Resources
Automated calling in India, written by the people building the carrier path underneath it. Measured numbers where we have them, and the regulation stated as it is rather than as it is usually repeated.
How a voice AI pipeline actually works, end to end
What happens between a caller finishing a sentence and an agent answering it: voice activity detection, streaming speech recognition, the language model, speech synthesis, and the four places it usually breaks.
Read the articleUse cases
What automated calling is actually used for in India — order confirmation, lead qualification, renewals, reminders — and how each one is built.
- Use case
COD order confirmation calls: cancelling the bad orders before you ship them
Cash-on-delivery drives most Indian e-commerce and most of its returns. How an automated confirmation call works, what it asks, what it costs per order, and where the compliance line sits.
Read - Use case
Qualifying real estate leads by phone, automatically
Portal enquiries go cold in minutes and most of them are unqualified. How an automated call grades a lead in 90 seconds — and why RERA makes a scripted agent safer than a keen human closer.
Read
Voice AI engineering
How a voice agent works end to end: the speech-to-speech pipeline, where the latency goes, and what we measure in production.
- Article
How a voice AI pipeline actually works, end to end
What happens between a caller finishing a sentence and an agent answering it: voice activity detection, streaming speech recognition, the language model, speech synthesis, and the four places it usually breaks.
Read - Article
Voice AI latency in India: the numbers we measure in ap-south-1
A stage-by-stage latency breakdown of a production voice agent running in Mumbai — where every millisecond of a 1,220ms reply goes, and why in-region matters more than model choice.
Read
India compliance
TRAI, TCCCPR and DLT for automated voice calls — what the rules require, what they do not, and what an audit trail has to contain.
Looking for the API?
These pages explain the problem space. The developer documentation explains the product — endpoints, webhooks, and how to place a call.