Overview
This plugin allows you to use Sarvam as an STT provider for your voice agents.
Installation
Install the plugin from PyPI:
uv add "livekit-agents[sarvam]~=1.4"
Authentication
The Sarvam plugin requires a Sarvam API key.
Set SARVAM_API_KEY in your .env file.
Usage
Use Sarvam STT in an AgentSession or as a standalone transcription service. For example, you can use this STT in the Voice AI quickstart.
from livekit.plugins import sarvamsession = AgentSession(stt=sarvam.STT(language="en-IN",model="saaras:v3",mode="transcribe", # default),# ... llm, tts, etc.)
Parameters
This section describes some of the available parameters. See the plugin reference for a complete list of all available parameters.
stringOptionalBCP-47 language code. Language support varies by model:
saaras:v3supports the full set of plugin-supported languages.saarika:v2.5andsaaras:v2.5support a smaller subset.
See documentation for a complete list of supported languages.
stringOptionalDefault: saarika:v2.5The Sarvam STT model to use. Valid values are:
saarika:v2.5saaras:v2.5saaras:v3
saaras:v3 is the recommended model for advanced mode control and broader language support.
stringOptionalDefault: transcribeTranscription mode for saaras:v3. Valid values are:
transcribetranslateverbatimtranslitcodemix
Only default transcription behavior is supported for saarika:v2.5 and saaras:v2.5 models.
stringOptionalOptional prompt for translation workflows on saaras models.
Additional resources
The following resources provide more information about using Sarvam with LiveKit Agents.
Python package
The livekit-plugins-sarvam package on PyPI.
Plugin reference
Reference for the Sarvam STT plugin.
GitHub repo
View the source or contribute to the LiveKit Sarvam STT plugin.
Sarvam docs
Sarvam's full docs site.
Voice AI quickstart
Get started with LiveKit Agents and Sarvam.
Sarvam TTS
Guide to the Sarvam TTS plugin with LiveKit Agents.