How much does Sarvam: Bulbul V2 cost?

Sarvam: Bulbul V2 costs $15.00 per 1M input tokens.

What is the context length of Sarvam: Bulbul V2?

Sarvam: Bulbul V2 has a 1,500 token context window.

What inputs and outputs does Sarvam: Bulbul V2 support?

Sarvam: Bulbul V2 accepts text as input and returns audio.

What other models does Sarvam have?

Sarvam: Saaras V3, Sarvam: Sarvam 105B and Sarvam: Sarvam 105B (Free) are other models from Sarvam.

When was Sarvam: Bulbul V2 released?

Sarvam: Bulbul V2 was released on May 7, 2025.

Bulbul V2

SarvamReleased May 7, 2025sarvam/bulbul:v2

Compare

Sarvam: Bulbul V2 is a text-to-speech (TTS) model from Sarvam AI, delivering real-time, natural-sounding speech in 11 Indian languages at a fraction of global costs. It builds on prior versions with key enhancements including improved audio quality, 30+ speaker voices (expanded from six distinct voices in v1 for diverse use cases like professional or conversational tones), and adjustable speech speed from 0.5x to 2.0x for customized delivery.

Context

Max output

Input /1M

$15.00

Output /1M

—

AcceptsTextProducesAudio

Providers

FastRouter routes your requests to this provider. You can also bring your own key.

ProviderInput /1MOutput /1MContextMax output

Sarvam

sarvam

Input /1M$15.00

Output /1M—

Context2K

Max output2K

Supported parameters

Request parameters you can send with this model.

Core (Sampling & basic generation)

temperature: Controls randomness of output.

Other

enable_cached_responses
enable_preprocessing
loudness
output_audio_codec
pace
pitch
speaker
speech_sample_rate
target_language_code

Make your first API call

OpenAI-compatible. Point your SDK at FastRouter, or call the API directly.

Full API docs

Replace <FASTROUTER_API_KEY> with your key · Get your key →

HTTP

Frequently asked questions

More models from Sarvam

Saaras V3sarvam/saaras:v3

Saaras V3 is Sarvam AI's next-generation automatic speech recognition (ASR) model engineered for Indian languages and real-world speech conditions. Saaras V3 supports 23 languages (22 official Indian languages plus English) within a unified multilingual model. The model achieves approximately 19% Word Error Rate (WER) on the IndicVoices benchmark, improving significantly from its predecessor Saaras V2.5 which had ~22% WER. On the 10 most popular languages in the IndicVoices dataset, it achieves 19.3% WER, and performance advantages widen for lower-resource Indian languages

Sarvam 105Bsarvam/sarvam-105b

Sarvam 105B is Sarvam AI's flagship open-source Mixture-of-Experts (MoE) large language model (LLM), trained from scratch as India's first competitive 105-billion-parameter model. It delivers state-of-the-art performance across Indian languages and excels in enterprise-grade applications, with strong capabilities in multi-step reasoning, mathematics, coding, knowledge retrieval, and instruction-following.

Sarvam 105B (Free)sarvam/sarvam-105b:free

Sarvam 105B is Sarvam AI's flagship open-source Mixture-of-Experts (MoE) large language model, trained from scratch as India's first competitive 105-billion-parameter model. It delivers strong performance across Indian languages and excels in enterprise-grade applications, with capabilities in multi-step reasoning, mathematics, coding, knowledge retrieval, and instruction-following.

Model scores sourced from ArtificialAnalysis