Sarvam AI
Sarvam Motif

Speech to Text, perfected for Marathi

Every accent. Every dialect. Code-switching mid-sentence. Saaras hears Marathi the way you actually speak it.

Speak Marathi to see live captions

Every Marathi word, captured accurately

Code-mixing. Numbers. Proper nouns. Abbreviations.
0:00
होमीPROPER NOUNFlipkartवरुनNUMBER₹12,499चाENTITYSamsungGalaxyCODE SWITCHफोनऑर्डरकेलाहोताऑर्डरIDआहेABBREVIATIONFLK78234-XNआणिCODE SWITCHडिलीवरीॲड्रेसआहे42,PROPER NOUNKoraMangala5thBlockPROPER NOUNBangaloreमाझाफोननंबरआहेPHONE NUMBER9840950950CODE SWITCHप्लीजडिलीव्हरीलवकरकरूशकालकामाझाजुनाफोनअगदीचकामकरतनाहीये

Flexible output. Same Marathi audio,
multiple formats

Transcribe

With formatting and number normalization.

Output
माझा फोन नंबर 9840950950

Translate

From Indic languages to English.

Output
My phone number is 9840950950

Transliteration

Indian languages written in English letters.

Output
phone number 9840950950

Verbatim

Preserves fillers and spoken numbers.

Output
माझा फोन नंबर 9840950950

Saaras hears मराठी the way you speak it

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

Speaker Diarization

Know who said what

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

Click to play
0:01Speaker 1

नमस्कार, HDFC बँकेमध्ये कॉल केल्याबद्दल धन्यवाद. मी प्रिया बोलतीये. मी तुमची काय मदत करू शकते?

0:10Speaker 2

हो, मला माझ्या savings account चा balance check करायचा आहे. Account number आहे 2641-0078-3395.

0:20Speaker 1

ओके, verification साठी तुमचा registered mobile number confirm करा

Code-Mixing

Seamless Minglish

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

Click to play
अच्छी मीटिंग सूपर प्रड़क्टिव जाली, लंच नंतर चा कोडिंग सेशन मदे तर सगला इक्तम स्मूथली जाला, टीम ने फारच चान काम केला
Telephony-Optimized

Built for real calls

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

8kHzNoisy
Click to play

अच्छा, तुम्हाला सध्याच्या सरकारच्या कामाबद्दल काय वाटतं? हे बघा, रस्ते तर बनले आहेत, पण महागाई प्रचंड वाढली आहे. पेट्रोलचा दर ₹108 झाला आहे. समान्य जनतेला जरा relief पाहिजे. बाकी metro चं काम चांगलं चालू आहे, Nagpur मध्ये खूप development होतीये.

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 Marathi, trained on diverse speech data covering regional accents and conversational patterns.
Yes. Saaras v3 handles natural Marathi-English code-switching seamlessly without accent shifts or dropped words.
Yes. Our WebSocket streaming API delivers sub-250ms latency for Marathi, ideal for real-time voice agents and conversational AI.
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