idle
Live simulation · every screen below is interactive

The call you missed
was a customer.

Swaram is a 24×7 AI voice agent for Indian small businesses. It answers the phone, the website and the app — in Hindi, Hinglish, Odia, Tamil and more — books the appointment, takes the order, captures the lead, and hands the hard calls to a human. Start on Overview for the pitch, then play every feature for yourself.

6+ croreIndian small businesses
3Ways to reach it
<1sResponse target
₹0To start
Business — everything below adapts
Transcript language

What Swaram is

One sentence, the way we'd say it in a pitch room.

Swaram gives any Indian small business a 24×7 AI voice agent that answers the phone and the website — in the customer's own language — books appointments, captures leads, takes orders, and hands difficult conversations to a human.

Built in India, in Indian languages, for the businesses global tools ignore. Self-serve, starts free, priced for a kirana — not a call centre.

The problem, in rupees

Every missed call is a customer who called someone else. Move the sliders to your own numbers.

Calls missed per dayLunch hours, after close, second line busy12
Of those, how many would have boughtRealistic conversion, not best case25%
Average value of one customerOne visit, one order, one admission₹600
Lost every month
₹54,000
Lost every year
₹6.5L
Swaram costs
₹999/mo

How it works

Three steps, and the owner does all of them from a phone.

Step one

Tell it about your business

Photograph the rate card, paste your website, or just let the agent interview you for five minutes. No forms, no typing out a catalogue.

Step two

Pick where it answers

Your phone number, a button on your website, or a link and QR code we host for you. Same agent on all three — set up once.

Step three

It starts answering

Every call picked up, in your customer's language. Bookings and leads land in your app. Anything it can't handle rings you, with the full story attached.

What it can do today

Every card here is live and demoable. Click any of them to jump straight to that demo.

Who it's for

The long tail of 2-to-50-person businesses that lose money to missed calls and can't afford a receptionist.

Clinics & labs

Appointments, timings, reports, doctor availability. Every missed call is a missed consultation.

Kirana & wholesale

Order taking, stock checks, delivery slots, payment links. Orders arrive by phone, not by app.

Coaching centres

Batch enquiries, fees, demo classes. Admission season is entirely a phone business.

Logistics & transport

Docket tracking, ETAs, quotes. High call volume, mostly the same five questions.

Salons & spas

Bookings, price lists, stylist availability. Staff are with clients, not at the phone.

Real estate

Site enquiries, availability, visit scheduling. Leads go cold within the hour.

Repair & services

Job booking, charges, technician dispatch. The owner is usually on-site, not at a desk.

Restaurants & catering

Table bookings, takeaway orders, party enquiries. Peak calls hit exactly when nobody is free.

Pricing

A bundle of minutes, not a per-minute meter. In rupees, upgradeable in one tap over UPI.

Free
₹0
30 minutes
Every new sign-up. Enough to feel it work on real calls.
Starter
₹999
1,500 minutes
Solo or micro business. The plan most kiranas and clinics land on.
Growth
₹4,999
10,000 minutes
Busy small business with steady inbound all day.
Scale
₹14,999
40,000 minutes
Multi-location, or talk to us for something custom.
Internal note: these numbers are provisional. ₹999 for 1,500 minutes is ₹0.67 a minute, and that has to cover telephony, speech, the model, media relay, infra and payment fees before any margin. Settle it on the Economics tab before this goes on a website.

Why not just use a global tool

Ringg.ai is the closest reference point and a useful contrast — we deliberately don't fight on their turf.

Ringg.ai
Swaram
Sells to
Large companies and call teams
Indian small businesses
Main motion
Outbound — calling out at scale
Inbound — phone, website and app
Pricing
Pay-as-you-go, per minute, in dollars
Monthly plans in rupees
Languages
Many global languages
Indian-language-first, code-mixing native
Setup
Sales-led, built for big teams
Self-serve, start free, no sales call
Feel
Enterprise software
Made for a two-person shop
The line to use: "Ringg sells calling systems to big companies. Swaram gives every kirana, clinic and coaching class a second chance at the calls they miss."

Where it goes next

Be honest about the boundary. The left column is demoable today; the right is the vision, and shouldn't be sold as present tense.

Live nowShips today
Answers the phone, website and app in Indian languages
Books appointments, captures leads, takes orders
Answers from the business's own information
Hands difficult calls to a human with full context
Searchable record of every conversation
Owner dashboard, wallet and one-tap upgrade
Video agent as a premium add-on

Why this matters beyond the business case

Made in India, for India

Indian-language speech models, tuned for how India actually talks — code-mixed, accented, on a bad line. Global tools are English-first and feel foreign the moment a customer switches to Hindi.

Inclusion, not automation

This isn't replacing a call centre. These businesses never had one. It's the first time a two-person shop can answer every customer who calls.

Cross-sector by nature

One product already serving health, education, retail and logistics. That reads as broad impact rather than a single niche — which is exactly what the IndiaAI Mission is backing.

The phone rings, Swaram picks up

A customer dials the business number. The call arrives over a SIP trunk from an Indian telecom provider, terminates into a LiveKit room, and the agent joins it as a participant. Press call and watch the whole loop run — including the tool calls it makes mid-conversation.

Ready
00:00
Press ✋ while the agent is talking. That's barge-in — the customer cuts in and the agent stops instantly. Without it, this feels like an IVR, and everyone already hates IVR.
Live transcript hi-IN idle
Round-trip latency

Build on SIP, not SDKs

Exotel, Plivo, Twilio, Ozonetel and Knowlarity all speak SIP. Keep the provider as a database row, not a branch in the code — switching becomes config, not a rewrite.

Numbers take days, not minutes

Indian DIDs need KYC and provider review. Treat "number pending" as a real onboarding state and put the business live on the widget meanwhile.

Forwarding is the cheap wedge

Owners already have a number customers know. Conditional forward on busy or no-answer means Swaram catches exactly the missed calls — no new signboard.

The website that talks back

One script tag on the owner's site. The loader injects a Shadow DOM widget and opens WebRTC from the parent origin, so there's no cross-origin microphone permission to get wrong. Click the orange button on the demo site.

connecting…

Why not a plain iframe

A cross-origin iframe can't touch the microphone unless the parent page adds allow="microphone" to the tag. Every customer has to edit HTML correctly, and any CMS that strips attributes breaks it silently.

Ship a script loader plus Shadow DOM instead. CSS isolation without the permission problem, and one clean mic prompt from the parent origin.

The install, in full

<!-- paste once, before </body> -->
<script src="https://cdn.swaram.in/w.js"
        data-agent="ag_7f3c91"
        data-lang="hi,en,or" async></script>

Live in minutes — genuinely, for this module. Don't let that promise leak onto the phone-number path, where KYC takes days.

The dependency everyone forgets: TURN

On Indian mobile networks and corporate wifi, a meaningful share of WebRTC sessions can't connect peer-to-peer and must relay through a TURN server. LiveKit Cloud includes it; self-hosting means running coturn and paying relay bandwidth. Budget for it before it surprises you in production.

The app, split in two

The owner app is the real product — it's where the business lives and where every escalation lands. The customer doesn't get an app; they get a link and a QR code, because nobody downloads an app to call a kirana store.

Swaram · handoverCustomer needs youTap to take the call with full context
Scan, or tap below
No app to install. Opens in any browser.
Call
Hours
Find us

Why the customer-side super app is a trap

A customer will not download an app to call a kirana store — they'll dial, or WhatsApp. A two-sided directory needs enormous liquidity before either side turns up, and it would put Swaram against JustDial, Zomato, Swiggy, ONDC and WhatsApp at the same time as selling a voice agent. That's two hard companies stapled together.

Do this instead: give every business a hosted page, a link and a QR code. Counter, bill book, WhatsApp status. Zero downloads, zero cold start, same stack as the website widget.

What the owner app earns its place doing

Handover receiverThe owner's phone rings when the agent escalates, with the transcript already on screen. Run the logistics call to see it fire.
Business knowledgePhotograph the rate card, paste a URL, or let the agent interview the owner. Nobody types a catalogue.
Lead & booking inboxEvery captured lead and booking in one list, with the call it came from.
Wallet & planMinutes remaining, the 80% nudge, one-tap upgrade over UPI autopay.
LoginPhone and OTP. Email-and-password is the wrong door for this audience.

Every capability, playable

These are the features behind the claims in the brief. Each one is a working demo, not a screenshot.

Speaks your customer's language

The same opening line, for the same business, in every language Swaram answers in. Click any card to hear it delivered.

Before anything ships externally: have a native speaker review every one of these strings. Machine-produced regional-language copy is exactly the kind of detail an Indian audience notices immediately, and getting it wrong undoes the whole "made for India" claim.

Code-mixing is the real test

Indians don't speak one language per sentence. A global English-first model breaks on this; an Indian-language model is built for it. Here's an actual customer sentence, tokenised by language:

Detects, doesn't ask

The agent picks up the language from the first few words. No "press 1 for Hindi" — that menu is the thing customers hang up on.

Switches mid-call

If the customer switches, the agent switches. Numbers, prices and names stay intelligible either way.

Narrowband is the hard case

Phone audio is 8 kHz and noisy. The widget will always sound better than the phone line — test on the phone line, not the laptop.

Answers from your own business information

The single biggest lever on answer quality — and the thing owners will never do if it involves a form. Click a source to ingest it.

Extracted knowledge

0 facts
Nothing yet. Ingest a source above and the facts land here.

Ask it something

The agent only answers from what it actually knows, and it says so when it doesn't.

Why this has to be self-serve: more than 90% of these businesses have no software, no API and no exported catalogue. The clinic keeps a paper register; the kirana's prices are in the owner's head. If ingestion isn't as easy as taking a photo, the knowledge base stays empty and the agent stays useless.

Sign up and go live in minutes

No sales call, no demo booking, no onboarding manager. Press start and watch the clock — this is the whole journey from download to first answered call.

Time elapsed
0:00
The honest caveat: "live in minutes" is true for the website widget and the hosted QR page. A dedicated phone number needs KYC documents and provider review, which takes days. Marketing must not blur the two — put the business live on the widget while the number is pending.

A face for your business, online

The same agent, same knowledge, same tools — with a face on screen. Sold as a premium add-on, for reasons the cost bar below makes obvious.

idle
Press play to run the same conversation with the video agent.

Cost per minute, relative

Illustrative ratio, not a quote — but the shape is right.

voice
video avatar

Anam bills on credits with a small free allowance. Video minutes cost many times what voice minutes cost, which is why they can never sit inside a ₹999 bundle.

How to sell it

Add-on onlyNever bundled into a plan. Separate line item, separate meter.
Hard minute capCut off at the cap rather than billing through it. Surprise bills kill trust in this segment.
Website firstVideo makes sense on a webpage or a kiosk. It makes no sense on a phone call.
Good fitClinics, salons, real estate, showrooms — where a face builds trust before a visit.

Hands the hard ones to your team

The agent knows what it can't do. When it escalates, it passes the whole conversation across so the customer never repeats themselves. Press play to walk the fallback chain — including what happens when the owner doesn't pick up.

What gets passed across

Full transcriptEverything said, in the original language plus a translation.
Why it escalatedThe specific thing the agent couldn't decide or wasn't allowed to.
Customer detailsNumber, name, and anything captured mid-call.
Suggested actionWhat the agent would have done if it had permission.
Never a dead end. If every step of the chain fails, the customer still gets a callback promise and the owner still gets the lead. A dropped escalation is worse than never answering.

Rules, not vibes

Each vertical declares what forces a handover — a clinic never gives medical advice, logistics never promises a priority slot, coaching never negotiates fees.

Angry is a trigger

Repeated frustration, a raised voice, or an explicit "let me talk to a person" escalates immediately. Arguing with an upset customer is the fastest way to lose them.

Warm, not cold

The agent tells the customer it's connecting them and why. Silence during a transfer reads as a dropped call.

Every conversation saved and searchable

Search across every call this business has taken — transcripts, outcomes, phone numbers. Type anything, or try one of the suggestions.

Why this matters more than it looks: the search index is also the product's best insight tool. The questions customers ask most are the FAQ the owner should fix, and the calls that ended without an outcome are the leads that leaked.

See your results at a glance

What the owner opens the app to check. Deliberately four numbers, not forty — this is a shopkeeper's dashboard, not an analyst's.

Calls by hour

Where calls end up

The funnel the owner actually cares about.

Most asked questions

Fix the top three on your website and the call volume drops.

What we deliberately don't show yet

Call quality scoringOn the roadmap. Don't claim it.
Conversion attributionNeeds the owner's sales data, which they don't have digitally.
Sentiment chartsImpressive in a demo, useless to a kirana owner. Cut it.

Start free, upgrade in one tap

Drag the slider to burn through the free minutes and watch what the owner sees. The nudge fires at 80%, not at zero — running out mid-call is how you lose a customer.

Free plan · 30 minutes0 used
30 minutes left80% nudge ↑
Minutes usedDrag to simulate a busy week
You've used 80% of your free minutes

At your current pace you'll run out in about two days. Upgrade now and nothing gets interrupted.

Why bundles, not a meter

A per-minute meter makes a shopkeeper anxious about every call — the exact opposite of what we want. A bundle is a known number they've already paid, so they stop counting and let the agent work.

Payment realities in this segment

UPI autopayEssential. Card-on-file recurring fails constantly here.
Wallet top-upFor owners who'd rather pay as they go than commit monthly.
Never hard-stopGoing over should degrade, not disconnect. Cutting a live call to enforce a limit is unforgivable.
Rupees, alwaysDollar pricing reads as "not for me" instantly.

Your business, your data

A voice agent hears things — names, phone numbers, health complaints, addresses. Being specific about what happens to that is not optional, and under India's DPDP Act it's law.

What we store

TranscriptsYes — that's the searchable record the owner is paying for.
Audio recordingsOptional, off by default, retention set by the owner.
Customer numbersYes, they're the lead. Visible only to that business.
Business knowledgeYes, scoped to that business alone. Never pooled across customers.

What we commit to

India residencyData stays in Indian regions. Also a latency win, not just compliance.
No cross-trainingOne business's conversations never train anything another business touches.
Consent on recordCalls announce they're recorded, in the customer's language, before anything is captured.
Deletion means deletionOwner deletes, it's gone — including from backups within the stated window.
Don't put a number on it until it's true. No uptime percentage, no accuracy percentage, no "bank-grade encryption" unless someone can point at the audit. In this market a broken security claim is unrecoverable — earn the certifications, then say them.

Three doors, one room

This is the decision that keeps Swaram buildable. LiveKit has a SIP bridge, so a phone call terminates into a room as just another participant — identical to a browser visitor or an app user. One agent worker serves all three. Build it any other way and the STT→LLM→TTS loop gets written three times and drifts three ways.

Phone numberSIP trunk · Exotel / Plivo Website widgetWebRTC · Shadow DOM App / QR linkIn-app VoIP · hosted page Session & media layer LiveKit rooms · SIP bridge · TURN relay · recording Agent runtime VAD · STT · LLM · TTS · barge-in · tool calls · handover Clinic pack Kirana pack Logistics pack Coaching pack

The pipeline, one turn at a time

Press play to walk a single customer utterance through the runtime. The budget is under one second from the moment they stop talking to the moment they hear a reply.

total —

A vertical is four things, not a fork

LayerWhat changes per industryCurrent pack
Adding "salon" should be a config PR, not a sprint. The runtime never changes — only the prompt, the tool schema, the tables and the owner screens.
The hard truth about tool calling: more than 90% of these businesses have no API and no software at all. So Swaram has to own the system of record — build the calendar, build the catalogue — and treat integrations with Practo or Vyapar as a higher-tier feature for the minority who have them. Architect it the other way round and you ship a booking engine with no data in it.

Dependencies — click one to break it

Every box below is something outside our control. Toggle any of them to failing and watch which modules go down, degrade, or survive. This is the map worth arguing about before writing code, not after an outage.

Phone
Operational
Inbound calls answered normally.
Website widget
Operational
Website visitors connect normally.
App & QR
Operational
In-app and hosted-page calls working.

Owner-side dependencies

LoginPhone and OTP. Emails get forgotten and passwords reset weekly in this segment.
Business knowledgePhoto of the rate card, a URL, or a five-minute onboarding call. Never a form.
Number KYCBlocks phone go-live for days. Ship them live on the widget meanwhile.
Tool / API accessThey don't have one. Swaram owns the data.
Handover reachabilityApp push → owner mobile → WhatsApp summary. Never a dead end.
Payment mandateUPI autopay, or ₹999 recurring silently fails.

Design rules that fall out of this map

Two of everythingTwo telephony providers, a fallback model, a fallback TTS. Behind one interface each.
Degrade, don't dieTools unavailable? The agent still answers and takes a message — a far better call than a busy tone.
Video is an add-onAvatar minutes cost many times voice minutes. Never inside ₹999, and hard-capped.
Colocate in IndiaEvery network boundary is latency you can't get back.

The number to settle before launch

Starter is ₹999 for 1,500 minutes — ₹0.67 a minute, covering telephony, speech, the model, media relay, infrastructure and payment fees before a single rupee of margin. Drag in real vendor quotes and see whether the plan survives.

Plan

Monthly priceWhat the owner pays₹999
Included minutesBundle size1,500
UtilisationShare of the bundle actually used75%

Cost per minute

TelephonySIP inbound, India₹0.30
Speech (STT + TTS)Sarvam₹0.25
ModelGemini, per conversation minute₹0.08
Media + infraTURN, workers, storage₹0.05
Payment feesGateway on the subscription2.0%
Revenue per used minute
Cost per minute
TelephonySpeech ModelInfra Gross margin

Per business, per month

Revenue
Minutes actually used
Variable cost
Payment fees
Gross profit
Gross margin
The defaults are placeholders, not quotes. Get real numbers from Exotel, Sarvam and Google and put them in before this pricing table goes on a website. If cost lands above revenue, we've built a business that loses more money the better it sells — and repricing after launch is far more painful than pricing correctly now.