Skip to content
Ittisal
Hosted in the GCC

A contact centre that answers in your customer's dialect

Voice, WhatsApp and autonomous agents on one routing engine. The flow engine opens the media and inference planes only when a node needs them, and the whole stack — recognition included — runs inside your own data boundary.

10
channel types
130
Studio node types
< $0.01
per AI voice minute

audio stream plane · inference core · agent surfaces — drag to rotate

Data residency

Your audio does not have to leave the country

Databases, media servers, object storage, the event bus and the inference tier all deploy on infrastructure you control. Channel providers are the only mandatory egress; recognition, generation and synthesis each have an in-boundary counterpart selected per flow.

In region

UAE · Dubai

Primary tenancy. Media, recognition and recordings stay on in-country hosts.

In region

Qatar · Doha

Second hosting region for tenants under Qatari data rules.

Boundary

Zero audio egress

Select the self-hosted recognition tier and no call audio crosses your perimeter.

Isolation

Per-tenant keys

Credentials and channel tokens encrypted per tenant, rotated outside the image.

AES-256-GCM at restTLS on every legOIDC · SAML · TOTPHMAC webhook guardsSOC 2 style audit trail
Platform

Three parts, one contract

Ittisal Studio

Seven archetypes across seven channels. The archetype decides which nodes exist, the channel removes the rest, and an AI co-pilot builds the first draft of the graph from a written brief.

130 node types · dry-run self-healing

Voice AI engine

Audio forks off the live call leg and streams into recognition while the caller is still speaking. Managed or self-hosted recognition, generation and synthesis, chosen per flow.

streaming turns · barge-in aware

Omnichannel routing

One capacity budget per agent, spent by channel: a call takes all of it, a WhatsApp thread a quarter, an email ticket a tenth. Skills and language are matched before assignment.

100 points · skill and language match

A production graph, mid-call

pulses follow execution order
STARTIncoming callLANGUAGE_DETECTSwitch AR / ENLLM_VOICE_AGENTAI voice agentmedia fork openHTTP_REQUESTCRM webhookHANDOFF_TO_HUMANAgent queueCHANNEL_SWITCHDeflect to WhatsAppno agent available · deflection branchnode types shown are canonical BlockRegistry types · dashed node is on the roadmap
How it runs

From ringing to resolution

trunk · recognition · orchestration · desktop — drag to rotate

01

Caller arrives

The trunk hands the call to the media server, which asks the flow engine what to do with this number.

02

Speech to text

Reaching a voice-agent node opens an audio fork. Each leg streams separately, tagged by speaker.

03

LLM orchestration

Intent, tenant knowledge and guardrails decide the turn. Tool calls hit your CRM through the graph, not a side channel.

04

Agent desktop

On escalation the agent receives the live transcript, sentiment and a disposition draft — no repeated questions.

Governance

Tenant context is forced, not trusted

Every request resolves its tenant once and then runs under it. A hint that disagrees with the session is refused and logged; only platform system roles may cross a boundary, and the target is verified before the request proceeds.

Request the security pack

Encrypted audio streams

Call legs and recognition forks are carried over TLS; recordings are encrypted at rest in your own object store.

Local GCC hosting

Deploy on in-country infrastructure, including the inference tier. No component requires an external region to function.

Zero data egress

With the self-hosted recognition and generation tiers selected, the only outbound traffic is to the channel providers your customers already use.

Commercials

Quote-led licensing, metered usage

Enterprise licence

Priced per deployment on residency model, channel mix and seat count. Issued and enforced through the licence server.

Usage on top

Per-minute and per-message rates that step down with volume. Metering derives from the flow graph, so a line on the invoice maps to the nodes that ran.

AI voice pipeline
< $0.01
per minute, recognition through synthesis

Deflected minutes cost a fraction of agent-served ones, and the self-hosted tier turns a variable provider cost into fixed infrastructure at scale.

Get started

See it answer a live call

A scoped pilot on one queue, with your dialect, your CRM and a success metric agreed in advance.

Booking hoursSunday to Thursday, 09:00–18:00 GST (UTC+4)
ResponseWe reply within two working days

Business email required (free email domains like gmail.com are not accepted)

International format: +971, +966, +973, +974, +968, +965

Demo requests only. We typically respond within one business day.