Speech to text

Speech to text API that picks the right engine per language

Ten transcription engines — Deepgram, Whisper, Sarvam, Soniox, ElevenLabs Scribe and more — behind one API, with a smart router that sends each language to the engine that transcribes it best.

Last updated 2026-09-15

Engines you can route between

Deepgram Nova-3OpenAI WhisperGroq WhisperSarvam SaarasSonioxElevenLabs ScribeAWS TranscribexAICustom endpointTelenow Smart router

The same streaming STT layer powers live phone agents — where a transcript that arrives late is a conversation that fails. Try it against real audio from the dashboard, or read the API docs.

Frequently asked questions

Which speech-to-text engines are available?+

Ten: Deepgram (Nova-3), OpenAI Whisper, Groq Whisper, Sarvam (Saaras), Soniox, ElevenLabs Scribe, AWS Transcribe, xAI, custom endpoints — plus Telenow Smart, a router that sends each language to its best engine automatically.

Does it handle Indian languages and code-switching?+

Yes — Hindi, Tamil, Telugu, Kannada, Malayalam, Marathi, Bengali, Gujarati, Punjabi and Odia, including Hinglish code-switching mid-sentence. Telenow Smart routes each to the engine that transcribes it best.

Is it real-time?+

Streaming transcription is the default — it is the same STT layer that powers live phone agents, where words must land in milliseconds, not after the call.

How is it priced?+

Per minute of audio, itemised by engine, on the same component-level billing as everything else — no subscription required, and unanswered/empty sessions are never billed.

$1.00 free credit on signup

Transcribe with the best engine per language — free credit included

Sign up free and get $1.00 in credit — no card required. Connect your number, pick a template, and go live in minutes.