Knowledge base
Everything you need before you pick a vendor — or build it yourself.
Two audiences use this directory. One wants to hire a company to run voice calling. The other wants to build the engine. Both need the same underlying picture: what the stack is, which layer decides what, and where the money and the time actually go.
For buyers
What “live in 5 minutes” means
The five phases between a demo and production, honest day ranges for each, and ten pitch claims translated into the question that settles them.
Read →
For builders
How the stack works
Six layers, what each one does, what you have to build at every step, and the mistake people make there.
Read →
For buyers and builders
What it actually costs
A cost model per layer with every rate editable, so you can put your own quotes in and see what moves.
Read →
For everyone
Hard facts
Things that are true regardless of vendor, and that people repeatedly discover too late.
Read →
For builders
Resources
Open source, documentation and standards for every layer, grouped by where they sit in the stack.
Read →
Articles
Written by us, not a link roundup
- Buyers & builders9 min read
The Hinglish problem: why your voice bot will fail on real Indian callers
Supporting Hindi and English is not the same as following a caller who switches between them mid-sentence. What breaks, why, and how to test for it before you buy.
Read →
- Buyers & builders11 min read
DLT, DND and outbound voice bots in India: what the obligations actually are
A plain-language primer on the regulatory layer under automated outbound calling in India — who carries the obligation, what it means for a pilot, and the questions to settle in writing.
Read →
- Buyers10 min read
Per-lead pricing: the only model where your vendor wants what you want
Per-lead pricing aligns incentives better than per-minute — and creates a definition problem that decides whether the deal works. How to write the definition before you sign.
Read →
The stack, at a glance
01
Telephony
Gets the call in and out
02
Speech to text (STT/ASR)
Turns caller audio into words
03
Language model
Decides what to say next
04
Text to speech (TTS)
Speaks the reply
05
Orchestration and turn-taking
Runs the conversation loop
06
Recording, storage and analytics
Tells you what happened
6
stack layers documented
13
hard facts, vendor-independent
24
curated resources
3
articles