Sarvam (Saaras v3) for AI voice agents
Sarvam (Saaras v3) is one of the speech-to-text engines you can run a Telenow AI voice agent on. India-native ASR — 11 Indian languages + Hinglish code-mixing, streaming. Use Sarvam (Saaras v3) to transcribe the caller in real time so your agent understands every word, even with accents and code-switching. Mix and match it with any LLM, STT, TTS and carrier — Telenow is component-level, so you're never locked in.
Last updated 2026-06-25
Sarvam (Saaras v3) speech-to-text
Languages
Frequently asked questions
Can Sarvam (Saaras v3) transcribe live phone calls?
Yes — Sarvam (Saaras v3) streams real-time transcription into your Telenow agent so it understands the caller as they speak.
Which languages does Sarvam (Saaras v3) support?
Hindi, English, Bengali, Tamil, Telugu, Kannada, Malayalam, and Marathi.
Is Sarvam (Saaras v3) fast enough for a live call?
Sarvam (Saaras v3) is built for low-latency streaming, so partial transcripts arrive in well under a second — fast enough for natural back-and-forth.
How much does Sarvam (Saaras v3) cost for a voice agent?
You pay Sarvam (Saaras v3)'s usage at cost plus Telenow's transparent platform fee — billed per component (speech, model, telephony) and per minute, with new accounts getting free signup credit to try it.
Can I bring my own Sarvam (Saaras v3) API key?
Yes. Telenow supports BYOK — paste your own Sarvam (Saaras v3) key to bill Sarvam (Saaras v3) usage to your account, or use the platform key and pay through Telenow.
Other speech-to-text (stt) options
Build a voice agent with Sarvam (Saaras v3)
Sign up free and get ₹300.00 in credit — no card required. Connect your number, pick a template, and go live in minutes.