Sarvam

Speech-to-text service implementation using Sarvam AI’s WebSocket-based streaming API

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.

Parameter	Type	Default	Description
model	str	None	STT model identifier. (Inherited from base STT settings.)
language	Language | str	None	Target 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”.
prompt	str	None	Optional prompt to guide transcription/translation style. Only applicable to saaras models (v2.5 and v3).
vad_signals	bool	None	Enable VAD signals in responses. When enabled, the service broadcasts UserStartedSpeakingFrame and UserStoppedSpeakingFrame from the server.
high_vad_sensitivity	bool	None	Enable 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:

Event	Description
on_speech_started	Speech detected in the audio stream
on_speech_stopped	Speech stopped
on_utterance_end	End 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")