Sarvam AI
Sarvam Motif

Speech to Text, perfected for Tamil

Every accent. Agglutinative morphology. Tanglish switching. Saaras hears Tamil the way Tamils actually speak it.

Speak Tamil to see live captions

Every Tamil word, captured accurately

Code-mixing. Numbers. Proper nouns. Abbreviations.
0:00
நான்PROPER NOUNFlipkart-லஇருந்துNUMBER₹12,499rupees-க்குஒருENTITYSamsungGalaxyCODE SWITCHphoneorderபண்ணியிருந்தேன்.அதோடOrderIDவந்துABBREVIATIONFLK-78234-XN.CODE SWITCHDeliveryaddressவந்து42,PROPER NOUNKoramangala5thBlock,PROPER NOUNBangalore.அப்புறம்என்னோடphonenumberவந்துPHONE NUMBER9840950950.CODE SWITCHPleaseகொஞ்சம்சீக்கிரம்deliveryபண்ணிடுங்க,என்னோடபழையphoneசுத்தமாவேலைசெய்யல.

Flexible output. Same Tamil audio,
multiple formats

Transcribe

With formatting and number normalization.

Output
என் போன் நம்பர் 9840950950

Translate

From Indic languages to English.

Output
My phone number is 9840950950

Transliteration

Indian languages written in English letters.

Output
en phone number 9840950950

Verbatim

Preserves fillers and spoken numbers.

Output
என் போன் நம்பர் ஒன்பது எட்டு நான்கு zero ஒன்பது ஐந்து zero ஒன்பது ஐந்து zero

Saaras hears தமிழ் the way you speak it

Every feature shown with real Tamil audio. Play each clip. Read the transcript. See the difference.

Speaker Diarization

Know who said what

Automatically labels speakers in multi-party Tamil conversations. Colors match the transcript.

Click to play
0:00Speaker 1

வணக்கம், HDFC Bank-க்கு call பண்ணதுக்கு நன்றி. நான் Karthick பேசறேன், How can I help you?

0:00Speaker 2

வணக்கம்ங்க, என்னோட savings account balance check பண்ணனும். Account number வந்து 2641 0078 3395.

0:00Speaker 1

கண்டிப்பா நான் help பண்றேன், verification பண்ண, உங்க registered mobile number-அ கொஞ்சம் confirm பண்ணுங்க.

Code-Mixing

Seamless Tanglish

Handles mid-sentence switching between Tamil and English. No drops, no accent shifts.

Click to play
இனக்கு Code-switchmeeting வந்து ரொம்ப productive ஆ இருந்துச்சு lunch கப்பிரம் Englishcoding sessionல ரொம்பவே smooth ஆ போச்சு team ரொம்ப cooperative ஆ நல்ல work பண்ணாங்க
Telephony-Optimized

Built for real calls

8kHz call center audio, compression, background noise — maintains accuracy for Tamil where others fail.

8kHzNoisy
Click to play

சரி, இப்போ இருக்க அரசாங்கத்தோட செயல்பாடுகள் பத்தி நீங்க என்ன நினைக்கிறீங்க? பாருங்க, ரோடு எல்லாம் நல்லா போட்டிருக்காங்க, ஆனா விலைவாசி தான் ரொம்ப ஏறிடுச்சு. பெட்ரோல் விலை பார்த்தீங்கன்னா 108 ரூபாய் ஆகிடுச்சு. எங்கள மாதிரி சாதாரண ஆளுங்களுக்கு ஏதாவது ஒரு விடிவு காலம் பொறந்தாத்தான் உண்டு. மத்தபடி மெட்ரோ வேலைங்க எல்லாம் நல்லாதான் நடக்குது, சென்னைல நல்ல முன்னேற்றம் தெரியுது.

Developer-first platform

OpenAI-compatible APIs. Drop-in SDKs for Python and Node.js. Go from zero to first transcription in under 5 minutes.

REST & WebSocket APIs

Standard REST for batch, WebSocket for real-time streaming with sub-250ms first byte.

SDKs & libraries

Official Python and Node.js SDKs with TypeScript support. pip install sarvam-ai.

Complete documentation

Interactive API reference, code samples, and integration guides for every endpoint.

Free tier included

Start building immediately. No credit card, no sales call, no minimum commitment. 

from sarvamai import SarvamAI

client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")

# Transcribe audio
response = client.speech_to_text.transcribe(
    file_path="call_recording.wav",
    language_code="hi-IN",
    model="saaras:v3",
    with_diarization=True
)

print(response.transcript)
for turn in response.turns:
    print(f"[{turn.speaker}] {turn.text}")

Enterprise-ready. Responsible AI.

Built with safety, compliance, and data sovereignty at the core.

SOC 2 Type II & ISO 27001

Enterprise-grade security certifications. Annual audits, documented controls, continuous monitoring.

No training on your data

Your API inputs are never used for model training. Zero data retention after processing unless explicitly requested.

Data sovereignty

All data processed and stored in India. No cross-border transfers. Full compliance with Indian data regulations.

Audio data privacy

Audio data is processed in real-time and never stored unless explicitly requested. Complete privacy by default.

Content safety filters

Automated detection and filtering of harmful, abusive, or misleading content in transcriptions.

Audit-ready logging

Comprehensive API usage logs, access controls, and RBAC for enterprise governance and compliance reporting.

Simple, transparent pricing

Start free. Scale as you grow. No hidden costs.

Base plan

₹1.25 per minute

Free trial included

No credit card required. Get API keys instantly.

Volume discounts available
Enterprise pricing available
Speaker diarization included
Usage analytics
All 22 languages
Best for startups

Your questions, answered
Saaras v3 achieves industry-leading word error rates for Tamil, handling agglutinative morphology, grantha consonants, and compound characters with high accuracy.
Yes. Saaras v3 handles natural Tamil-English code-switching seamlessly without accent shifts or dropped words between languages.
Yes. Our WebSocket streaming API delivers sub-250ms latency for Tamil, ideal for real-time voice agents and conversational AI.
Saaras v3 is trained on diverse Tamil speech data covering Chennai Tamil, Madurai Tamil, Sri Lankan Tamil, and other regional variations.
10+ formats including MP3, WAV, AAC, OGG, Opus, FLAC, M4A, AMR, WMA, and WebM. Streaming API supports WAV and raw PCM at 16kHz.

Transcribe in 22 Indian languages Powered by Saaras v3