AstrosiaLabs Talk to the lab

An engineering lab · Astrosia Technologies LLP

The hard part is the whole point.

Astrosia Labs is where we take on the work that has no obvious answer yet: our own products, and custom systems and automation for businesses that have run out of off-the-shelf options. Then we write down what we learned.

Turn budget · one spoken exchange

800 ms
Carrier leg SIP trunk in, jitter buffer settled 120 ms
Endpointing Deciding the caller actually stopped talking 140 ms
Transcription Streaming ASR, code-mixed vocabulary 130 ms
Reasoning Intent, retrieval, next action, first token 250 ms
Speech First audio frame out, streamed onward 160 ms

This is the target we design to, not a measured production average. Go past it and the caller starts talking over the agent, which is the single hardest constraint in everything we ship.

What we take on

Most of it does not have a name yet.

Some of this work becomes a product. Most of it becomes someone else's system, quietly running. The engineering underneath is the same either way.

Custom product engineering

Systems built from nothing, for a business whose problem does not have a category yet. We have shipped five of our own this way, which is the only credential that matters here.

Automation that holds up

Work that used to need a person watching it: routing, follow-up, reconciliation, reporting. Built to fail loudly and recover, because quiet automation is worse than none.

Conversational and voice AI

Agents on phone lines and in messaging threads, in the languages your customers actually speak. Latency, interruption, and handoff treated as engineering, not configuration.

Integration and platform work

Making systems that were never meant to talk to each other agree on a contract: gateways, normalisation, rate limiting, and honest error semantics.

Design systems and interfaces

Tokens, components, and patterns that survive three platforms and a year of changes. The v3 UI Kit is this practice, packaged.

The problem nobody has scoped

The most useful conversations we have start with a description of something broken rather than a specification. Bring that, and we will tell you honestly whether we are the right people.

What came out of it

Proof, not a portfolio.

These started as internal experiments and are now systems people depend on. They are here because they are the honest answer to "have you built anything hard", not because we are selling you one.

Sales infrastructure production

Astrosia CRM

Leads, WhatsApp, calling, automation, and follow-ups in one workspace, so every conversation has an owner, a next step, and a path to revenue.

The lab work here is routing and state: assigning a lead before it cools, holding conversation state across channels, and making automations that fire on evidence rather than on a timer.

Surface
crm.astrosia.com
Channels
Web forms, WhatsApp, SIP calling, email
Lab track
Conversation ownership
Open Astrosia CRM

Voice AI over telephony testing

Voiceplix

A voice agent on a phone number your company owns. It answers in under a second, speaks the caller's language, and writes the outcome back to the record.

Everything we know about latency budgets, endpointing on noisy lines, and code-mixed speech comes out of this system. India first, on licensed carrier partners.

Surface
voiceplix.com
Stage
In testing, on real lines
Lab track
Latency and speech
Open Voiceplix

Contractor marketplace production

PlaceMePal

Independent contractor work in sales, telecalling, appointment setting, and SDR/BDR roles, with preparation, interviews, and payment protection built in.

The research question is matching without a resume: what signals actually predict that someone will do well on a phone-first sales desk.

Surface
placemepal.com
Focus
Phone-first sales roles
Lab track
Matching and verification
Open PlaceMePal

Multi-platform design system live

v3 UI Kit

Design tokens, components, patterns, live template sites, and a playground. Copyable code in HTML/CSS/JS, Kotlin, and SwiftUI from one token source.

Built on the Forge palette. The open question we keep testing: how much of a component can be generated from tokens before a human has to intervene.

Surface
labs.astrosia.com/uikit
Targets
Web, Android, iOS
Lab track
Interfaces
Open UI Kit

Unified developer APIs live

v1 API Kit

One account, one API key, one response shape. Weather, currency, books, and more behind a single envelope. Upstream credentials never leave the server.

A testbed for gateway concerns we need everywhere else: authentication, rate limiting, failure isolation, and honest error semantics.

Surface
labs.astrosia.com/apikit
Stack
Next.js · Java 21 · Spring Boot 3.4
Lab track
Platform
Open API Kit

Research notes

What we learned this quarter.

All research

Voice · 29 Jul 2026 ·9 min read

The turn budget: what it takes for a phone call to feel human

A conversational turn has about 800 milliseconds before the caller notices. Here is how we spend them, and which stage we lose first when the line is bad.

Read the note

Why it matters

Latency is not a performance metric on a voice agent. It is the product. Cross the threshold and the caller starts talking over the agent, and the call is unrecoverable from there.

8 Jul 2026

Language·7 min read

Code-mixing is the default, not the edge case

Systems built for one language per conversation break on the first real Indian sales call. What it costs to treat mixed speech as the normal input.

Read

17 Jun 2026

CRM systems·8 min read

Routing a lead in under a second

Most pipeline is lost in the first hour, not the last mile. What it takes to give every inbound lead an owner before it goes cold.

Read

26 May 2026

Platform·7 min read

One envelope, many upstreams

Every upstream API fails differently and says so in its own dialect. Notes from normalising a dozen of them behind a single response shape.

Read

5 May 2026

Interfaces·6 min read

Design tokens that survive three platforms

One source of truth emitting web, Kotlin, and SwiftUI. Where generated code holds up, and the exact point where it stops being worth it.

Read

White papers

Longer arguments, with the numbers attached.

All papers

Open problems

What we have not solved yet.

A lab that only publishes wins is a marketing department. These are live, unfinished, and the reason the next release takes as long as it does.

Voice Active

Endpointing on a noisy GSM line

Silence detection tuned on clean audio mistakes a bad line for a finished sentence. We are looking for signals that separate a caller thinking from a caller done, without adding to the turn budget.

Language Active

Code-mixing inside a single clause

Speakers switch language mid-sentence and mid-word. Model routing that picks one language per turn loses meaning; picking per token costs latency we do not have.

CRM systems Active

Attribution across four channels

A lead touched by a form, a WhatsApp thread, a voice agent, and a human rep has no single owner of the outcome. We want an attribution model a sales manager will actually believe.

Interfaces Exploring

Generated components that survive review

Token-to-code generation is easy for a button and hard for a data table. We are mapping where the boundary sits across web, Kotlin, and SwiftUI targets.

Marketplace Exploring

Trust signals without a resume

For contractor sales work, past employers predict little. We are testing what a short structured call tells us that a document cannot.

Working on one of these?

If you are solving the same problem from a different angle, we would rather compare notes than duplicate the effort.

Talk to the lab

Start here

Tell us what is broken.

A build you cannot get off the ground, a process that still needs a person babysitting it, or something on the open problems list you have thought about harder than we have. The fastest route is a booked slot with the people who write the code.

Corporate office

Astrosia Technologies LLP

Tech37, 1st Floor
Plot No. 2A, Electronic City 2nd Phase, Sy-No 37
Bengaluru 560100, Karnataka, India

WhatsApp
Message us