Sarvam

Sarvam AI: Saarika V2.5

sarvam/saarika:v2.5
Studio Quality Instant (~1–2s) 99% Uptime 4.9 (98% positive)
Context

N/A

Input

audio

Output

text

Tool calling

Not listed

OverviewProvidersPricingBenchmarksAPI and quickstartReviews

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.

Compare Speech-to-Text ModelsCompare Audio Models

Input modalities

audio

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Sarvam
Available

Speech transcription

$0.350 / hour

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Speech transcriptionSTT$0.350 / hour

Performance & Benchmarks

Independent evaluations and live cluster operational metrics

Quality Grade Verified Cluster Grade
Response Speed Standard Latency
Cluster Reliability Active (99% Uptime)
Community Rating 4.8 / 5.0
Key Strengths
  • • Optimized for unified API inference
  • • High prompt fidelity across structured outputs
Guidance & Watchouts

General inference, enterprise agent workflows, and conversational pipelines.

Artificial AnalysisSource: Artificial Analysis (artificialanalysis.ai)

Based on data from Artificial Analysis. This analysis was generated by OneInfer and does not represent the views or endorsement of Artificial Analysis.

API Guide

Refer Documentation
  1. 1

    Generate your access token

    Use your API key to generate the JWT access token required by the Models API.

  2. 2

    Add the JWT token

    Copy the generated JWT token and replace JWT_TOKEN in the example below.

  3. 3

    Check your credits

    If your balance is too low, before calling the model.

  4. 4

    Run the API example

    Choose your preferred language, copy the example, and send your first model request.

    curl -X POST https://api.oneinfer.ai/v1/ula/generate-audio \
  -H "Authorization: Bearer YOUR_JWT_TOKEN" \
  -F "provider=sarvam" \
  -F "model=sarvam/saarika:v2.5" \
  -F "file=@audio.mp3"

Community Model Reviews & Ratings

Verified visitor & developer evaluations on Sarvam AI: Saarika V2.5's real-world intelligence, code accuracy, and speed

4.8
Community consensus rating
Top Community Consensus Tags:
Be the first to rate and tag this model's coding and reasoning strengths!

No community reviews yet

Be the first to share developer feedback on Sarvam AI: Saarika V2.5's latency, code accuracy, and reliability in production.