Sarvam AI

OverviewCopy Anchor Link

• SarvamTTSService: streams text over Sarvam's WebSocket and pushes audio as it arrives. Interruptions reconnect the socket.
• SarvamHttpTTSService: one HTTP request per sentence.

InstallationCopy Anchor Link

bun add @pipedog/sarvam

import { SarvamHttpTTSService, SarvamTTSService } from "@pipedog/sarvam/tts";

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.

ModelsCopy Anchor Link

TTS_MODEL_CONFIGS holds each model's speakers and limits, and getSpeakersForModel(model) lists its speakers. Preprocessing is always on for these models. Settings a model doesn't support are dropped or clamped when the service is constructed.

SarvamTTSServiceCopy Anchor Link

ConfigurationCopy Anchor Link

SettingsCopy Anchor Link

Runtime-updatable settings, passed as settings: new SarvamTTSService.Settings({...}) (SarvamTTSSettings). Any setting you leave out keeps the default below.

UsageCopy Anchor Link

import { TTSUpdateSettingsFrame } from "@pipedog/core/frames/frames";
import { Language } from "@pipedog/core/transcriptions/language";
import { SarvamHttpTTSService, SarvamTTSService } from "@pipedog/sarvam/tts";

const tts = new SarvamTTSService({
  apiKey: process.env.SARVAM_API_KEY ?? "",
  settings: new SarvamTTSService.Settings({
    model: "bulbul:v3",
    voice: "shubh",
    language: Language.HI_IN,
  }),
});

Change settings mid-call with a TTSUpdateSettingsFrame:

// Queue it on the worker, or push it from a processor upstream of the service.
const update = new TTSUpdateSettingsFrame({
  delta: new SarvamTTSService.Settings({ pace: 1.2 }),
});

NotesCopy Anchor Link

• The socket carries config, text, flush and ping messages. The API key and a User-Agent go in the handshake headers.
• sampleRate can be 8000, 16000, 22050 or 24000; null uses the model's default.

SarvamHttpTTSServiceCopy Anchor Link

ConfigurationCopy Anchor Link

SettingsCopy Anchor Link

settings: new SarvamHttpTTSService.Settings({...}) (SarvamHttpTTSSettings) takes the same fields as above except minBufferSize and maxChunkLength, with the same defaults.

UsageCopy Anchor Link

const http = new SarvamHttpTTSService({
  apiKey: process.env.SARVAM_API_KEY ?? "",
  settings: new SarvamHttpTTSService.Settings({ voice: "shubh", pace: 1.1 }),
});

NotesCopy Anchor Link

• fetch replaces the global fetch (upstream takes an aiohttp session).
• baseUrl defaults to https://api.sarvam.ai. The WAV header of each reply is stripped before the audio is pushed.
• sampleRate can also be 32000, 44100 or 48000 for bulbul:v3.

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

• HTTP goes through fetch and the WebSocket through the core websocketConnect. Both work on Bun, Node, Deno and Cloudflare Workers.
• bulbul:v2, the InputParams class and the model, voice_id, params and aggregate_sentences constructor options are deprecated upstream and not ported.
• Tested against local servers, not against Sarvam itself.