The end-to-end voice platform

Every layer of voice.

Agents, telephony, contact center, evals — one modern platform, end to end. You bring the models. We run everything else.

Talk to an engineer See the platform$pip install telequickcopy
scroll
01 · The call

It starts with one sample.

A scrap of sound, captured the instant it's spoken.

Which becomes a turn.

The line knows when the caller is done — and when they want back in.

A pipeline you compose.

Any ASR, any LLM, any TTS — wired as a DAG, configured per agent, swapped without a deploy.

Or one model, speech to speech.

OpenAI Realtime, Grok realtime, or Qwen Omni self-hosted on your GPUs.

OpenAI RealtimexAI GrokQwen Omni · self-hosted

Thousands of calls at once.

First-class barge-in on every one, whichever model is behind it.

Explore in detail →
02 · Agents

Agents that do things.

Not just talk. Tools run alongside the audio, mid-call.

Native tools, your tools.

route_to_skill, transfer_call — blind, warm or consult — end_chat, present_form, plus any HTTP endpoint or MCP server you point them at.

route_to_skilltransfer_callend_chatpresent_formHTTPMCP

Escalation is native.

The agent hands a live call to a human queue — hold music, claim, ring, bridge. Proven end to end on the public phone network.

And you can prove they work.

Simulated callers, barge-in timing checks, LLM-judge grading, p50/p95 first-audio rollups — built into the platform.

Explore in detail →
03 · Contact center

A call hits your number.

Carrier-grade SIP, engine-native — built from scratch, not a FreeSWITCH wrapper. Trunk in from Twilio, Vapi or straight from your carrier.

Twilio BYOCVapicarrier SBCs

Your vector answers.

Announce, collect digits, check a skill, queue — the routing model contact centers already run, rebuilt AI-native.

DID → VDN → vectorDTMF · RFC 4733queue_to_skill

The right person picks up.

Skill-based ACD with presence, five claim strategies, full ECMA CSTA CTI — ring in the browser, or on SIP desk phones if your floor runs them.

Supervisors see everything.

Live wallboards — service level, ASA, AHT, occupancy — and listen-in on any call, without touching it.

Explore in detail →
04 · Chat

The same brain answers chat.

One embeddable widget. The same agents, tools and routing that run your calls.

Forms, mid-conversation.

The agent pushes a form into the thread; the answers come back as a turn.

One human, many chats.

Capacity-aware routing offers chats on the same ring as calls — up to each agent’s limit.

Explore in detail →
05 · Providers

We sell no models.

No LLM, no ASR, no TTS of ours. Your providers, your keys — sealed at rest, per tenant.

Swap without rewiring.

Every provider behind one alias table. Change a config, not your code — in production.

The catalog is wide open.

12 LLM providers, 9 streaming ASR, 5 streaming TTS, 3 realtime speech-to-speech — one integration.

OpenAIAnthropicGoogleGroqDeepgramElevenLabsCartesiaSoniox+ more
Explore in detail →
06 · Inference

Or run models yourself.

One token off your own GPU, on your own terms.

Streaming from the first one.

Tokens leave the GPU and start arriving immediately.

OpenAI-compatible, over QUIC.

Point your existing client at the edge. HTTP/3 halves WAN time-to-first-token versus HTTP/1.

Your GPUs, your tenants.

Per-tenant model deployments on Kubernetes, metered and routed by the platform.

Explore in detail →
Why Telequick

A platform, not a model vendor.

Three commitments behind every layer.

01

We sell no models.

No LLM, no ASR, no TTS of ours in the bill. Every provider runs on your keys, sealed at rest per tenant — swap any of them in production with a config change.

02

Lowest cost to operate.

Engine-native SIP, browser-based agent audio, single-port sharding, CPU-only prompt rendering. No PBX licenses, no per-seat desk phones, no media servers to babysit.

03

No legacy in the path.

The Avaya-shape routing your ops team knows — DIDs, vectors, skills, wallboards — rebuilt on QUIC and ClickHouse instead of twenty-year-old racks. And no FreeSWITCH or Asterisk under the hood: the media engine is ours.

Built from scratch

Not a FreeSWITCH in a trench coat.

Most voice AI platforms are a thin layer over FreeSWITCH, Asterisk or Pion. Our media engine is ours, top to bottom — same boxes, same workloads, measured:

Phone calls · G.711 answer + playback

Telequickengine-native5,700 calls · 7.6% CPU
Asteriskchan_pjsip5,000 calls · 47% CPU
PionGo RTP12,000 calls · 62% CPU
FreeSWITCHsofia4,500 calls · 83% CPU

Same load, half the CPU — head to head vs Pion

5,000
calls
Telequick
7.4%
Pion
18.9%
2.0×
less CPU
10,000
calls
Telequick
18.9%
Pion
50.1%
2.2×
less CPU
14,000
calls
Telequick
27.1%
Pion
~60%
2.6×
less CPU

Same box, matched concurrent G.711 calls. ClutchCall scales roughly linearly; Pion climbs superlinearly — the gap widens as you load it.

Realtime media fan-out · CPU per viewer at 30 fps

TelequickMoQT relay0.013% CPU / viewer
PionWebRTC0.24% CPU / viewer

About 750 calls per 1% of CPU — roughly 4× Pion, 7× Asterisk, 14× FreeSWITCH. And on realtime fan-out, 17× the viewers of Pion WebRTC.

Calls: concurrent G.711, identical hyperscaler VM; efficiency = sustained ÷ peak CPU. Pion ramp-ceilinged past 12,000 without saturating (62%); Asterisk setup-failed at 5,000; FreeSWITCH was CPU-bound at 4,500. Fan-out: 2-host GCE c4-highcpu-8, 1→N relay — 400 viewers / 2 Gbps on one core at 5.3% box CPU, 0% loss.

Enterprise · High availability

A node dies. The call doesn’t.

Engine-native failover, designed in from the start — not a load balancer bolted on. Active calls re-home to a surviving node with a sub-2-second media blip.

STEP 01 · ALWAYS ON

Deterministic media homes

Every node owns one fixed RTP port per core, calls demuxed by 4-tuple. A call’s media home is just an address — re-homing it needs no per-call port allocation.

STEP 02 · ALWAYS ON

Cluster truth on Redpanda

Heartbeats and a leader lease ride a dedicated Redpanda control plane, never the media path. Call ownership is registered the moment a call is established.

STEP 03 · ON ANSWER

A durable dialog journal

On answer, everything needed to reconstruct the call — dialog state, route, sequence, remote media, codec — is journaled to Redis, off-node.

STEP 04 · ON NODE DEATH

Rehome in one re-INVITE

The leader detects the dead node, hashes each call to a survivor, and the takeover node rebuilds the dialog from the journal and recovers it with an in-dialog re-INVITE.

Failover knowledge flows over Redpanda; media never waits on the control plane. Design target: <2 s media blip on node death, in-flight calls preserved.

Integrations

Keep the framework you love.

Telequick is the platform underneath — not a walled garden on top. Run your agents on us end to end, or take transport only: your agents stay on LiveKit or Pipecat and ride our SIP core.

Your stack
Twilio · Vapi · carriers

Bring your trunks: BYOC from Twilio or Vapi, or go straight to carrier SBCs. Your numbers land on engine-native SIP either way.

LiveKit

Point LiveKit agents at Telequick trunks and DIDs — transport-only is a first-class path. Your rooms get carrier-grade telephony, ACD escalation and recording underneath.

Pipecat

Run Pipecat pipelines against the same SIP core and provider catalog — agents stay in your DAG; you gain evals, routing and human handoff.

WebRTC · WebTransport

Browser audio first-class both ways: MoQT over WebTransport — uplink and downlink — where you have it, WebRTC where you don’t.

Telequick — the platform underneathSIP core · DIDs · routing · ACD · evals · recording
# a voice agent on the phone network, in 6 lines
from telequick import Agent
a = Agent(asr="deepgram", llm="groq/llama", tts="cartesia")
a.tool("route_to_skill")          # AI → human, native
async for call in a.answer("+1..."):
    if call.bargein: a.cancel()  # instant, every provider

Nine idiomatic SDKs, generated from one RPC schema — Python, TypeScript, Go, Rust and more. The voice events plane is included, so your app hears everything the platform hears.

Read the docs
Pricing

Unlimited voice minutes.

You pay for lines, not minutes — because minutes should be free, and for us they basically are.

Get started

Bring us one call flow.

We’ll put it on the platform with you — your number, your providers, your keys — and you can judge the difference on a live call.

FAQ

Questions builders ask.

No. We sell no LLM, no ASR, no TTS. You bring provider keys — they’re sealed at rest, per tenant — or point us at models you host yourself. Our bill is for the platform, not for tokens.

Yes — two ways. Run Telequick as the full platform with your framework on top, or take transport only: your agents keep running on LiveKit or Pipecat while trunks, DIDs, routing, ACD, evals and recording ride our SIP core. Both paths are first-class.

Yes. Interruption detection lives in the platform — turn detection plus energy VAD — not in each provider’s SDK. Cancel fires the same way whether the agent is a cascaded pipeline or a realtime speech-to-speech model.

That’s the shape it’s built to. DID → VDN → vector routing, skill-based ACD with presence and claim strategies, CMS-style interval reporting, live wallboards and supervision — with AI agents and AI-to-human transfer native instead of bolted on.

Yes. The platform is multitenant SaaS by default, but the core — including self-hosted speech-to-speech inference on your GPUs — can run in your own racks.

No — voice minutes are unlimited. You pay for lines, not minutes, because minutes should be free, and for us they basically are: the media engine is cheap enough per call that metering minutes would cost more to run than the minutes are worth. You bring provider keys for models; the platform bill is capacity, not talk time.

We’re early, and we’d rather show you the platform than a rate card. Talk to us and we’ll scope it against what your current stack costs to operate.