Skip to main content

​
Overview

SarvamSTTService provides real-time speech recognition using Sarvam AI’s WebSocket API, supporting Indian language transcription with Voice Activity Detection (VAD) and multiple audio formats for high-accuracy speech recognition.

Sarvam STT API Reference

Pipecat’s API methods for Sarvam STT integration

Example Implementation

Complete example with interruption handling

Sarvam Documentation

Official Sarvam AI STT documentation and features

Sarvam AI Platform

Access API keys and speech models

​
Installation

To use Sarvam services, install the required dependency: 
pip install "pipecat-ai[sarvam]"

​
Prerequisites

​
Sarvam AI Account Setup

Before using Sarvam STT services, you need:
  1. Sarvam AI Account: Sign up at Sarvam AI
  2. API Key: Generate an API key from your account dashboard
  3. Model Access: Access to Saarika (STT) or Saaras (STT-Translate) models, including the saaras:v3 model with support for multiple modes (transcribe, translate, verbatim, translit, codemix)

​
Required Environment Variables

  • SARVAM_API_KEY: Your Sarvam AI API key for authentication

​
Configuration

​
SarvamSTTService

​
api_key
str
required
Sarvam API key for authentication.
​
model
str
default:"saarika:v2.5"
deprecated
Sarvam model to use. Allowed values: "saarika:v2.5" (standard STT), "saaras:v2.5" (STT-Translate, auto-detects language), "saaras:v3" (advanced, supports mode and prompts). Deprecated in v0.0.105. Use settings=SarvamSTTService.Settings(...) instead.
​
sample_rate
int
default:"None"
Audio sample rate in Hz. Defaults to 16000 if not specified.
​
mode
Literal['transcribe', 'translate', 'verbatim', 'translit', 'codemix']
default:"None"
Mode of operation. Only applicable to models that support it (e.g., saaras:v3). Defaults to the model’s default mode.
​
input_audio_codec
str
default:"wav"
Audio codec/format of the input file.
​
params
SarvamSTTService.InputParams
default:"None"
deprecated
Configuration parameters for Sarvam STT service. Deprecated in v0.0.105. Use settings=SarvamSTTService.Settings(...) instead.
​
settings
SarvamSTTService.Settings
default:"None"
Runtime-configurable settings for the STT service. See Settings below.
​
keepalive_timeout
float
default:"None"
Seconds of no audio before sending silence to keep the connection alive. None disables keepalive.
​
ttfs_p99_latency
float
default:"SARVAM_TTFS_P99"
P99 latency from speech end to final transcript in seconds. Override for your deployment. See stt-benchmark.
​
keepalive_interval
float
default:"5.0"
Seconds between idle checks when keepalive is enabled.

​
Settings

Runtime-configurable settings passed via the settings constructor argument using SarvamSTTService.Settings(...). These can be updated mid-conversation with STTUpdateSettingsFrame. See Service Settings for details.
ParameterTypeDefaultDescription
modelstrNoneSTT model identifier. (Inherited from base STT settings.)
languageLanguage | strNoneTarget language for transcription. (Inherited from base STT settings.) Behavior varies by model: saarika:v2.5 defaults to “unknown” (auto-detect), saaras:v2.5 ignores this (auto-detects), saaras:v3 defaults to “en-IN”.
promptstrNoneOptional prompt to guide transcription/translation style. Only applicable to saaras models (v2.5 and v3).
vad_signalsboolNoneEnable VAD signals in responses. When enabled, the service broadcasts UserStartedSpeakingFrame and UserStoppedSpeakingFrame from the server.
high_vad_sensitivityboolNoneEnable high VAD sensitivity for more responsive speech detection.

​
Usage

​
Basic Setup

from pipecat.services.sarvam.stt import SarvamSTTService

stt = SarvamSTTService(
    api_key=os.getenv("SARVAM_API_KEY"),
)

​
With Language and Model Configuration

from pipecat.services.sarvam.stt import SarvamSTTService
from pipecat.transcriptions.language import Language

stt = SarvamSTTService(
    api_key=os.getenv("SARVAM_API_KEY"),
    mode="transcribe",
    settings=SarvamSTTService.Settings(
        model="saaras:v3",
        language=Language.HI_IN,
        prompt="Transcribe Hindi conversation about technology.",
    ),
)

​
With Server-Side VAD

from pipecat.services.sarvam.stt import SarvamSTTService

stt = SarvamSTTService(
    api_key=os.getenv("SARVAM_API_KEY"),
    settings=SarvamSTTService.Settings(
        vad_signals=True,
        high_vad_sensitivity=True,
    ),
)

​
Notes

  • Supported languages: Bengali (bn-IN), Gujarati (gu-IN), Hindi (hi-IN), Kannada (kn-IN), Malayalam (ml-IN), Marathi (mr-IN), Tamil (ta-IN), Telugu (te-IN), Punjabi (pa-IN), Odia (od-IN), English (en-IN), and Assamese (as-IN).
  • Model-specific parameter validation: The service validates that parameters are compatible with the selected model. For example, prompt is not supported with saarika:v2.5, and language is not supported with saaras:v2.5 (which auto-detects language).
  • VAD modes: When vad_signals=False (default), the service relies on Pipecat’s local VAD and flushes the server buffer on VADUserStoppedSpeakingFrame. When vad_signals=True, the service uses Sarvam’s server-side VAD and broadcasts speaking frames from the server.
The InputParams / params= pattern is deprecated as of v0.0.105. Use Settings / settings= instead. See the Service Settings guide for migration details.

​
Event Handlers

In addition to the standard service connection events (on_connected, on_disconnected, on_connection_error), Sarvam STT provides:
EventDescription
on_speech_startedSpeech detected in the audio stream
on_speech_stoppedSpeech stopped
on_utterance_endEnd of utterance detected
@stt.event_handler("on_speech_started")
async def on_speech_started(service):
    print("User started speaking")

@stt.event_handler("on_utterance_end")
async def on_utterance_end(service):
    print("Utterance ended")