Skip to content
Mank Yazılım
enTürkçe: tr

Technology & Security

Technology and security

Mank Voice AI is built from modular layers. Each layer is configured to integrate with the organization's existing systems while data control stays bound to the organization's own policy.

Modular architecture

The STT, understanding and orchestration, enterprise action and TTS layers scale independently and can be used separately.

L1

Speech recognition (STT)

L2

Understanding and orchestration

L3

Enterprise action layer

L4

Speech synthesis (TTS)

The five-stage technology flow

  1. 01

    Listens

    Converts speech to text with low latency using Turkish-specialized STT under real call conditions.

  2. 02

    Understands

    Extracts intent, topic and required data fields, and evaluates them against the rule set defined by the organization.

  3. 03

    Takes action

    Runs queries or transactions in your systems through authorized API and tool calls.

  4. 04

    Responds

    Delivers the outcome in a consistent, controlled voice suited to the rhythm of Turkish, and hands off to a human when required.

  5. 05

    Measures

    Makes the conversation summary, structured data and process metrics reportable.

Integration with existing systems

Telephony, CRM, core applications, identity management and reporting tools connect over APIs. The goal is to run on top of existing systems, not replace them.

Data-control principles

  • Processing location, retention period and access rights are configured per project.
  • The scope of data used for model adaptation is defined together with the organization and set out contractually.
  • Separate retention and masking rules can be defined for audio, transcripts and derived data.
  • In on-premise and private-cloud deployments, data can be configured to remain within the organization's own boundary.
  • Integrations are built on least-privilege access, reaching only the endpoints they require.

Deployment models

On-premise

Data control
Data and models stay in the organization's own data centre; access is governed by the organization's own authorization structure.
Isolation
The highest level of network isolation; outbound connectivity requirements are defined by the organization.
Operating responsibility
Hardware, capacity and operations sit with the organization; Mank provides installation, adaptation and version support.
Best suited when
When data residency and network isolation requirements are the deciding factor.

Private cloud

Data control
Runs in the organization's own cloud account, in a dedicated environment governed by the organization's policies.
Isolation
A tenant-isolated environment; network and identity controls follow the organization's cloud configuration.
Operating responsibility
Capacity elasticity is higher; operational responsibility can be shared between the organization and Mank.
Best suited when
When scalability and institutional control are both required.

Mank infrastructure in Türkiye

Data control
The service is delivered from Mank infrastructure located in Türkiye; the scope of data processing is defined contractually.
Isolation
Per-organization isolated configuration; access and retention periods are defined per project.
Operating responsibility
Operations and version management sit with Mank; the organization's infrastructure investment is lowest here.
Best suited when
When a fast start and low operational overhead are the priority.

None of the three models is universally superior. The right model follows from the organization's data policy, existing infrastructure, expected scale and operating capacity.

The PoC-to-production working model

  1. 01

    Discovery

  2. 02

    Success criteria

  3. 03

    PoC

  4. 04

    Integration

  5. 05

    Controlled production

  6. 06

    Continuous improvement

AI is not a miracle. Set up correctly, running on the right data and monitored against the right measures, it is an operational tool.

Discuss the Technical Architecture