Sarvam AI

OverviewCopy Anchor Link

• SarvamSTTService: streams audio to Sarvam's speech-to-text WebSocket (saaras:v4 by default, or saaras:v3; see MODEL_CONFIGS). Sarvam's VAD signals can drive the turn.
• SarvamRealtimeSTTService: Sarvam's realtime endpoint (saaras:v3-realtime or saaras:v4), with the server or the pipeline marking turn boundaries, and reconnects.

InstallationCopy Anchor Link

bun add @pipedog/sarvam

import { SarvamRealtimeSTTService, SarvamSTTService } from "@pipedog/sarvam/stt";

PrerequisitesCopy Anchor Link

• A Sarvam account and an API key from the Sarvam dashboard.
• Pass the key as apiKey. The examples read it from SARVAM_API_KEY.

SarvamSTTServiceCopy Anchor Link

Connects to wss://api.sarvam.ai/speech-to-text/ws, with the key in the Api-Subscription-Key header.

ConfigurationCopy Anchor Link

SettingsCopy Anchor Link

Runtime-updatable settings, passed as settings: new SarvamSTTService.Settings({...}) (SarvamSTTSettings). They are the base STT settings (model, language) plus the VAD tuning fields below, all null (the server's default) unless you set them.

UsageCopy Anchor Link

import { Language } from "@pipedog/core/transcriptions/language";
import { SarvamSTTService } from "@pipedog/sarvam/stt";

const stt = new SarvamSTTService({
  apiKey: process.env.SARVAM_API_KEY ?? "",
  settings: new SarvamSTTService.Settings({ language: Language.HI_IN }),
});

Event handlersCopy Anchor Link

NotesCopy Anchor Link

• mode is one of transcribe, translate, verbatim, translit and codemix, for the models that support it; it defaults to the model's own default.
• keyterms (at most 50 terms of 64 characters each) are connection-time recognition hints for saaras:v4.
• Only 8000 and 16000 Hz audio is accepted.
• Settings that go in the connection query string reconnect the socket when they change.

SarvamRealtimeSTTServiceCopy Anchor Link

Connects to Sarvam's realtime speech-to-text WebSocket and maps its VAD and transcript events to frames. A dropped socket is reopened with backoff unless reconnectOnError is false.

ConfigurationCopy Anchor Link

SettingsCopy Anchor Link

Passed as settings: new SarvamRealtimeSTTService.Settings({...}) (SarvamRealtimeSTTSettings).

UsageCopy Anchor Link

import { SarvamRealtimeSTTService } from "@pipedog/sarvam/stt";

const realtime = new SarvamRealtimeSTTService({
  apiKey: process.env.SARVAM_API_KEY ?? "",
  endpointing: "vad",
  settings: new SarvamRealtimeSTTService.Settings({ language: Language.HI_IN }),
});

Change settings mid-call with an STTUpdateSettingsFrame:

import { STTUpdateSettingsFrame } from "@pipedog/core/frames/frames";

// Queue it on the worker, or push it from a processor upstream of the service.
const update = new STTUpdateSettingsFrame({
  delta: new SarvamRealtimeSTTService.Settings({ streamType: "fast" }),
});

NotesCopy Anchor Link

• endpointing: "vad" (the default) lets the server mark turn boundaries. With "manual" the pipeline does, so it needs a turn strategy that emits VADUserStartedSpeakingFrame and VADUserStoppedSpeakingFrame; without one Sarvam never emits a final transcript. It's an option, not a setting, because it decides which turn strategies the user aggregator runs.
• A VAD analyzer is needed in both modes: it times the transcription latency.
• sampleRate is 8000 or 16000; null adopts the pipeline's input rate.

Generated from pipecat.runtimes and pipecat.compat in packages/sarvam/package.json: ✅ means the compat smoke test passes on that runtime.

Runtime notesCopy Anchor Link

• Upstream uses the sarvamai Python SDK for SarvamSTTService. Here it is a plain WebSocket through the core websocketConnect (which sends the auth headers on Workers too), so no SDK is needed.
• The deprecated model and params constructor options and Settings.language_code are not ported.
• Tested against local WebSocket servers, as upstream's tests do, not against Sarvam itself.