For contact centers

Turn every call into a transcript, a summary and a category — privately.

Calls contain the clearest signal about your customers, and some of the most sensitive data you hold. Transcribe with Whisper-compatible speech models, then summarise, classify and analyse sentiment with a language model — on infrastructure with configurable retention.

Talk to an Engineer View Pricing

The problem

What gets in the way today.

Manual call notes are inconsistent and time-consuming
Quality teams can only review a small sample of calls
Complaint trends surface weeks too late
Recordings contain personal data that needs careful handling

Use cases

What teams build with it.

Transcription

Batch or near-real-time transcription in multiple languages.

Summarisation

Structured after-call summaries written into your CRM.

Call classification

Reason-for-call and outcome tagging for reporting.

Sentiment analysis

Flag frustrated customers for follow-up.

Complaint categorisation

Group complaints into themes your teams can act on.

Agent assistance

Suggested answers from your knowledge base during or after calls.

How it fits

Where it sits in your architecture.

Your application keeps running where it runs today. It calls a managed endpoint; we operate everything behind it.

Call recording
Speech-to-text
Summary & classification
CRM / QA dashboard

Recommended plans

Where most teams start.

Fixed monthly plans. All prices exclude VAT.

Compare all plans

Growth

Managed AI Node

Recommended

A dedicated, fully managed AI endpoint. Our flagship.

From€699/ month

Launch pricing

Deploy Managed AI

Dedicated 96 GB Apple Silicon environment
Model installation and configuration
OpenAI-compatible endpoint
Monitoring and alerting
Model and system updates
Secure API gateway
Backup configuration
Technical support
Deployment assistance

Recommended models

Models that suit this workload.

Model availability depends on licensing, memory requirements and deployment configuration.

Browse the model catalog

Whisper Large v3 Turbo

Available

OpenAI (open-weight) · 809M

Speech-to-text model for transcription in many languages, served via a Whisper-compatible endpoint.

SpeechMemory class XS

View in model catalog

Whisper Large v3

Private Node

OpenAI (open-weight) · 1.55B

Full-size Whisper model for highest transcription accuracy on dedicated capacity.

SpeechMemory class XS

View in model catalog

Qwen3 14B

Private Node

Alibaba Qwen · 14B (dense)

Balanced mid-size model — good quality per gigabyte for classification, summarisation and chat.

ChatMemory class S

View in model catalog

Considerations

Worth knowing before you start.

Personal data

Call audio is personal data. Review Data Processing and agree retention before go-live.

Dedicated capacity for volume

High call volumes are usually more economical on a dedicated node.

Inform callers

Your existing call-recording notices and legal basis still apply.

Data & location

Transparent about where your data is processed.

Designed to support GDPR-conscious deployments. Customers remain responsible for determining the appropriate legal basis for their workloads.

Infrastructure region: Georgia; Outside the EEA. All compute and model storage currently run here.
Commercial operations: Germany / Europe; Sales, contracts, onboarding and customer communication.
International data transfer: Safeguards available; For workloads involving EEA personal data, appropriate contractual and technical safeguards may be required.

EU region: not currently available. Read how we handle data processing — and speak with us about your data classification before deployment.

See how other teams use the platform.

Tell us what you are building.

An engineer reviews your requirements and comes back with a concrete proposal — model, plan and architecture.

Talk to an Engineer View Pricing