Beta Sarvam AI

Sarvam Bulbul v3

Indian-language TTS (Bulbul) with a WebSocket streaming endpoint; priced in rupees per 10K characters.

Est. per minuten/a

Overview

Best for: Hindi and other Indian-language voice agents.

At a glance

Free tierYes

Text stream inYes

WebRTCNo

WebSocketYes

gRPCNo

EU dataNo

Self-hostNo

Open weightsNo

Beta. Priced in INR: INR 30 per 10K chars (INR 3,000 per 1M) for v3, INR 15 for v2; USD not computed. Free credit INR 1,000. Indian languages plus English, list not verified. India region only. Rate limits are RPM (Starter 60).

Audio in

Text

Audio out

Default 24,000 Hz; formats not verified

Languages

Indian languages (e.g. hi-IN) plus English; exact list not verified

Voices

Named speakers (e.g. shubh)

Latency

Not verified

Regions

India

Compliance

Not verified.

Features

WebSocket streaming
flush and completion events
multiple conversions per connection

Pricing

What	Price	Unit	Notes
Bulbul v3	INR 30	per 10K characters	Beta pricing
Bulbul v2	INR 15	per 10K characters

How the per-minute estimate was worked out

Priced in INR (about INR 2.7/min at 900 chars for v3); USD not computed to avoid an assumed FX rate

Free tier: INR 1,000 free credits on every new plan

Source: docs.sarvam.ai

Setup

Create a Sarvam API key.
Use the SDK: client.text_to_speech_streaming.connect(model='bulbul:v3'), then configure(language, speaker), send text, flush.

Endpoint

/text-to-speech/ws (Sarvam API host)

Authentication

API subscription key

Warnings

Beta pricing on v3

Bulbul v3 rates are labelled beta and may change.

Billing rounds up per request

Each request's length is rounded up, so many tiny streaming messages can cost slightly more.

Send pings on long sessions

Sarvam recommends pings to keep long WebSocket connections alive.

Plus 12 warnings that apply to all text-to-speech, streaming APIs. See category warnings.

Limits

Streaming up to 2,500 characters per request
Rate limits: Starter 60 RPM, Pro 200, Business 1,000

Models and products

Name	Status	Notes
bulbul:v3	Beta pricing	No pitch/loudness; pace 0.5-2.0; temperature; default 24 kHz.
bulbul:v2	GA

Docs and sources

Docs

Sources used

Not fully verified

Full language list, output formats, latency, exact host.

Similar text-to-speech APIs

Resemble AIResemble AI TTS (Chatterbox models)n/a2 high-severity warnings NeuphonicNeuphonic APIn/a0 high-severity warnings Smallest AISmallest.ai Waves Lightning v3.1n/a1 high-severity warnings MiniMaxMiniMax Speech (international)$0.054 - 0.09/min1 high-severity warnings

Spotted a wrong price or a dead link?