bulbul:v3

sarvam/bulbul:v3

Context

2000

Input

text

Output

audio

Tool calling

Not listed

About this model

Bulbul v3 is a production-grade text-to-speech model optimized for 11 Indian languages. It features native support for code-mixed speech, professional voice cloning, and industry-leading stability in telephony environments (8 kHz). It automatically infers prosody, emphasis, and emotional tone.

Compare Text-to-Speech Models Compare Audio Models

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Sarvam

Available

Text to speech

$0.350 / 1M characters

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

Usage	Price
Text to speechTTS	$0.350 / 1M characters

Performance

Published evaluation results associated with this model.

Naturalness

Listener Preference (48kHz)63.14

Listener Preference (8kHz)77.95

Stability

Error Rate (%)8.6

Mispronunciation Rate (%)7.84

API example

Refer Documentation

curl -X POST https://api.oneinfer.ai/v1/ula/generate-audio \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "provider": "sarvam",
  "model": "sarvam/bulbul:v3",
  "prompt": "OneInfer makes AI inference simple.",
  "stream": false,
  "voice_id": "English_expressive_narrator",
  "format": "mp3"
}'