Sarvam + LiveKit

Voice Infra

Real-time voice infrastructure for building production-grade voice AI agents. Telephony, SIP, and global scaling handled automatically.

Sarvam APIs Supported

saarika:v2.5

Speech-to-Text

Accurate transcription built for Indian accents, dialects, and real-world audio with speaker diarisation.

bulbul:v3

Text-to-Speech

Natural, expressive voices across 11+ Indian languages for conversational AI, dubbing, and accessibility.

sarvam-m

LLM

Multilingual large language model with native proficiency across Indian languages for text generation and reasoning.

How it works

Install LiveKit Agents SDK

pip install livekit-agents livekit-plugins-sarvam

Add Sarvam as provider

Set SARVAM_API_KEY and configure STT/TTS plugins

Deploy your agent

Run locally or deploy to LiveKit Cloud

Quick start

python

# Install
pip install livekit-agents livekit-plugins-sarvam

# In your agent
from livekit.plugins import sarvam

stt = sarvam.STT()
tts = sarvam.TTS()

agent = VoicePipelineAgent(
    vad=silero.VAD.load(),
    stt=stt,
    llm=openai.LLM(),
    tts=tts,
)

Use cases

IVR

IVR & Call Centres

Automate inbound and outbound calls with Indic-language voice agents.

Voice

Voice Assistants

Build voice-first assistants that understand and speak Indian languages.

Telephony

Telephony Bots

Deploy SIP-connected bots for telecoms with real-time transcription and synthesis.

Resources & details

Type Open Source + Cloud

Language Python

Maintained by LiveKit Inc.

Install pip install livekit-plugins-sarvam

LiveKit docs → Sarvam plugin ref → GitHub → Sarvam API ref →

Ready to build? Start building with LiveKit in minutes.

Ready to build?

Start building with LiveKit in minutes.

Get API Key