Architecture

Everything underneath a voice agent, built as one system.

Xebit is nine components that ship as one platform: Agent SDK, Bridge, Agent Server, speech pipeline, orchestration, scheduling and campaigns, observability, control plane and SIP gateway. The same artefact runs on Docker or Kubernetes in our cloud and in yours. Point vendors sell you one layer and leave the integration to you, which is where the latency, the cost and the three in the morning debugging live.

What are the components of the Xebit stack?

  1. 01

    Agent SDK

    What your team builds agents against.

  2. 02

    Bridge · SFU

    Real time audio routing and fan out across SIP, WebRTC, WebSocket and gRPC, so a person can join an AI call from a browser. Sets your cost per node.

  3. 03

    Agent Server

    Agent and model session logic, on its own resource profile.

  4. 04

    Speech pipeline

    Speech to speech by default. Cascade when you want to pick each component.

  5. 05

    Orchestration

    Turn handling, barge in, business rules enforced in the call flow.

  6. 06

    Scheduling & campaigns

    Dialling plans, retries, list management, pacing.

  7. 07

    Observability

    Per call and per node metrics, transcripts, event logs, replay, and an SRE agent that opens incidents, writes the RCA and proposes a fix for you to approve.

  8. 08

    Control plane

    Auth, tokens, dispatch. In front of the media path, not inside it.

  9. 09

    SIP gateway

    Your carrier trunks, over standard SIP and WebSocket.

What path does a call take?

Media flows through the gateway, the Bridge and the Agent Server. The control plane handles auth, tokens and dispatch in front of the media path, not inside it. Orchestration enforces turn handling, barge in and business rules in the call flow, and observability records every call and node.
  1. 01

    Your carrier

    PSTN call arrives on trunks you already own

  2. 02

    SIP gateway

    Standard SIP and WebSocket ingress

  3. 03

    Bridge · SFU

    Real time audio routing for the session

  4. 04

    Agent Server

    Agent and model session logic

  5. 05

    Speech pipeline

    Speech to speech by default, or cascade

Which protocols does Xebit support?

Every way audio arrives, into one Bridge. Phone callers, browser and app users, telephony platforms and your own services all join the same live session, and the Bridge routes and fans the audio out between them in real time.
Phone callersRTP OVER SIPBrowser and app usersWEBRTCPlatforms and serversWEBSOCKETYour backend servicesGRPCAI agentAgent ServerA person joins livefrom a browser, WebRTCRecording & observabilityevery call, every nodeXEBITBridge · SFUone live sessionAudioSocketON THE ROADMAPQUICON THE ROADMAPMoQON THE ROADMAP

Mix protocols on one call: a customer rings in over SIP, the AI agent answers, and a team lead listens in from a browser over WebRTC. One session, one Bridge, audio fanned out to everyone in real time.

In production

RTP over SIP

Phone callers

The telephone network's own language. Your carrier trunks and PBX speak it today, so calls arrive without a middleman.

Best for

  • Inbound and outbound PSTN calls
  • Your existing carrier and numbers
  • Contact centre and PBX transfers

SIP signalling · RTP media · G.711 / Opus

WebRTC

Browser and app users

Real time audio straight from a browser or mobile app, with echo cancellation and jitter handling built in.

Best for

  • Talk buttons on your website and app
  • A person joining an AI call from a browser
  • Supervisors listening in live

UDP · SRTP · Opus

WebSocket

Platforms and servers

Audio frames over one persistent connection. The simplest way for a server, or a telephony platform that streams call audio, to plug in.

Best for

  • Telephony platforms that stream call audio
  • Server to server audio
  • Custom clients and quick prototypes

TCP · TLS · PCM or µ-law frames

gRPC

Your backend services

Typed, bidirectional streaming between services. Built for internal pipelines that need a strict contract and high throughput.

Best for

  • Backend to backend audio pipelines
  • Analytics and transcription taps
  • Service meshes inside your network

HTTP/2 · bidirectional streams · Protobuf

On the roadmap

AudioSocket

A lean TCP audio protocol from Asterisk: connect an existing Asterisk PBX without a SIP trunk.

QUIC

UDP transport with TLS 1.3 built in and no head-of-line blocking; holds up when mobile networks switch.

MoQ

Media over QUIC, the emerging IETF standard for low latency live media fan-out at scale.

Where does audio go in each deployment model?

Three deployments. We tell you where the audio goes in each.
Caller
Your carrier
Xebit cloud
Xebit platform
Model provider

Where audio goes: Audio leaves your network: it reaches Xebit's infrastructure and the model provider.