How to enable text preprocessing

Important: The enable_preprocessing parameter is only supported for bulbul:v2. It is not available for bulbul:v3.

The enable_preprocessing parameter improves pronunciation of numbers, dates, currencies, and mixed-language text.

It is optional — if omitted, default is False (no preprocessing).

When enabled:

Numbers are expanded (e.g., "Rs. 1,00,000" → “rupees one lakh”)
Dates are read naturally (e.g., “25th December, 2024” → “twenty-fifth December two thousand twenty-four”)
Abbreviations and symbols are handled correctly

Example Code

Rest API

Streaming API

1 from sarvamai import SarvamAI
2 from sarvamai.play import save
3 
4 # Initialize the REST client
5 client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
6 
7 # Generate speech using REST (bulbul:v2 only)
8 audio = client.text_to_speech.convert(
9     text="Welcome to Sarvam AI!",
10     model="bulbul:v2",
11     target_language_code="en-IN",
12     speaker="anushka",
13     enable_preprocessing=True  # Enable smart text normalization
14 )
15 save(audio, "output1.wav")

1	from sarvamai import SarvamAI
2	from sarvamai.play import save
3
4	# Initialize the REST client
5	client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
6
7	# Generate speech using REST (bulbul:v2 only)
8	audio = client.text_to_speech.convert(
9	text="Welcome to Sarvam AI!",
10	model="bulbul:v2",
11	target_language_code="en-IN",
12	speaker="anushka",
13	enable_preprocessing=True # Enable smart text normalization
14	)
15	save(audio, "output1.wav")