Sarvam AI Text-to-Speech

TTS for Indian languages with SarvamTTSService and SarvamHttpTTSService, with extensive voice customization on Sarvam AI’s API.

Overview

SarvamTTSService provides text-to-speech synthesis specialized for Indian languages and voices. The service uses the bulbul:v3 model by default, which offers temperature control for output randomness, pace adjustment, and 21 speaker voices. The previous bulbul:v2 model is deprecated as Sarvam’s API no longer serves it.

Sarvam TTS API Reference

Pipecat’s API methods for Sarvam AI TTS integration

Example Implementation

Complete example with Indian language support

Sarvam Documentation

Official Sarvam AI text-to-speech API documentation

Sarvam Console

Access Indian language voices and API keys

Installation

To use Sarvam AI services, no additional dependencies are required beyond the base installation:

uv add "pipecat-ai"

Prerequisites

Sarvam AI Account Setup

Before using Sarvam AI TTS services, you need:

1. Sarvam AI Account: Sign up at Sarvam AI Console
2. API Key: Generate an API key from your account dashboard
3. Language Selection: Choose from available Indian language voices

Required Environment Variables

• SARVAM_API_KEY: Your Sarvam AI API key for authentication

Configuration

Sarvam offers two service implementations: SarvamTTSService (WebSocket) for real-time streaming and SarvamHttpTTSService (HTTP) for simpler batch synthesis.

SarvamTTSService

api_key · str · required

Sarvam AI API subscription key.

model · str · default: "bulbul:v3" · deprecated

TTS model to use. Options: bulbul:v3, bulbul:v3-beta, bulbul:v2 (deprecated). Deprecated in v0.0.105. Use settings=SarvamTTSService.Settings(model=...) instead.

voice_id · str · default: "None" · deprecated

Speaker voice ID. If None, uses shubh (the default for v3). Deprecated in v0.0.105. Use settings=SarvamTTSService.Settings(voice=...) instead.

url · str · default: "wss://api.sarvam.ai/text-to-speech/ws"

WebSocket URL for the TTS backend.

text_aggregation_mode · TextAggregationMode · default: "TextAggregationMode.SENTENCE"

Controls how incoming text is aggregated before synthesis. SENTENCE (default) buffers text until sentence boundaries, producing more natural speech. TOKEN streams tokens directly for lower latency. Import from pipecat.services.tts_service.

aggregate_sentences · bool · default: "None" · deprecated

Deprecated in v0.0.104. Use text_aggregation_mode instead.

sample_rate · int · default: "None"

Audio sample rate in Hz (8000, 16000, 22050, 24000, and for v3: 32000, 44100, 48000). If None, uses model-specific default (24000 for v3, 22050 for deprecated v2).

params · InputParams · default: "None" · deprecated

Deprecated in v0.0.105. Use settings=SarvamTTSService.Settings(...) instead.

settings · SarvamTTSService.Settings · default: "None"

Runtime-configurable settings. See SarvamTTSService Settings below.

SarvamHttpTTSService

api_key · str · required

Sarvam AI API subscription key.

aiohttp_session · aiohttp.ClientSession · required

An aiohttp session for HTTP requests.

model · str · default: "bulbul:v3" · deprecated

TTS model to use. Options: bulbul:v3, bulbul:v3-beta, bulbul:v2 (deprecated). Deprecated in v0.0.105. Use settings=SarvamHttpTTSService.Settings(model=...) instead.

voice_id · str · default: "None" · deprecated

Speaker voice ID. If None, uses shubh (the default for v3). Deprecated in v0.0.105. Use settings=SarvamHttpTTSService.Settings(voice=...) instead.

base_url · str · default: "https://api.sarvam.ai"

Sarvam AI API base URL.

sample_rate · int · default: "None"

Audio sample rate in Hz (8000, 16000, 22050, 24000, and for v3: 32000, 44100, 48000). If None, uses model-specific default (24000 for v3, 22050 for deprecated v2).

params · InputParams · default: "None" · deprecated

Deprecated in v0.0.105. Use settings=SarvamHttpTTSService.Settings(...) instead.

settings · SarvamHttpTTSService.Settings · default: "None"

Runtime-configurable settings. See SarvamHttpTTSService Settings below.

SarvamTTSService Settings

Runtime-configurable settings passed via the settings constructor argument using SarvamTTSService.Settings(...). These can be updated mid-conversation with TTSUpdateSettingsFrame. See Service Settings for details.

Parameter	Type	Default	Description
model	str	None	Model identifier. (Inherited.)
voice	str	None	Voice identifier. (Inherited.)
language	Language | str	None	Language for synthesis. (Inherited.)
enable_preprocessing	bool	NOT_GIVEN	Enable text preprocessing.
pace	float	NOT_GIVEN	Pace of speech.
pitch	float	NOT_GIVEN	Pitch of speech.
loudness	float	NOT_GIVEN	Loudness of speech.
temperature	float	NOT_GIVEN	Temperature for speech synthesis.
min_buffer_size	int	NOT_GIVEN	Minimum buffer size for WebSocket.
max_chunk_length	int	NOT_GIVEN	Maximum chunk length for WebSocket.

SarvamHttpTTSService Settings

Runtime-configurable settings passed via the settings constructor argument using SarvamHttpTTSService.Settings(...). These can be updated mid-conversation with TTSUpdateSettingsFrame. See Service Settings for details.

Parameter	Type	Default	Description
model	str	None	Model identifier. (Inherited.)
voice	str	None	Voice identifier. (Inherited.)
language	Language | str	None	Language for synthesis. (Inherited.)
enable_preprocessing	bool	NOT_GIVEN	Enable text preprocessing.
pace	float	NOT_GIVEN	Pace of speech.
pitch	float	NOT_GIVEN	Pitch of speech.
loudness	float	NOT_GIVEN	Loudness of speech.
temperature	float	NOT_GIVEN	Temperature for speech synthesis.

Usage

Basic Setup (WebSocket)

from pipecat.services.sarvam.tts import SarvamTTSService
from pipecat.transcriptions.language import Language

tts = SarvamTTSService(
    api_key=os.getenv("SARVAM_API_KEY"),
    settings=SarvamTTSService.Settings(
        voice="shubh",
        model="bulbul:v3",
        language=Language.HI,
    ),
)

With Temperature Control

from pipecat.services.sarvam.tts import SarvamTTSService
from pipecat.transcriptions.language import Language

tts = SarvamTTSService(
    api_key=os.getenv("SARVAM_API_KEY"),
    settings=SarvamTTSService.Settings(
        voice="shubh",
        model="bulbul:v3",
        language=Language.HI,
        pace=1.2,
        temperature=0.8,
    ),
)

HTTP Service

import aiohttp
from pipecat.services.sarvam.tts import SarvamHttpTTSService
from pipecat.transcriptions.language import Language

async with aiohttp.ClientSession() as session:
    tts = SarvamHttpTTSService(
        api_key=os.getenv("SARVAM_API_KEY"),
        aiohttp_session=session,
        settings=SarvamHttpTTSService.Settings(
            voice="shubh",
            model="bulbul:v3",
            language=Language.HI,
            pace=1.2,
            temperature=0.8,
        ),
    )

The InputParams / params= pattern is deprecated as of v0.0.105. Use Settings / settings= instead. See the Service Settings guide for migration details.

Notes

• Model default: bulbul:v3 is the default model. The previous bulbul:v2 is deprecated since 1.9.0 — Sarvam’s API rejects it.
• Model differences: bulbul:v2 supported pitch and loudness control; bulbul:v3 supports temperature control but does not support pitch or loudness. Setting unsupported parameters for a model will log a warning.
• Default voice: v3 defaults to shubh; deprecated v2 defaulted to anushka.
• Default sample rate: v3 defaults to 24000 Hz; deprecated v2 defaulted to 22050 Hz.
• Indian language focus: Sarvam AI specializes in Indian languages, supporting Bengali, English (India), Gujarati, Hindi, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, and Telugu.
• Pace ranges differ: bulbul:v3 supports pace from 0.5 to 2.0; deprecated v2 supported 0.3 to 3.0. Values outside the range are clamped automatically.

Event Handlers

Sarvam WebSocket TTS supports the standard service connection events:

Event	Description
on_connected	Connected to Sarvam WebSocket
on_disconnected	Disconnected from Sarvam WebSocket
on_connection_error	WebSocket connection error occurred

@tts.event_handler("on_connected")
async def on_connected(service):
    print("Connected to Sarvam")