create a key and make your first call in a minute.

Get startedBrowse the API reference

Native support forहिन्दीবাংলাதமிழ்తెలుగుमराठीગુજરાતીಕನ್ನಡമലയാളംਪੰਜਾਬੀଓଡ଼ିଆঅসমীয়াاردوनेपालीकोंकणीکٲشُرسنڌيसंस्कृतम्संतालीমৈতৈলোন্बर’मैथिलीडोगरीEnglish

Call the models

REST, WebSocket, and batch endpoints for transcription, speech synthesis, translation, chat, and document extraction. Official Python and JavaScript SDKs.

QuickstartSDKs

Build agents

Design, deploy, and monitor conversational agents across phone and chat in 10 Indian languages, hand recurring work to agents wired into Gmail, Slack, and Notion, or deploy coding agents for development tasks.

Voice AgentsWork AgentsCoding Agents

Work without code

Dub video, clone voices, generate speech, and turn scans and handwritten forms into structured data, all from the dashboard with no integration required.

Content AgentsDoc Agents

Explore the platform

Six products, one account. Start wherever your problem lives.

Model APIs

Speech, text, chat, and document models behind a single API key. Build it into your own product.

Voice Agents

Build, deploy, and monitor voice and chat agents. Bring your own telephony or rent a number from Sarvam.

Doc Agents

Extract fields and digitise documents (invoices, KYC, land deeds, handwritten manuscripts) into JSON, CSV, Markdown, or DOCX.

Content Agents

Sarvam Studio: dub video, clone voices, generate speech, and transcribe audio from the browser.

Work Agents

An agentic workspace for real work: email triage, morning briefings, internal helpdesk, lead follow-up.

Coding Agent

An agentic coding assistant for your terminal and IDE, built on Sarvam models for development tasks.

Build with the APIs

Guides and tutorials for each capability, from a first request to production patterns.

All API guides →

Speech-to-Text Saaras v3

Transcribe, translate, and caption audio in real time or in batch, across code-mixed and regional speech.

Text-to-Speech Bulbul v3

Generate natural, expressive speech in Indian languages with control over pitch, pace, and speaker.

Chat Completion Sarvam-105B

Build conversational AI on a flagship model tuned for Indic reasoning, with a 128K context window.

Text Processing Mayura

Translate, transliterate, and detect languages across 22 Indian languages and English.

Document AI Sarvam Vision

Turn PDFs, scans, and handwriting into structured, searchable data: whole documents or just the fields you define.

Dubbing Beta

Localize video and audio into Indian languages with speaker voice cloning, tone control, and multi-format exports.

Models

Every model is trained and evaluated on Indian languages, accents, and code-mixed usage, not adapted from an English-first baseline.

Compare models →
Saaras v3Speech-to-text

23 languages (22 Indian + English), with transcribe, translate, verbatim, translit, and codemix output modes.

Bulbul v3Text-to-speech

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

Sarvam-105BChat

Flagship 105B-parameter chat model: the highest quality Indian language understanding, reasoning, and generation.

MayuraTranslation

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

Sarvam VisionDocument intelligence

Document model with accurate OCR and structured output across 23 languages.

Integrations

Drop Sarvam into the frameworks and telephony you already run.

All integrations →
LiveKit

Real-time voice agents with Saaras and Bulbul in the pipeline.

Pipecat

Build a real-time voice agent wired end to end to Sarvam models.

Vapi

Run a Vapi agent on Saaras v3, Sarvam-105B, and Bulbul v3.

Twilio

Phone voice agents and WhatsApp bots over Twilio.

Exotel

Phone voice agents on Exotel telephony, via Pipecat.

LangChain

The official langchain-sarvam package: streaming, tools, structured output.

Vercel AI SDK

Chat, speech, and translation through the sarvam-ai-sdk provider.

n8n

Automate Indian-language speech and chat with the community node.

Cookbook

End-to-end projects you can run today, with the full source in each guide.

All recipes →
Call analytics pipeline

Transcribe support calls, then summarise, tag, and score them into a reporting pipeline.

WhatsApp bot

Wire Sarvam speech and chat into a WhatsApp bot that answers in the user’s own language.

Live video transcription

Real-time transcription and translation with the streaming STT API, Flask-SocketIO, and the Web Audio API.

Podcast generator

Turn a script into a multi-speaker podcast episode with distinct Bulbul voices.

What’s new

Full changelog →
June 2026Saaras v3 is the new Speech-to-Text default

/speech-to-text now defaults to saaras:v3 and honours the mode parameter. Use mode=“translate” instead of the legacy translate endpoint.

Read the changelog →
June 2026Sarvam-105B is the supported chat model

sarvam-m has been deprecated and is no longer accepted by the Chat Completions API. Migrate to sarvam-105b and its full 128K context window.

May 2026Document digitization repriced to ₹0.5 per page

Down from ₹1.5 per page, making bulk document processing significantly cheaper.

Resources

Built with