Skip to content
ArenaPlatform

Saaras v4

sarvam/saaras-v4

Sarvam's newest speech recognition model, introduced August 18, 2026 and now its default recommendation. It keeps Saaras v3's five output modes and 22 Indian languages, adds Global English accents, and supports keyterm prompting.

Get API KeyRead the Docs
API
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -F 'model=sarvam/saaras-v4' \
  -F 'file=@recording.wav'
Read docs
Input Price
₹0.425 / minute
Output Price
—
Input
Audio
Output
Text

Capabilities

Explore what Saaras v4 supports, then use the API section for a request tailored to this model.

BatchStreamSegment timestampsTranslation

Languages

Multilingual

Model Information

Provider
Sarvam AI
Product
Speech-to-Text
Release Date
Aug 18, 2026
Data Policy
Configurable
Region
India
Input
Audio
Output
Text
Provider Documentation

Playground

Try Saaras v4 by Sarvam AI. Requests use the selected workspace’s credits and API pricing.

Saaras v4Credits —
Saaras v4
Attach an audio file to turn speech into text.
Sign in to run a requestAPI reference

Providers

Compare available endpoints, pricing, and context limits for Saaras v4.

ProviderContextOutputInput PriceOutput PriceEndpoint
Sarvam AINot specifiedText₹0.425 / minute—
sarvam/saaras-v4:sarvam

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max bytes2000000
Max seconds30
Formatswav

Performance

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

API
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -F 'model=sarvam/saaras-v4' \
  -F 'file=@recording.wav'
Read docs
Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

ParameterDetails
modelsarvam/saaras-v4 — Required model identifier.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max bytes2000000
Max seconds30
Formatswav

Similar Models

Explore more speech-to-text and compare their capabilities.

ModelContextInput PriceOutput Price
saaras-v4-batchSarvam AINot specified₹0.425 / minute—
Saaras v3Sarvam AINot specified₹0.425 / minute—
Saaras v3 (Batch)Sarvam AINot specified₹0.425 / minute—
Saarika v2.5Sarvam AINot specified₹0.425 / minute—
MAI-Transcribe 2Microsoft AzureNot specified$0.0014 / minute—
Gemini 3.5 TranscribeGoogle GeminiNot specified$0.0043 / minute—
View All Speech-to-Text