Sarvam AI
Sarvam Motif

Speech to Text, perfected for India

Trust every transcript, even with background noise, multiple accents, or mid-sentence language switches.

Speak to see live captions

Want to use this API?

Flexible output Same audio,
multiple formats

Transcribe

With formatting and number normalization.

Output
मेरा फोन नंबर है 9840950950

Translate

From Indic languages to English.

Output
My phone number is 9840950950

Transliteration

Indian languages written in English letters.

Output
mera phone number hai 9840950950

Verbatim

Preserves fillers and spoken numbers.

Output
मेरा फोन नंबर है नौ आठ चार zero नौ पांच zero नौ पांच zero

Codemix

Native script, keeps English words in English.

Output
मेरा phone number है 9840950950

Every word, captured accurately

Code-mixing. Numbers. Proper nouns. Abbreviations.

हाँमैंनेPROPER NOUNFlipkartसेNUMBER₹12,499काENTITYSamsungGalaxyCODE SWITCHफ़ोनऑर्डरकियाथा।ऑर्डरIDहैABBREVIATIONFLK-78234-XN।CODE SWITCHडिलीवरीएड्रेसहै42,PROPER NOUNKoramangala5thBlock,PROPER NOUNBangalore।मेराफ़ोननंबरहैPHONE NUMBER9840950950।CODE SWITCHप्लीज़डिलीवरीजल्दीकरदीजिए,मेरापुरानाफ़ोनबिल्कुलकामनहींकररहा।

Turn speech into text
you can trust

Seamless code-mixing

00:00

HCG MCC Hospital ஒரு ground breaking achievement பண்ணிட்டாங்க.

Telephony-optimized

00:00

नमस्कार डब्ल्यू सी बैंक में संपर्क करने के लिए आपका धन्यवाद

Handle noisy audio

00:00

अच्छा, मौजूदा सरकार का कामकाज आपको कैसा लगता है?

Powering real-world
voice solutions

From call centers to accessibility tools. Real use cases, already in production.

Voice agents

Real-time transcription for live voice agents and customer interactions.

Customer support

Sales & lead qualification

Edtech tutors

Social & companion bots

0:00

Voice agents

Made for developers.
Scales for enterprises

22 Indian languages with automatic detection

Comprehensive coverage across all major Indian languages with seamless code-mixing support.

REST, streaming & batch APIs

Synchronous REST for quick calls, real-time streaming for voice agents, batch for analytics.

Speaker diarization

Differentiate speakers in conversations.

Key term prompting

Bias recognition toward names, brands, and terms that are easy to miss.

Plug & play integrations

LiveKit / Pipecat: deploy a voice agent in under 10 minutes.

<250ms

Median latency

100M+

Mins transcribed

>99.5%

Uptime

22 Indian languages, every
script natively transcribed

Accurate transcription across all scheduled languages with code-mixing support.

Your questions, answered

Start transcribing in minutes Powered by Saaras V4