Skip to main content

AI service

Speaker recognition / verification

We provide Speaker recognition / verification at any scale, on a private cluster dedicated to you — from a single GPU to a hundred, on premise or in any cloud.

If you need such a service please contact us.

A voice is matched against speakers enrolled in a database you hold and control, returning a similarity score against a threshold you set. Enrolment, retention and deletion are governed by your rules inside your own deployment. Scores are returned rather than verdicts, so the accept threshold stays a decision you make. Enrolled voiceprints are never shared between deployments.

You can use the models we operate or bring your own model and we run it on your cluster. Work arrives as an API call, a batch over a folder or bucket, or a resident on-premise service, and results return as structured output with a per-job audit record.

More services