Skip to content
Callmenta
CALLAII Pro
A model trained on your own data

Not just humans, your AI voice agents get scored too

CALLAII Pro scores responses from your human agents and AI agents against the same quality framework. Turn approved evaluations into one-click training data - ALPACA, ChatML or JSONL. Fine-tune your own model on your own real operational data.

Runs on our own GPU
CALLAII Pro · export queue
● 6 APPROVED
Approved Calls · Export Queue
#48291 May 22, 2026 Human 4.8 ✓ approved
#48292 May 22, 2026 AI Voice Agent 4.6 ✓ approved
#48293 May 22, 2026 Human 4.9 ✓ approved
#48294 May 23, 2026 AI Voice Agent 3.2 ✕ rejected
#48295 May 23, 2026 Human 4.7 ✓ approved
#48296 May 23, 2026 AI Voice Agent 4.4 ✓ approved
ALPACA
ready
ChatML
ready
JSONL
ready
Hands sorting through printed call logs on a desk
Setup and pricing

Your model runs on your own server

CALLAII Pro is an Edge deployment. The model is trained on your GPU server and runs there; your conversation data does not leave your organisation.

Covered by Edge
One-off

On-site setup and go-live

90.000 ₺

Installation on your GPU server, data preparation and cleaning, the first training run, validation and go-live.

Monthly

Maintenance and updates

22.000 ₺

Model monitoring, version upgrades and support. There is no hosting fee because the hardware is yours.

Per run

Retraining

30.000 ₺

We recommend it every three months; it is not mandatory.

If you do not have your own GPU server, we can also run your Pro model on our hardware. In that case an activation fee replaces the installation fee and the monthly amount covers hosting. We decide together during discovery which one suits you.

Learning Loop

Collect, approve, train

Every day, operational data flows in and - with supervisor sign-off - becomes clean training data. Your own LLM grows on your own floor.

  1. Collect

    Every call (human agent + AI voice agent) is scored in a single panel. Soft-skill rubric + industry weights.

  2. Approve

    The supervisor approves or rejects to surface only high-quality examples. Built-in appeal mechanism for a second pass.

  3. Train

    One-click export in ALPACA / ChatML / JSONL. Fine-tune your own voice agent LLM on your own data.

Training Formats

Three formats, one click

Your approved evaluations export ready-to-train in all three standard formats of the LLM ecosystem.

ALPACA

ALPACA

Standard for instruction-tuned LLM training

ChatML

ChatML

OpenAI-compatible multi-turn dialogue

JSONL

JSONL

General-purpose line-based training data

Who It's For

If you develop AI voice agents CALLAII Pro was written for you

In-house voice agent teams

You're training your own voice agent model and need real-world data from the floor. CALLAII Pro turns approved human and AI voice agent responses into clean training data.

Enterprise operations leaders

Running multiple AI voice agents? See which model actually performs - on an objective, side-by-side score.

Data science researchers

Access to Turkish contact center datasets was always a wall. Now you can generate a KVKK-compliant, anonymised dataset from real operations on demand.

A hand closing the front panel of a server cabinet inside an office
Impact We Measured

Impact you can expect from Pro

3×faster fine-tuning iterations
+18 pointson the Turkish contact center benchmark
100%KVKK + GDPR compliant pipeline
< 5 minexport to training-ready data

The figures come from our own internal measurements and pilot studies. They vary by operation and dataset and do not guarantee your own result.

Why Unique

The same yardstick, one panel

Scores your human agents and, if you have them, your AI voice agents with the same quality form, and turns the approved evaluations straight into training data.

Common questions

Frequently asked questions about CALLAII Pro

What is CALLAII Pro?

CALLAII Pro is the advanced package that lets you grow your own AI agent and train your own model.

How do I train my own model?

The right training data is generated automatically by our system from your real call data. With these ready-made sets you can train and customize your own model.

How is it different from CALLAII Assistant?

Assistant delivers ready-to-use AI coaching. Pro focuses on training and owning your own model and AI agent.

Who is it for?

It suits contact center operations that want to build their own AI capability and that prioritize data ownership and customization.

Do I own my data and model?

Yes. The whole point of Pro is to develop your own AI while the training data and model stay with you. The process is KVKK and GDPR compliant.

Your model runs on your own server

CALLAII Pro is an Edge deployment. The model is trained on your GPU server and runs there; your conversation data does not leave your organisation.