LogoFastRouter
Sarvam: Saaras V3
Sarvam
Feb 11, 2026
sarvam/saaras:v3
Context Length2,046
Input Price$0.00008800/second
Output Price-
Max Output
Blended Price-

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

Input Modalitiesaudio
Output Modalitiestext
Modalityaudio->text
Provider Details

sarvam

Input Cost$0.00008800/second
Output Cost-
Context Length2,046
Max Output-
Pricing Details
Duration Cost$0.000088/second
Supported Parameters
Parameter
Other
input_audio_codec
language_code
mode
Make Your First API Call

Get started by making your first request to FastRouter. Use your favorite SDK or make direct API calls.

Copy

Before you run this code:

  1. Replace <FASTROUTER_API_KEY> with your actual API key
  2. Run the code, then check your dashboard for analytics
Frequently Asked Questions

More models from Sarvam
Sarvam: Bulbul V2
sarvam/bulbul:v2

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.

Sarvam: Sarvam 105B
sarvam/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: 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