Bulbul | Sarvam API Docs

Bulbul v3 is our latest text-to-speech model, specifically designed for Indian languages and accents. It features improved audio quality, 30+ speaker voices, and supports up to 2500 characters per request.

At a Glance


Model ID	`bulbul:v3` (legacy: `bulbul:v2`)
What it does	Text-to-speech with 30+ natural speaker voices and pace control
Languages	11 (10 Indian + English), full list
APIs	REST, HTTP streaming, WebSocket
Input limits	2,500 characters per REST request; sample rates up to 48 kHz (REST API only), all limits
Pricing	Pricing page
Best for	Voice agents, IVR prompts, narration and audio content
Known limitations	See below

Key Features

30+ Speaker Voices

Wide selection of natural-sounding voices including Shubh, Aditya, Ritu, Simran, Anand, Roopa, Priya, and more.

Extended Character Limit

Support for up to 2500 characters per request for longer content generation.

Sample Rate Options

Multiple sample rates: 8kHz, 16kHz, 22.05kHz, 24kHz (default). Higher rates (32kHz, 44.1kHz, 48kHz) available in bulbul:v3 REST API only.

Language Support

Support for 11 languages (10 Indian + English) with BCP-47 codes. The target language code is primarily used by the pre-TTS text normalization model.

Natural Prosody

Human-like speech patterns with natural intonation and emotional expression.

Pace Control

Adjustable speech speed from 0.5x to 2.0x for customized delivery.

Language Support

Bulbul v3 supports the following Indian languages:

Hindi (hi-IN), Bengali (bn-IN), Tamil (ta-IN), Telugu (te-IN), Gujarati (gu-IN), Kannada (kn-IN), Malayalam (ml-IN), Marathi (mr-IN), Punjabi (pa-IN), Odia (od-IN), English (en-IN)

Available Speakers

Bulbul v3 offers 30+ speaker voices:

Speakers: Shubh (default), Aditya, Ritu, Priya, Neha, Rahul, Pooja, Rohan, Simran, Kavya, Amit, Dev, Ishita, Shreya, Ratan, Varun, Manan, Sumit, Roopa, Kabir, Aayan, Ashutosh, Advait, Anand, Tanya, Tarun, Sunny, Mani, Gokul, Vijay, Shruti, Suhani, Mohit, Kavitha, Rehan, Soham, Rupali

Use the speaker parameter to select specific voices for your use case. Each speaker has unique characteristics suitable for different applications.

Key Capabilities

Basic Usage

Speaker Selection

Sample Rate Control

Convert text to speech with default settings. This is the simplest way to get started with Bulbul v3.

from sarvamai import SarvamAI
from sarvamai.play import play, save
client = SarvamAI(
    api_subscription_key="YOUR_SARVAM_API_KEY"
)
response = client.text_to_speech.convert(
    text="Hello, how are you today?",
    language_code="en-IN",
    model="bulbul:v3"
)
# Play the audio
play(response)
# Save the response to a file
save(response, "output.wav")

Limits

Limit	Value
Max characters per request (REST)	2,500
`pace`	0.5–2.0 (`bulbul:v3`) / 0.3–3.0 (`bulbul:v2`)
`pitch`	-1.0 to 1.0; suitable range -0.75 to 0.75 (`bulbul:v2` only)
`loudness`	0.1–3.0 (`bulbul:v2` only)
`speech_sample_rate`	8000 / 16000 / 22050 / 24000 Hz; plus 32000 / 44100 / 48000 Hz (REST API only). Default: 24000 (v3), 22050 (v2)
Rate limits	See Rate Limits

Known Limitations

Limitation	Detail	Workaround
No SSML support	Bulbul does not support SSML tags for fine-grained prosody control	Use `pace` for coarse control; split text at natural pause points
Romanised Indic input degrades quality	Transliterated input (e.g., `"Aapka order confirm ho gaya hai"`) significantly reduces output quality	Always use native script for Indic words (e.g., `"आपका order confirm हो गया है"`)
High sample rates are REST-only	32 kHz, 44.1 kHz, and 48 kHz are available via the REST API with `bulbul:v3`; both HTTP streaming and WebSocket streaming are capped at 24 kHz	Use ≤ 24 kHz for streaming (HTTP or WebSocket)

Next Steps

Developer quickstart

Learn how to integrate the Bulbul v3 API within your application.

API Reference

Complete API documentation for text to speech endpoints.

Cookbook

Step-by-step tutorial for text-to-speech implementation.