Ship voice agents for anything you can imagine.
The voice-AI infrastructure layer. Compose any model, voice and carrier into real-time phone, web, chat & WhatsApp agents — in a few lines of code. A REST API, five SDKs, webhooks, tools & MCP. Your stack, your brand, no lock-in.
Free starter credits · No card to explore · REST API + 5 SDKs · BYO model & carrier
Plug in the best of every layer
barge-in latency — interrupt mid-sentence
official SDKs · Web, React, RN, Node, Python
carriers + native SIP / BYOC
LLM · STT · TTS providers to compose
If you can describe the call, you can build it
Telenow isn’t a fixed product — it’s a set of swappable building blocks. Pick a model, a voice, a carrier, your tools and your data, and compose them into whatever the moment calls for.
Any model
OpenAI, Anthropic, Gemini, Groq, Bedrock — or your own OpenAI-compatible endpoint or full agentic backend.
Any voice
ElevenLabs, Cartesia, Sarvam, Rime, Polly and more — pick a voice, tune the persona, or clone your own.
Any transcription
Deepgram, Sarvam, Soniox — sub-300ms partials and instant barge-in so callers can interrupt mid-sentence.
Any carrier
6 CPaaS providers (Twilio, Plivo, Vonage, Exotel, Vobiz) or a native SIP trunk. BYOC — your trunks, your rates.
Tools & MCP
Call any HTTPS endpoint or MCP server mid-call. Read and write to the systems you already run, in real time.
Knowledge (RAG)
Ground answers in your PDFs, docs and URLs; the agent retrieves and cites your content as it talks.
Caller memory
Recognise repeat callers across calls with a rolling summary and a facts ledger, with a TTL you control.
Flows & code
Branch with a visual flow builder, or drop into a sandboxed JS code node when you need real logic.
Every channel
Phone, web, chat & WhatsApp from one agent — same brain, tools and memory across every surface.
From npm install to a live call in minutes
No boilerplate, no telephony plumbing. Drop in an SDK, point it at an agent, and you’re on a real-time voice call — in the browser or out to any phone.
Mic in, voice out, live transcript — a few lines of client code.
import { TelenowCall } from '@telenow/client';
const call = new TelenowCall({
publicSlug: 'YOUR_AGENT_SLUG', // agent's public slug (Publish tab)
baseUrl: 'https://api.telenow.ai',
onTranscript: (line) => console.log(`${line.role}: ${line.text}`),
onState: (state) => console.log('call:', state),
});
await call.start(); // prompts for mic, connects, the agent greets
// call.stop(); // hang upnpm i @telenow/client · zero dependencies, runs in any browser.
One server-side request dials out and the agent takes it from there.
import { Telenow } from '@telenow/server';
const telenow = new Telenow({ apiKey: process.env.TELENOW_API_KEY });
const call = await telenow.calls.create({
agentId: 'agent_123',
to: '+919876543210',
});
console.log('calling:', call.sessionId);npm i @telenow/server
Try a live agent — four ways
No signup. Talk in your browser, call our number, or have the agent call your phone — and each one comes with the SDK code to build it yourself.
Every missed call is a customer walking away.
Phone support breaks exactly where it matters most — after hours, at scale, in your caller’s language — and the vendors meant to fix it just lock you in.
Calls go unanswered
After-hours, lunch rushes and hold queues quietly send your callers — and their money — straight to your competitor.
Phone staff don’t scale
Hiring, training and replacing agents is slow and expensive, and the headcount never quite matches the call volume.
Vendors hold you hostage
Most platforms force their model, their carrier and their brand on you, then bury the real cost in one opaque per-minute rate.
Callers can’t be understood
When your agents speak only one language, every caller in another is left frustrated, switching to English, or hanging up.
Infrastructure, not a walled garden
Most platforms hand you their model, their carrier, and their brand. Telenow hands you the primitives instead — and gets out of your way.
Human + AI on one line
AI answers, qualifies and resolves, then warm-transfers to your team on the same number — and your agents can dial out manually too. No silos between bot and human.
Bring your own brain
OpenAI, Anthropic, Gemini, Groq, Bedrock — or your own OpenAI-compatible model (Custom LLM) or full agentic backend (Custom API). Zero model lock-in.
Bring your own carrier
Run on your own Plivo, Twilio, Vonage, Exotel or Vobiz account (BYOC) — or a native SIP trunk. Your trunks, your rates; we run the real-time voice pipeline.
Transparent pricing
Component-level cost — LLM + STT + TTS + telephony + platform fee, itemized in your currency. No opaque bundled minute.
A platform, not an API
Numbers + compliance, softphone dialer, campaigns, knowledge bases, integrations, recordings, analytics, teams — all included.
Developer & business friendly
A full REST API + webhooks + 5 official SDKs for engineers, and a no-code agent builder + dashboard for everyone else.
Everything you need, in one place
From the no-code builder to compliance, analytics, and the developer API — the whole stack, not just a voice API.
No-code agent builder
Design agents visually with live cost & latency estimates — every save is versioned, restore or A/B-compare any time.
Knowledge bases (RAG)
Upload PDF / DOCX / CSV or point at a URL; agents retrieve and cite your content mid-conversation.
Integrations & MCP
CRMs, calendars, sheets, payments, forms, support — plus any MCP server or your own HTTPS endpoint.
Numbers & compliance
Search, buy, port or bring numbers across carriers, with in-app DLT / regulatory compliance flows.
SIP trunking & BYOC
Run on your own Plivo/Twilio/Vonage/Exotel/Vobiz account, or a native SIP trunk — G.711, DTMF, IP/digest auth.
Outbound campaigns
Bulk CSV upload, 1–50 concurrency, retries, AMD, calling windows & DNC suppression with live progress.
Caller memory
Agents recognise repeat callers across calls — rolling summaries and a facts ledger with a configurable TTL.
Post-call analysis
Auto summaries, sentiment, disposition, action items, plus up to 30 custom fields and QA-rubric scoring.
Live ops & wallboard
Real-time KPIs, active calls and team presence, with listen-in monitoring of any live call.
Warm transfer & softphone
Hand off to a teammate or external number on any carrier with auto-resume, or dial manually from the softphone.
Spend controls
Prepaid credits or postpaid billing with soft & hard spend caps and per-org concurrency limits — full cost control, no surprises.
Developer platform
Full REST API, signed webhooks, the Chat & web-call APIs, and official SDKs for Web, React, React Native, Node & Python.
One agent, every channel
Build once. Your agent shows up on the phone, in the browser, in chat, and on WhatsApp — with the same knowledge, tools, and memory.
Phone
Inbound & outbound PSTN calls on any of 6 carriers or your own SIP trunk.
Web voice
Browser voice via an embeddable widget or the WebSocket / web-call API.
Chat
Drop the same agent into any text surface over the REST Chat API.
Two-way WhatsApp via 5 providers — or a built-in paired number, no external account.
Connects to the tools you already run
Let your agent read and write to your CRM, calendar, sheets, payments, and support tools — during the call.
50+ integrations, plus any MCP server and any HTTPS endpoint your agent can call.
Explore all integrationsLive in four steps
Build your agent
Pick a model, voice and language in the no-code builder — or bring your own LLM or full agentic backend.
Connect knowledge & tools
Add a knowledge base, your integrations and MCP servers, and function-calling tools to your own APIs.
Add a number or channel
Buy or bring a number, or publish to web, chat and WhatsApp. Set compliance and routing.
Go live & improve
Publish, monitor live calls, and review post-call analytics — then iterate with versioned agents.
Built to scale with the enterprise
A Rust real-time core, horizontal scaling, instant barge-in, and per-org concurrency controls — engineered for reliability at volume.
Enterprise-grade by default
Encryption, isolation, audit logging, and telephony compliance built into the platform — not bolted on.
Encryption everywhere
Secrets, carrier credentials and API keys stored AES-GCM encrypted; TLS in transit; HMAC-signed webhooks.
Org isolation & RBAC
Strict per-organization data isolation with role-based access for every member.
Full audit log
Every mutating action is logged and filterable, with CSV export for your records.
Telephony compliance
In-app DLT / regulatory flows, TCPA calling windows, and org-wide Do-Not-Call enforcement.
BYO keys & carrier
Bring your own model keys and carrier accounts — provider usage is billed directly to you.
SSO ready
OIDC single sign-on for enterprise teams. DPA available on request.
Start where you are — pay only for what you run
Three ways to run Telenow, all on the same component-level meter. No fixed plan tax — the exact per-minute cost is shown by the live calculator below.
Self-serve
Free credits, then pay-as-you-go
For builders and small teams who want to ship an agent today.
- Free starter credits — build and test a real agent before you pay
- Prepaid wallet (1 credit = ₹1) via Razorpay, hard cut-off at zero
- No-code builder for web, chat & WhatsApp in minutes
- Buy or bring a number, add knowledge bases, integrations & MCP
- Component-level per-minute pricing, itemized in your currency
Growth
Usage-based, postpaid
For teams scaling outbound and inbound operations.
- Everything in Self-serve, on postpaid usage invoicing
- Outbound campaigns — concurrency, retries, AMD, calling windows & DNC
- Soft & hard spend caps plus per-org concurrency limits
- Teams, roles, departments, call routing & warm transfer
- Live wallboard, post-call analysis, QA scoring & usage analytics
Enterprise
Custom
For larger teams that need SSO, compliance and dedicated support.
- Bring your own carrier (BYOC / native SIP) and your own model keys
- OIDC SSO, org isolation & RBAC, full audit log with CSV export
- DPA on request, telephony compliance (DLT, TCPA windows, DNC)
- Dedicated support, SLA & priority response
- White-glove onboarding & volume pricing
See how Telenow compares
Most platforms hand you their model, their carrier and their brand. Here’s where Telenow draws the line differently — judge for yourself.
Built for real conversations
From the first hello to a warm human handoff.
Inbound support
Answer FAQs, triage, and resolve common requests 24/7 — grounded in your knowledge base.
Outbound campaigns
Reminders, renewals, and surveys at scale, within compliant calling windows.
Lead qualification
Qualify and route inbound leads, capture details, and book the meeting.
Appointment booking
Schedule, confirm, reschedule — warm-transfer to a human when needed.
After-hours overflow
Catch every call when your team is offline; hand off or take a message.
Internal helpdesk
IT/HR self-service over voice and chat, embedded in your tools.
Built on infrastructure you already trust
We don’t ask you to bet on us — you bet on the model, carrier and voice vendors you already know. Telenow is the platform that ties them together, on your brand.
LLM · STT · TTS · telephony
- Full REST API — provision agents, place calls, manage everything
- Official SDKs for Web, React, React Native, Node & Python
- Signed HMAC webhooks: call.ended, recording.ready, transcripts & tool calls
- Web-call WebSocket API + a text Chat API for any surface
- Custom LLM (OpenAI-compatible) and Custom API (your own agent)
- Function-calling tools to your HTTPS endpoints + MCP servers
- No-code agent builder with live cost & latency estimates
- Buy or bring numbers, run the compliance flow, and go live
- Softphone dialer, call history, recordings, transcripts & AI insights
- Outbound campaigns with calling windows, AMD & DNC suppression
- Team roles, departments & call routing
- Usage, analytics, wallboard & audit logs
Questions, answered
Everything teams ask us before they build. Still curious? Book a demo.
Pricing & billing
Transparent, component-level per-minute pricing: language model + speech-to-text + text-to-speech + telephony + platform fee, itemised in your currency. A softphone-only call is just the carrier minute plus any platform fee. Use the live calculator above to see your exact stack.
Both. Top up a prepaid wallet (1 credit = ₹1) via Razorpay with a hard cut-off at zero, or run on postpaid usage invoicing. You also get soft and hard spend caps and per-organization concurrency limits to control cost.
Yes — explore the live demo with no credit card, and self-serve signup comes with free starter credits so you can build and test a real agent before you commit.
No long-term lock-in. You can export your call history (CSV) and recordings (signed URLs) at any time, and release numbers when you leave.
Security & data
Yes. Secrets, carrier credentials and API keys are stored AES-GCM encrypted, all transport is over TLS, and outbound webhooks are signed with HMAC-SHA256.
Only members of your organization, governed by role-based access. Data is strictly isolated per organization and every mutating action is captured in an audit log.
No. Your conversations, recordings and knowledge bases are yours and are not used to train models.
Recording storage is configurable, and caller-memory has a TTL you set (from 1 day to several years). You can export or delete your data on request.
Compliance
In-app compliance flows for Plivo and Twilio (document submission and regulatory bundles), TCPA calling windows on campaigns, and an org-wide Do-Not-Call list enforced at both upload and dial time, in both directions.
Yes — regulatory bundles and per-provider compliance applications are handled inside the app, including India DLT.
We follow GDPR-aligned data handling with a DPA available on request, and operate with encryption, access control and audit logging throughout. Formal certifications are on our roadmap — talk to us about your specific requirements.
Capabilities
Multilingual voices across 30+ languages — including Hindi and 10+ Indian languages (Sarvam, Smallest.ai), Indian-English accents, and global languages via ElevenLabs, Amazon Polly, LMNT and Rime. Custom voice cloning is supported via ElevenLabs.
A Rust real-time core with instant, configurable barge-in (callers can interrupt mid-sentence), sub-300ms STT partials and ultra-low-latency TTS. Per-call STT / LLM / TTS / server latency is measured and visible to you.
Yes. Bring your own LLM (OpenAI/Anthropic/Groq/Azure/Bedrock/OpenRouter, or any OpenAI-compatible endpoint), a full custom agentic backend, and your own carrier (Plivo/Twilio/Vonage/Exotel/Vobiz or native SIP). BYO keys are billed directly by the provider.
CRMs (HubSpot, Salesforce, Zoho, Intercom), calendars (Google Calendar, Calendly), Sheets & Airtable, payments (Razorpay, Stripe, PayPal), forms (JotForm, Typeform, Tally), Freshdesk, WhatsApp, automation (Zapier, Make, n8n, viaSocket), any MCP server, and custom function-calling tools to your own APIs.
Getting started
Yes, self-serve signup is available (email or WhatsApp OTP), with free starter credits. Enterprise teams can also request white-glove onboarding.
A sandboxed, temporary demo organization with isolated data that auto-expires in 24 hours — explore the full product with no commitment.
Minutes for a self-serve agent on web or chat; a little longer for phone numbers that require compliance approval, which we guide you through in-app.
A note from our founder
I spent years watching teams get boxed in by voice AI — someone else’s model, someone else’s carrier, a bundled per-minute price you could never actually read. So we built Telenow the other way around: your model, your carrier, your brand, with every cost itemized down to the cent. Voice and chat are too important to rent on someone else’s terms. We’re a small team shipping fast, and we’d genuinely love to build the next part of this with you.
Share your link and earn a percentage of every referred account’s usage — for as long as they stay.
Build voice AI on your own stack
Start free with starter credits and ship a real agent today — or book a 30-minute demo and we’ll spin one up for your use case.
No card to explore · Cancel anytime · No long-term lock-in