How to adjust the pace (speed)

The pace parameter controls the speed at which the speech is delivered.

It is optional, if omitted, the default value is 1.0 (normal speed).

bulbul:v3 range: 0.5 (slowest) to 2.0 (fastest)
bulbul:v2 range: 0.3 (slowest) to 3.0 (fastest)
Values < 1.0 slow the speech down; values > 1.0 speed it up.

Pace Recommendations by Use Case

Pace Value	Effect	Recommended Use Case
0.5 – 0.7	Very slow, deliberate	Accessibility tools, elderly users, pronunciation guides
0.8 – 0.9	Relaxed, measured	EdTech narration, meditation/wellness apps, tutorials
1.0	Natural speed (default)	Conversational agents, general-purpose TTS
1.1	Slightly brisk	Notifications, news briefings, professional IVR
1.2 – 1.5	Fast, energetic	Quick summaries, high-engagement marketing audio
1.6 – 2.0	Very fast	Screen readers, speed-listening (use with caution)

Start at 1.0 (natural) or 1.1 (brisk, professional contexts). Avoid values above 1.5 unless specifically building speed-listening features.

Example Code

Rest API

Streaming API

from sarvamai import SarvamAI
from sarvamai.play import save
# Initialize the REST client
client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
# Generate speech using REST
audio = client.text_to_speech.convert(
    text="Welcome to Sarvam AI!",
    model="bulbul:v3",
    language_code="en-IN",
    pace=1.5  # Increase pace for faster speech
)
save(audio, "output1.wav")