How to enable text preprocessing

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

1 # Import SarvamAI client and save helper
2 from sarvamai import SarvamAI
3 from sarvamai.play import save

1 # Initialize the SarvamAI client with your API key
2 client = SarvamAI(api_subscription_key="YOUR_API_SUBSCRIPTION_KEY")

1 # Example 1: Without text preprocessing (default)
2 audio = client.text_to_speech.convert(
3     text="The price is Rs. 1,00,000 on 25th December, 2024",
4     target_language_code="en-IN",
5     enable_preprocessing=False   
6 )

1 #Example 2: With text preprocessing enabled
2 audio = client.text_to_speech.convert(
3     text="The price is Rs. 1,00,000 on 25th December, 2024",
4     model="bulbul:v2",
5     target_language_code="en-IN",
6     enable_preprocessing=True  # Enable smart text normalization
7 )

1 # Save the generated audio to a file
2 save(audio, "output_pitch_up.wav")