Stream low-latency transcripts during live calls or transcribe recordings in bulk — across 22 Indian languages + English, accents, and noisy telephony.
02Speech to Text
Word

Real phone lines are noisy. The model separates speech from the line, streams partial words as they're said and settles each one with its own timestamp.
Hello,I'dliketocheckmypendingfeeforthismonth.
Click to start transcription
English (India)
Uses your microphone — not the sample video or page audio.
Transcription output
Transcription tuned for real phone audio — accents, domain terms, and spontaneous speech.
22 Indian languages + English, with mid-conversation language switching.
I'd like to check my pending fee
Low-latency streaming transcripts for live agents, plus fast batch for recordings.
Handles background noise, cross-talk, and low-bitrate telephony without falling apart.
Know who said what — agent vs caller — with word-level timing and confidence.
Usage-based pricing that scales from a handful of calls to millions of minutes.
Batch accuracy at scale, or real-time transcripts for live calls.
Industry-leading transcription powered by Scribe. Supports 22 Indian languages + English with keyterm prompting and dynamic audio tagging — built for batch transcription at scale.
Real-time transcription with ~150ms latency and word-level timestamps. Built for live voice calls, meeting assistants, and streaming audio pipelines across 22 Indian languages + English.
Optimized models for every use case
Reliable speech recognition model optimized for general-purpose transcription
Next-generation model with enhanced accuracy and advanced features
Click a capability to see how it behaves and the request shape that turns it on.
punctuate: trueAutomatic punctuation, capitalization, and readable paragraphing — no post-processing required.
Live example
id like to check my pending fee please can you send the receipt
{
"audio_url": "https://cdn.example/call.wav",
"language": "en-IN",
"punctuate": true,
"smart_format": true
}{
"text": "I'd like to check my pending fee, please.",
"words": [
{ "word": "I'd", "start": 0.12, "end": 0.28 },
{ "word": "like", "start": 0.30, "end": 0.48 }
]
}Native pronunciation and scripts — with the ability to switch language mid-call based on the speaker.
Both. Stream audio for live transcripts during a call, or submit recordings for fast, accurate batch transcription.
Get an API key and stream your first transcript in minutes.