Now in private beta · onboarding teams

Voice agents that pick up when your team can't.

Talknex answers inbound calls, qualifies callers, and books appointments straight into your calendar. Responses land in under 600ms, with natural prosody and clean interruption handling.

~580ms
Median round-trip latency
30+
Languages supported
24/7
Always-on coverage
Private beta
Onboarding teams now
talknex.ai — live call Live
A
Aria · Sales Agent
Connected to +1 (415) 555 0192 · 00:42
Calling tool: book_appointment...
Calls this session
Live preview
Sample dashboard
Sentiment
Positive
Latency
580ms

Currently in private beta

Built for clinics, brokerages, and support teams that can't afford to miss a call. We're onboarding a small group of early teams — request access to join.

Capabilities

A complete platform — not a wrapper

Four pillars, one stack. Build, deploy, and scale autonomous voice agents without stitching together five vendors.

Real-time voice

Conversations indistinguishable from a human.

Streaming Deepgram STT, GPT-4o reasoning, and ElevenLabs Turbo TTS pipelined together for sub-600ms responses with natural prosody and graceful interruption.

580ms median round-trip
Real-time voicev3.2

WhatsApp + SIP

Reach customers on every channel they answer.

One agent, every channel: PSTN voice via Twilio, WhatsApp Business, and direct SIP trunking with carrier portability. Bring your own number or buy in-app.

30+ languages supported
WhatsApp + SIPv3.2

Multi-agent system

Spin up an entire workforce, not just an IVR.

Compose specialised agents with shared memory, hand off mid-call, and orchestrate workflows across departments with deterministic routing rules.

Scale concurrent lines on demand
Multi-agent systemv3.2

Knowledge-grounded

Answers backed by your real source of truth.

Drop in PDFs, crawl your site, or sync Notion. pgvector RAG keeps responses grounded — no hallucinations, with citations exposed in transcripts.

pgvector + 1536-dim embeddings
Knowledge-groundedv3.2

Live demo

Hear our agents in the wild

Pick a persona to preview. Sign up to talk to a live agent on your number, on your data, in your voice.

A
Aria
AI Receptionist
Play sample
Thanks for calling the clinic, this is Aria. How can I help you?
I want to reschedule my appointment for next week.
Of course — I'll pull up your record now and find the next open slot.
Books and reschedules appointments
S
Sage
Sales SDR
Play sample
Hi, this is Sage. Is now a good time for a quick minute?
Sure, go ahead.
Quick context — we help teams qualify inbound leads and book meetings automatically. Mind a couple of questions?
Qualifies leads and books meetings
C
Cas
Customer Support
Play sample
My order hasn't shipped yet. Order #82144.
Let me check that for you... I see #82144 just left the warehouse this morning. ETA Friday.
Oh, perfect.
Resolves tier-1 questions
N
Nova
Booking Specialist
Play sample
I have 2:15pm or 3:45pm Tuesday. Which works?
3:45 please.
Booked. You will get a confirmation text in a few seconds.
Confirms slots in real time
Sign up to talk to a live agent — no credit card required.

How it works

Live in three steps

From signup to taking real calls in less than 15 minutes — no engineers required.

01

Create your agent

Configure persona, voice, system prompt, and connect your knowledge base in minutes.

02

Connect a number

Provision a Twilio number or plug in WhatsApp / SIP with one click.

03

Go live 24/7

Your agent answers, books, transfers, and reports — while you sleep.

For developers

An API your team will actually enjoy.

REST + WebSocket. Type-safe SDKs for Node and Python. Webhooks for every call event. Spin up an agent, place calls, and stream transcripts with one import.

  • Streaming transcripts over WebSocket
  • Webhooks for every call event
  • Function calling for tools
  • Idempotent retries built-in
Read the docs
# Place a call with a Talknex agent
curl -X POST https://api.talknex.ai/v1/calls \
  -H "Authorization: Bearer $TALKNEX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agentId": "agent_aria_8f3c",
    "to": "+14155550192",
    "metadata": { "leadId": "lead_4421" }
  }'

Performance

Built for low-latency conversations

Streaming STT, GPT-4o, and Turbo TTS are pipelined to keep median round-trip latency around 580ms — under our 600ms target.

Median round-trip latency, measured on our own pipeline

Streaming STT

Deepgram emits transcript deltas every ~120ms — we feed GPT before the caller finishes speaking.

Sub-tokenized routing

Predictive intent classification skips full inference for short responses like confirmations.

ElevenLabs Turbo TTS

Audio chunks stream back before the LLM finishes, so callers hear the first words while the response is still being generated.

Use cases

Built for every industry

From clinics to brokerages, teams use Talknex to handle the calls they used to miss.

Healthcare
Patient intake, refills, and appointment reminders.
Intake & remindersLearn more
Sales
Outbound qualification, follow-ups, and meeting booking.
Qualify & bookLearn more
Customer Support
Tier-1 questions with seamless human handoff.
Deflect & transferLearn more
Real Estate
Lead qualification and live tour scheduling.
Qualify & scheduleLearn more
Hospitality
Reservation handling, concierge, and front-desk overflow.
24/7 coverageLearn more
Logistics
Shipment tracking, ETA updates, and dispatch routing.
Track & updateLearn more

Who it's for

Built for teams that can't miss a call

Talknex is currently in private beta. We're working closely with a small group of clinics, brokerages, and support teams to get the details right before opening up.

Clinics & front desks

Answer patient calls, take intake details, and book or reschedule appointments after hours.

Brokerages & agents

Qualify inbound leads the moment they call and schedule tours without playing phone tag.

Support teams

Resolve common tier-1 questions instantly and warm-transfer anything that needs a human.

What teams are saying

Built for teams that live on the phone

We went from missing almost half our after-hours calls to zero. Talknex books appointments straight into our calendar, and the front desk finally has room to breathe.
HW
Hannah Whitfield
Practice Manager, Maple Ridge Family Dental
It qualifies every inbound lead the second the phone rings, so our agents only spend time with people who are actually ready to tour. Like an SDR that never sleeps.
MD
Marcus Devlin
Managing Broker, Beacon & Park Realty
Tier-1 ticket volume dropped by about a third in the first month. Most callers can't tell it isn't a person until we tell them.
SM
Sofia Marchetti
Head of Support, Tidewave

Why Talknex

One stack, batteries included

The capabilities you need to run production voice agents — without stitching together five vendors.

CapabilityTalknexWhat it means
Median round-trip latency~580msUnder our 600ms target on identical utterances.
Voices (ElevenLabs)HundredsPlus custom voice cloning on paid plans.
Languages30+Speech-to-text and text-to-speech across major locales.
Calendar bookingBuilt-inbook_appointment writes straight to Google or Outlook.
Telephony channelsVoice, WhatsApp, SIPVia Twilio — bring your own number or buy in-app.
Knowledge base (RAG)Includedpgvector embeddings keep answers grounded in your docs.
Human handoffBuilt-intransfer_to_human warm-transfers the live call.
Streaming SDK + webhooksIncludedREST + WebSocket transcripts and a webhook for every event.

What you get

Built on a real-time stack

The product facts that matter when you put a voice agent on a live phone line.

~580ms
Median latency
under our 600ms target
30+
Languages
STT + TTS coverage
24/7
Always on
answers around the clock
RAG
Grounded answers
pgvector knowledge base
Tools
Function calling
book & transfer built-in
API
REST + WebSocket
webhooks for every event

Security & compliance

Enterprise-grade from day one

SOC 2
Type II in progress
HIPAA-ready
BAA available
GDPR
EU data residency
E2E encryption
TLS 1.3 + AES-256
pgvector RAG
Org-scoped embeddings

Pricing

Pay only for what you use

No fixed tiers. Pick a billing mode and pay by the minute — bring your own keys, or let us run the whole stack.

Bring Your Own Keys

$0.05/min

Plug in your own provider keys. No monthly base. Your first concurrent line is free, then $20 per additional line.

  • $0 monthly base
  • $0.05 per minute
  • First concurrent line free
  • $20 per extra line

Fully Managed

$99/mo + usage

We run the infrastructure end to end — no keys to manage. $99/mo base plus $0.12 per minute and $45 per concurrent line.

  • $99 monthly base
  • $0.12 per minute
  • $45 per concurrent line
  • Zero provider keys to manage

Integrations

Plays nicely with your stack

Native integrations for the tools teams already use — and a webhook for everything else.

Twilio logo
Twilio
Google Calendar logo
Google Calendar
Microsoft Outlook logo
Microsoft Outlook
HubSpot logo
HubSpot
Salesforce logo
Salesforce
Slack logo
Slack
Zapier logo
Zapier
Make logo
Make
Notion logo
Notion
Gmail logo
Gmail
W
Webhooks
LemonSqueezy logo
LemonSqueezy

FAQ

Got questions?

Answers to the things teams ask before they ship their first agent.

How quickly can I deploy a voice agent?
Most teams ship their first agent in under 15 minutes — pick a voice, paste a system prompt, connect a Twilio number, and you are live.
What languages and voices are supported?
Out of the box we support 30+ languages and hundreds of voices through ElevenLabs, plus custom voice cloning.
Will my agent sound like a robot?
No. We pipeline streaming Deepgram STT, GPT-4o, and ElevenLabs TTS so latency stays under 600ms with natural prosody and interruption handling.
Can agents book appointments and transfer to humans?
Yes. Both are built-in tools. Agents call book_appointment to write to your calendar, and transfer_to_human to warm-transfer the live call.
How does pricing work?
Pricing is purely usage-based — no fixed tiers. Choose Bring Your Own Keys ($0.05/min, first concurrent line free, $20 per extra line, no monthly base) or Fully Managed ($99/mo base + $0.12/min + $45 per concurrent line). You only pay for what you use, and you can switch modes anytime.
Is my data secure?
All data is encrypted in transit and at rest. Recordings, transcripts, and embeddings are scoped to your organization and never used to train shared models.
Do you support WhatsApp and SIP?
Yes — WhatsApp Business and SIP trunking are supported. Bring your own carrier or use ours.
How am I billed for usage?
You are billed per minute of call time plus any concurrent lines, based on the mode you pick. There are no minute caps to hit — every minute is metered at a transparent per-minute rate, and you can set hard caps in the dashboard.

Voice AI moves fast. Keep up.

One short email a month — product updates, benchmarks, and the occasional teardown.

Ready in 15 minutes

Stop missing calls.
Start scaling conversations.

Join the teams using Talknex to answer every call, qualify every lead, and book every appointment — automatically.

No credit card required · Cancel anytime
Talknex.ai — AI Voice Agent Platform