Sarvam STT

Sarvam AI provides streaming speech-to-text built for Indian languages. The plugin uses WebSocket streaming with built-in voice activity detection for turn events.

Vision Agents requires a Stream account for real-time transport. Get your Sarvam API key from the Sarvam dashboard.

Sarvam also provides text-to-speech and an LLM. You can use all three in the same agent.

Installation

uv add "vision-agents[sarvam]"

Quick start

from vision_agents.core import Agent, User
from vision_agents.plugins import sarvam, getstream, smart_turn

agent = Agent(
    edge=getstream.Edge(),
    agent_user=User(name="Sarvam Agent", id="agent"),
    instructions="Reply in the same language the user speaks.",
    llm=sarvam.LLM(model="sarvam-m"),
    stt=sarvam.STT(language="hi-IN"),
    tts=sarvam.TTS(speaker="shubh"),
    turn_detection=smart_turn.TurnDetection(),
)

Set SARVAM_API_KEY in your environment or pass api_key directly.

Parameters

stt = sarvam.STT(
    model="saaras:v3",
    language="hi-IN",
    mode="transcribe",
    sample_rate=16000,
    high_vad_sensitivity=False,
)

Name	Type	Default	Description
model	str	"saaras:v3"	Streaming model (saaras:v3, saarika:v2.5, saaras:v2.5)
language	str	None	Language code (e.g. hi-IN, en-IN). None for auto-detect
mode	str	None	transcribe, translate, verbatim, translit, or codemix
sample_rate	int	16000	Input sample rate — 8000 or 16000 Hz
high_vad_sensitivity	bool	False	Increase VAD sensitivity for noisy input
vad_signals	bool	True	Emit speech start/end events for turn detection
prompt	str	None	Optional biasing prompt sent after connect
api_key	str	None	API key (defaults to SARVAM_API_KEY env var)

Next steps

Sarvam TTS

Streaming text-to-speech for Indian languages

Sarvam LLM

Chat completions with Sarvam models