Skip to main content
Models/Sarvam AI/Bulbul v3

Bulbul v3

Sarvam AI 🔊 Text-to-Speech

Sarvam's latest text-to-speech model, 30+ voices across Indian languages and English. Natural prosody with cultural intonation. Currently in beta.

Specifications

Input modalitiestext
Output modalitiesaudio
Relative speed●●●●○ Fast
Streaming outputNo
Input price$0.63 / 1M

Pricing

$0.63 / 1M input characters

Platform credit pricing — live rates on the Models page.

Use Bulbul v3 on Zubnet →

More from Sarvam AI

S
Sarvam 105B
Sarvam's 24B multilingual LLM, fluent in all 22 official Indian languages + English. OpenAI-compatible API. Free tier with no per-token charges. Supports wiki grounding, reasoning
🧠 Language Model
B
Bulbul v2
Sarvam's stable text-to-speech model for Indian languages and English. Returns base64-encoded WAV audio. Production-ready with consistent quality.
🔊 Text-to-Speech