sarvam

saarika:v2.5

Context

N/A

Input

audio

Output

text

Tool calling

Not listed

About this model

Saarika v2.5 is Sarvam AI's legacy speech recognition model designed for Indian languages and accents. It transcribes audio in the same language spoken, excelling in multi-speaker conversations, telephony audio (8kHz), and code-mixed speech. Supports 11 languages (Hindi, Bengali, Gujarati, Kannada, Malayalam, Marathi, Odia, Punjabi, Tamil, Telugu, English) with automatic language detection and speaker diarization. Achieves 4.96% CER and 18.32% WER on VISTAAR benchmark.

Capabilities

audio

Available through the unified API

text

Available through the unified API

Quick start

View API docs

curl https://api.oneinfer.ai/v1/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ed42b0d03a0b48aaa8d44ae9a042b6aa",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

Providers

Available routing options for this model through OneInfer.

sarvam

ed42b0d03a0b48aaa8d44ae9a042b6aa

Available

Input

$0.000 / 1M

Output

$0.000 / 1M

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

Usage	Price
Input tokens	$0.000 / 1M
Output tokens	$0.000 / 1M

Performance

Published evaluation results associated with this model.

Accuracy

IndicVoices WER (%)20.8

Telephony WER (%)22.1

Efficiency

Real-time Factor0.08

Auto-LID Accuracy (%)94.5

API example

curl https://api.oneinfer.ai/v1/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ed42b0d03a0b48aaa8d44ae9a042b6aa",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'