We won the DIMOP Plusz grant: an intelligent voice-based customer service platform

We have been awarded HUF 14,534,144 in non-repayable funding under the DIMOP_PLUSZ-1.1.2/A-24 call to develop an intelligent voice-based customer service platform. The project officially started today, 1 July 2025, and it is the one our telecom and backend work of recent years has been building towards. Below are the grant details and the planned technical scope.

Co-financed by the European Union.

Grant details

• Call: DIMOP_PLUSZ-1.1.2/A-24
• Project identifier: DIMOP_PLUSZ-1.1.2/A-24-2025-00236
• Project title: Development of an intelligent voice-based customer service platform
• Amount of funding: HUF 14,534,144 (14.53 million forints), non-repayable grant
• Funding intensity: 70%
• Implementation period: 1 July 2025 - 14 September 2026

The company covers the remaining 30% from its own funds. For a micro-company that is a significant commitment, which is why we spent the past months working out the plan and milestones in detail.

The same request, every time

In recent years we have worked with SIP telephony, PSTN integration, SMS and WhatsApp channels, and multi-tenant SaaS systems. Every customer support project produced the same request: a share of inbound calls (appointment booking, opening hours, simple status checks, taking messages) should be handled automatically, with no human involved, around the clock and in several languages.

Progress in speech recognition, large language models and speech synthesis has made that technically possible. What is missing is a platform that connects those components to the ordinary telephone network and that a small or medium-sized business can set up itself, without a developer. That is what we are building.

The committed scope

The project has seven main components.

A multi-tenant SaaS platform. One infrastructure serves many customers, with data, configuration and billing separated per tenant. It builds on the multi-tenant patterns described in our earlier posts: shared schema, row-level security, per-tenant limits.

A no-code flow editor. Customers assemble the course of a call in a visual editor in the browser: greeting, questions, branches, data collection, handover to a human. No programming is required. The flow definition is stored in the database and drives the assistant during the call.

An STT-LLM-TTS processing chain. Continuous speech recognition (speech-to-text) turns incoming audio into text, a large language model interprets it and decides the next step, and speech synthesis (text-to-speech) speaks the reply. Every link in the chain can be swapped out. Cutting latency is one of the project’s central technical tasks.

SIP and PSTN integration. The platform receives and places calls on real phone numbers over a SIP trunk, built on our own PSTN bridge component. Call audio flows to the processing chain in real time, and back.

Call log and CSV export. Each call produces a transcript, a summary and structured data, such as a booked appointment. These are searchable in the interface and can be exported as CSV into existing systems.

Usage-based pricing. There is no package to pay for up front; customers pay for the calls actually handled. Billing uses the usage event model already proven in Abisearch.

GDPR-compliant EU operation. Recordings, transcripts and personal data are stored encrypted on servers inside the European Union, with a configurable retention period, a privacy notice and terms of service.

Tested on real calls

Development follows our usual setup: a Docker-based environment, automated tests, staging and production kept apart. Voice systems are new territory for testing, so on top of unit tests we run the call flows end to end with real SIP calls, automatically.

We will report progress on this blog regularly: what we learn about cutting latency, the pitfalls of streaming speech recognition, and how a language model copes with the noise of a real phone call. The tone will stay the usual engineering one. The grant does not change what we write or how.

We thank the Hungarian Government and the European Union for their support!