How to set the sample rate (audio quality)

The speech_sample_rate parameter controls the audio quality and size of the generated output.

It is optional — if omitted, the default value is 22050 Hz (high quality).

Supported values:

Sample Rate (Hz)	Audio Quality Description
8000	Basic telephony quality
16000	Good quality voice
22050	Default high-quality audio
24000	Premium audio quality (larger size)

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_API_SUBSCRIPTION_KEY")
6 
7 # Generate speech using REST
8 audio = client.text_to_speech.convert(
9     text="Welcome to Sarvam AI!",
10     model="bulbul:v2",
11     target_language_code="en-IN",
12     speech_sample_rate=24000  # Set premium audio quality
13 )
14 save(audio, "output1.wav")